ComfyUI
ComfyUI copied to clipboard
Published
3 days ago
•
comfyanonymous
comfyanonymous
I had a hard time using ComfyUI on Windows 11 previously... so this is what I changed...
I installed Ubuntu but running from Windows 11 itself.
I am not sure if there are any real benefits to doing this... as I have no idea how to run benchmarks to verify if there are any improvement gains.
but... since i technically have a linux machine now, i can technically get flash attention 2 running.
even though it is not supported in windows.
can someone direct me how i can benchmark and verify if running ComfyUI in WSL2 via Ubuntu have any speed gains or improvements or something?
okay. so first issue that i encounter is the following:
[START] Security scan
DEPRECATION: Loading egg at /home/ks/comfy/venv/lib/python3.12/site-packages/flash_attn-2.6.3-py3.12-linux-x86_64.egg is deprecated. pip 24.3 will enforce this behaviour change. A possible replacement is to use pip for package installation. Discussion can be found at https://github.com/pypa/pip/issues/12330
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-09-14 21:56:00.044347
** Platform: Linux
** Python version: 3.12.3 (main, Jul 31 2024, 17:43:48) [GCC 13.2.0]
https://github.com/pypa/pip/issues/12330
i have no idea what i need to do. can i simply reinstall based on the suggested steps?
i am unsure.
from the rest of the startup process... i can't actually tell if there's any difference...
i just wish i can figure out how to get rid of all the warnings... they are causing a lot of anxiety.
Prestartup times for custom nodes:
0.0 seconds: /home/ks/ComfyUI/custom_nodes/rgthree-comfy
15.6 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI-Manager
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.6.0.dev20240913+cu124
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
Using pytorch cross attention
[Prompt Server] web root: /home/ks/ComfyUI/web
/home/ks/comfy/venv/lib/python3.12/site-packages/kornia/feature/lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
@torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `/home/ks/ComfyUI/custom_nodes/was-node-suite-comfyui/was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 218 nodes successfully.
"Art is the breath of life." - Liza Donnelly
### Loading: ComfyUI-Manager (V2.50.3)
### ComfyUI Revision: 2691 [369a6dd2] | Released on '2024-09-13'
[rgthree] Loaded 42 epic nodes.
[rgthree] NOTE: Will NOT use rgthree's optimized recursive execution as ComfyUI has changed.
/home/ks/comfy/venv/lib/python3.12/site-packages/diffusers/utils/outputs.py:63: FutureWarning: `torch.utils._pytree._register_pytree_node` is deprecated. Please use `torch.utils._pytree.register_pytree_node` instead.
torch.utils._pytree._register_pytree_node(
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.6.0.dev20240913+cu124
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
[Crystools INFO] Crystools version: 1.16.6
[Crystools INFO] CPU: AMD Ryzen 5 5600X 6-Core Processor - Arch: x86_64 - OS: Linux 5.15.153.1-microsoft-standard-WSL2
[Crystools INFO] Pynvml (Nvidia) initialized.
[Crystools INFO] GPU/s:
[Crystools INFO] 0) NVIDIA GeForce RTX 4080 SUPER
[Crystools INFO] NVIDIA Driver: 560.81
Import times for custom nodes:
0.0 seconds: /home/ks/ComfyUI/custom_nodes/websocket_image_save.py
0.0 seconds: /home/ks/ComfyUI/custom_nodes/cg-use-everywhere
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI_Noise
0.0 seconds: /home/ks/ComfyUI/custom_nodes/cg-noisetools
0.0 seconds: /home/ks/ComfyUI/custom_nodes/comfy-image-saver
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI-Custom-Scripts
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI_UltimateSDUpscale
0.0 seconds: /home/ks/ComfyUI/custom_nodes/rgthree-comfy
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI-post-processing-nodes
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI-GGUF
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI-KJNodes
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI_essentials
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI-GlifNodes
0.0 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/ks/ComfyUI/custom_nodes/ComfyUI-Crystools
0.9 seconds: /home/ks/ComfyUI/custom_nodes/was-node-suite-comfyui
Starting server
To see the GUI go to: http://127.0.0.1:8188
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
This issue is being marked stale because it has not had any activity for 30 days. Reply below within 7 days if your issue still isn't solved, and it will be left open. Otherwise, the issue will be closed automatically.
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
Okay i am in the process of installing flash attention on my windows 11 pc
ddd insightface ven
Sat Oct 26 17:29:25 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:0B:00.0 On | N/A |
| 0% 37C P0 18W / 320W | 1351MiB / 16376MiB | 9% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 435 G /Xwayland N/A |
+-----------------------------------------------------------------------------------------+
VIRTUAL_ENV=/home/ks/ven
VIRTUAL_ENV_PROMPT=(ven)
ddd insightface ven
CODEOWNERS app comfyui.prev2.log fix_torch.py models pytest.ini tests
CONTRIBUTING.md comfy comfyui_screenshot.png folder_paths.py new_updater.py requirements.txt tests-unit
LICENSE comfy_execution cuda_malloc.py input node_helpers.py script_examples user
README.md comfy_extras custom_nodes latent_preview.py nodes.py server.py utils
__pycache__ comfyui.log execution.py main.py notebooks styles web
api_server comfyui.prev.log extra_model_paths.yaml.example model_filemanager output temp
on bash ven 3.12.3 master ≡ ?1 0ms
╭─ 17:29:26 | 26 Oct, Saturday | in ven comf
╰─❯ python main.py
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-10-26 17:29:34.939822
** Platform: Linux
** Python version: 3.12.3 (main, Sep 11 2024, 14:17:37) [GCC 13.2.0]
** Python executable: /home/ks/ven/bin/python
** ComfyUI Path: /home/ks/ven/comf
** Log path: /home/ks/ven/comf/comfyui.log
Prestartup times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.9 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
Using xformers cross attention
[Prompt Server] web root: /home/ks/ven/comf/web
/home/ks/ven/lib/python3.12/site-packages/kornia/feature/lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
@torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
### Loading: ComfyUI-Manager (V2.51.8)
### ComfyUI Revision: 2787 [d605677b] | Released on '2024-10-25'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[comfy_mtb] | INFO -> loaded 86 nodes successfuly
[comfy_mtb] | INFO -> Some nodes (2) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information.
[ReActor] - STATUS - Running v0.5.1-b2 in ComfyUI
Torch version: 2.5.0+cu124
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
[rgthree-comfy] Loaded 42 exciting nodes. 🎉
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `/home/ks/ven/comf/custom_nodes/was-node-suite-comfyui/was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 218 nodes successfully.
"The artist's world is limitless. It can be found anywhere, far from where he lives or a few feet away. It is always on his doorstep." - Paul Strand
FaceDetailer: Model directory already exists
FaceDetailer: Model already exists
Import times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/websocket_image_save.py
0.0 seconds: /home/ks/ven/comf/custom_nodes/Skimmed_CFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_JPS-Nodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-AutomaticCFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-instantId-faceswap
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Custom-Scripts
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Image-Saver
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-KJNodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui_face_parsing
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-NuA-FlashFace
0.0 seconds: /home/ks/ven/comf/custom_nodes/facerestore_cf
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_ExtraModels
0.3 seconds: /home/ks/ven/comf/custom_nodes/comfyui-reactor-node
0.3 seconds: /home/ks/ven/comf/custom_nodes/comfyui-faceless-node
0.3 seconds: /home/ks/ven/comf/custom_nodes/DZ-FaceDetailer
0.5 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Facerestore-Tensorrt
0.6 seconds: /home/ks/ven/comf/custom_nodes/was-node-suite-comfyui
0.8 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-SUPIR
2.4 seconds: /home/ks/ven/comf/custom_nodes/comfy_mtb
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/extension-node-map.json [DONE]
got prompt
model weight dtype torch.float16, manual cast: None
model_type EPS
Using xformers attention in VAE
Using xformers attention in VAE
Requested to load SDXLClipModel
Loading 1 new model
loaded completely 0.0 1560.802734375 True
loaded straight to GPU
Requested to load SDXL
Loading 1 new model
loaded completely 0.0 4897.0483474731445 True
[ReActor] 17:30:13 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
got prompt
0: 640x480 1 face, 55.8ms
0: 640x480 1 face, 55.8ms
Speed: 4.5ms preprocess, 55.8ms inference, 15.3ms postprocess per image at shape (1, 3, 640, 480)
Speed: 4.5ms preprocess, 55.8ms inference, 15.3ms postprocess per image at shape (1, 3, 640, 480)
Requested to load SDXLClipModel
Loading 1 new model
loaded completely 0.0 1560.802734375 True
Requested to load SDXL
Loading 1 new model
loaded completely 0.0 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:51<00:00, 1.16it/s]
Requested to load AutoencoderKL
Loading 1 new model
loaded completely 0.0 159.55708122253418 True
[ReActor] 17:31:37 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 17:31:44 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 17:31:44 - STATUS - Analyzing Source Image...
[ReActor] 17:31:47 - STATUS - Trying to halve 'det_size' parameter
[ReActor] 17:31:53 - STATUS - Analyzing Target Image...
[ReActor] 17:31:57 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 17:31:57 - STATUS - OK - Detected Gender matches Condition
[ReActor] 17:32:00 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 17:32:00 - STATUS - OK - Detected Gender matches Condition
[ReActor] 17:32:00 - STATUS - Swapping...
[ReActor] 17:32:00 - STATUS - Face Boost is enabled
[ReActor] 17:32:01 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 17:32:04 - STATUS - --Done!--
[ReActor] 17:32:04 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 17:32:21 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 1,646,826,258
VRAMdebug: free memory after: 1,613,767,442
VRAMdebug: freed memory: -33,058,816
Prompt executed in 150.53 seconds
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:53<00:00, 1.12it/s]
[ReActor] 17:33:33 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 17:33:37 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 17:33:37 - STATUS - Using Hashed Source Face(s) Model...
[ReActor] 17:33:37 - STATUS - Analyzing Target Image...
[ReActor] 17:33:37 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 17:33:37 - STATUS - OK - Detected Gender matches Condition
[ReActor] 17:33:37 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 17:33:37 - STATUS - OK - Detected Gender matches Condition
[ReActor] 17:33:37 - STATUS - Swapping...
[ReActor] 17:33:37 - STATUS - Face Boost is enabled
[ReActor] 17:33:38 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 17:33:39 - STATUS - --Done!--
[ReActor] 17:33:39 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 17:33:48 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 5,540,433,906
VRAMdebug: free memory after: 5,540,433,906
VRAMdebug: freed memory: 0
Prompt executed in 92.59 seconds
got prompt
Killed
on bash ven 3.12.3 master ≡ ?1 5m 5s 251ms
╭─ 17:34:39 | 26 Oct, Saturday | in ven comf
╰─❯
if you can see, currently without flash attention and using xformers, my image generations are about 150 seconds or so...
the other window is still installing flash-attn as i type this.
let's see if it makes any difference once it is installed...
i am assuming once it is installed i don't have to do anything... and just run comfy as usual.
and it completed the installation.
and it states that it has:
Successfully built flash-attn
Installing collected packages: flash-attn
Successfully installed flash-attn-2.6.3
You are kidding me right?
that's all i got to do and now my image generation based on my existing workflows... wiithout any other special modification...
from the normal 150seconds per generation...
i shaved off 100seconds just like that?????????????????
ddd insightface ven
Sat Oct 26 19:08:12 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:0B:00.0 On | N/A |
| 0% 37C P0 18W / 320W | 1157MiB / 16376MiB | 8% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 435 G /Xwayland N/A |
+-----------------------------------------------------------------------------------------+
VIRTUAL_ENV=/home/ks/ven
VIRTUAL_ENV_PROMPT=(ven)
ddd insightface ven
CODEOWNERS app comfyui.prev2.log fix_torch.py models pytest.ini tests
CONTRIBUTING.md comfy comfyui_screenshot.png folder_paths.py new_updater.py requirements.txt tests-unit
LICENSE comfy_execution cuda_malloc.py input node_helpers.py script_examples user
README.md comfy_extras custom_nodes latent_preview.py nodes.py server.py utils
__pycache__ comfyui.log execution.py main.py notebooks styles web
api_server comfyui.prev.log extra_model_paths.yaml.example model_filemanager output temp
on bash ven 3.12.3 master ≡ ?1 0ms
╭─ 19:08:12 | 26 Oct, Saturday | in ven comf
╰─❯ python main.py
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-10-26 19:08:19.317467
** Platform: Linux
** Python version: 3.12.3 (main, Sep 11 2024, 14:17:37) [GCC 13.2.0]
** Python executable: /home/ks/ven/bin/python
** ComfyUI Path: /home/ks/ven/comf
** Log path: /home/ks/ven/comf/comfyui.log
Prestartup times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.5 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
Using xformers cross attention
[Prompt Server] web root: /home/ks/ven/comf/web
/home/ks/ven/lib/python3.12/site-packages/kornia/feature/lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
@torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
### Loading: ComfyUI-Manager (V2.51.8)
### ComfyUI Revision: 2787 [d605677b] | Released on '2024-10-25'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[comfy_mtb] | INFO -> loaded 86 nodes successfuly
[comfy_mtb] | INFO -> Some nodes (2) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information.
[ReActor] - STATUS - Running v0.5.1-b2 in ComfyUI
Torch version: 2.5.0+cu124
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
[rgthree-comfy] Loaded 42 magnificent nodes. 🎉
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `/home/ks/ven/comf/custom_nodes/was-node-suite-comfyui/was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 218 nodes successfully.
"Success is not about being better than someone else. It's about being better than you used to be." - Unknown
FaceDetailer: Model directory already exists
FaceDetailer: Model already exists
Import times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/websocket_image_save.py
0.0 seconds: /home/ks/ven/comf/custom_nodes/Skimmed_CFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-AutomaticCFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_JPS-Nodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-instantId-faceswap
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Image-Saver
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Custom-Scripts
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-KJNodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui_face_parsing
0.0 seconds: /home/ks/ven/comf/custom_nodes/facerestore_cf
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-NuA-FlashFace
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_ExtraModels
0.1 seconds: /home/ks/ven/comf/custom_nodes/comfyui-reactor-node
0.2 seconds: /home/ks/ven/comf/custom_nodes/comfyui-faceless-node
0.3 seconds: /home/ks/ven/comf/custom_nodes/DZ-FaceDetailer
0.3 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Facerestore-Tensorrt
0.5 seconds: /home/ks/ven/comf/custom_nodes/was-node-suite-comfyui
0.6 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-SUPIR
1.7 seconds: /home/ks/ven/comf/custom_nodes/comfy_mtb
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/extension-node-map.json [DONE]
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/.cache/1742899825_extension-node-map.json [DONE]
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/.cache/1514988643_custom-node-list.json [DONE]
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/.cache/746607195_github-stats.json [DONE]
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/.cache/1742899825_extension-node-map.json [DONE]
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/custom-node-list.json [DONE]
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/.cache/1241942342_custom-node-list.json [DONE]
Install custom node 'Phi-3-mini in ComfyUI'
Install: ['https://github.com/ZHO-ZHO-ZHO/ComfyUI-Phi-3-mini']
Download: git clone 'https://github.com/ZHO-ZHO-ZHO/ComfyUI-Phi-3-mini'
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 7.0/7.0 [00:00<00:00, 8.66it/s]
Install: pip packages
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'transformers>=4.40.0']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Installation was successful.
After restarting ComfyUI, please refresh the browser.
Restarting... [Legacy Mode]
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-10-26 19:10:37.768441
** Platform: Linux
** Python version: 3.12.3 (main, Sep 11 2024, 14:17:37) [GCC 13.2.0]
** Python executable: /home/ks/ven/bin/python
** ComfyUI Path: /home/ks/ven/comf
** Log path: /home/ks/ven/comf/comfyui.log
Prestartup times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.5 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
Using xformers cross attention
[Prompt Server] web root: /home/ks/ven/comf/web
/home/ks/ven/lib/python3.12/site-packages/kornia/feature/lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
@torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
### Loading: ComfyUI-Manager (V2.51.8)
### ComfyUI Revision: 2787 [d605677b] | Released on '2024-10-25'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[comfy_mtb] | INFO -> loaded 86 nodes successfuly
[comfy_mtb] | INFO -> Some nodes (2) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information.
[ReActor] - STATUS - Running v0.5.1-b2 in ComfyUI
Torch version: 2.5.0+cu124
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
[rgthree-comfy] Loaded 42 fantastic nodes. 🎉
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `/home/ks/ven/comf/custom_nodes/was-node-suite-comfyui/was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 218 nodes successfully.
"Success usually comes to those who are too busy to be looking for it." - Henry David Thoreau
FaceDetailer: Model directory already exists
FaceDetailer: Model already exists
Import times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/websocket_image_save.py
0.0 seconds: /home/ks/ven/comf/custom_nodes/Skimmed_CFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-instantId-faceswap
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-AutomaticCFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_JPS-Nodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Image-Saver
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Custom-Scripts
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-faceless-node
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-KJNodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/facerestore_cf
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui_face_parsing
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-NuA-FlashFace
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_ExtraModels
0.1 seconds: /home/ks/ven/comf/custom_nodes/comfyui-reactor-node
0.2 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Facerestore-Tensorrt
0.2 seconds: /home/ks/ven/comf/custom_nodes/DZ-FaceDetailer
0.4 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-SUPIR
0.5 seconds: /home/ks/ven/comf/custom_nodes/was-node-suite-comfyui
0.6 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Phi-3-mini
1.3 seconds: /home/ks/ven/comf/custom_nodes/comfy_mtb
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/extension-node-map.json [DONE]
got prompt
model weight dtype torch.float16, manual cast: None
model_type EPS
Using xformers attention in VAE
Using xformers attention in VAE
Requested to load SDXLClipModel
Loading 1 new model
loaded completely 0.0 1560.802734375 True
Requested to load SDXL
Loading 1 new model
loaded completely 0.0 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:34<00:00, 1.75it/s]
Requested to load AutoencoderKL
Loading 1 new model
loaded completely 0.0 159.55708122253418 True
[ReActor] 19:24:08 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 19:24:13 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
0: 640x480 1 face, 31.9ms
0: 640x480 1 face, 31.9ms
Speed: 1.5ms preprocess, 31.9ms inference, 7.9ms postprocess per image at shape (1, 3, 640, 480)
Speed: 1.5ms preprocess, 31.9ms inference, 7.9ms postprocess per image at shape (1, 3, 640, 480)
[ReActor] 19:24:15 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 19:24:15 - STATUS - Analyzing Source Image...
[ReActor] 19:24:17 - STATUS - Trying to halve 'det_size' parameter
[ReActor] 19:24:21 - STATUS - Analyzing Target Image...
[ReActor] 19:24:24 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 19:24:24 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:24:24 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 19:24:24 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:24:24 - STATUS - Swapping...
[ReActor] 19:24:24 - STATUS - Face Boost is enabled
[ReActor] 19:24:25 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 19:24:26 - STATUS - --Done!--
[ReActor] 19:24:26 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 19:24:45 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 1,675,718,354
VRAMdebug: free memory after: 1,626,177,234
VRAMdebug: freed memory: -49,541,120
Prompt executed in 93.70 seconds
got prompt
model weight dtype torch.float16, manual cast: None
model_type EPS
Using xformers attention in VAE
Using xformers attention in VAE
Requested to load SDXLClipModel
Loading 1 new model
loaded completely 0.0 1560.802734375 True
Requested to load SDXL
Loading 1 new model
loaded completely 0.0 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:33<00:00, 1.77it/s]
Requested to load AutoencoderKL
Loading 1 new model
loaded completely 0.0 159.55708122253418 True
[ReActor] 19:25:45 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 19:25:48 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
0: 640x480 1 face, 7.5ms
0: 640x480 1 face, 7.5ms
Speed: 1.3ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 480)
Speed: 1.3ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 480)
[ReActor] 19:25:50 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 19:25:50 - STATUS - Analyzing Source Image...
[ReActor] 19:25:50 - STATUS - Trying to halve 'det_size' parameter
[ReActor] 19:25:50 - STATUS - Analyzing Target Image...
[ReActor] 19:25:50 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 19:25:50 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:25:50 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 19:25:50 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:25:50 - STATUS - Swapping...
[ReActor] 19:25:50 - STATUS - Face Boost is enabled
[ReActor] 19:25:50 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 19:25:51 - STATUS - --Done!--
[ReActor] 19:25:51 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 19:25:59 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 5,276,451,682
VRAMdebug: free memory after: 5,276,451,682
VRAMdebug: freed memory: 0
Prompt executed in 61.69 seconds
got prompt
loaded completely 7571.969965744019 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:33<00:00, 1.78it/s]
[ReActor] 19:26:44 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 19:26:47 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 19:26:47 - STATUS - Using Hashed Source Face(s) Model...
[ReActor] 19:26:47 - STATUS - Analyzing Target Image...
[ReActor] 19:26:47 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 19:26:47 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:26:47 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 19:26:47 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:26:47 - STATUS - Swapping...
[ReActor] 19:26:47 - STATUS - Face Boost is enabled
[ReActor] 19:26:47 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 19:26:48 - STATUS - --Done!--
[ReActor] 19:26:48 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 19:26:56 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 5,553,085,362
VRAMdebug: free memory after: 5,553,085,362
VRAMdebug: freed memory: 0
Prompt executed in 50.14 seconds
got prompt
loaded completely 7310.373362350464 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:34<00:00, 1.74it/s]
[ReActor] 19:27:39 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 19:27:42 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 19:27:42 - STATUS - Using Hashed Source Face(s) Model...
[ReActor] 19:27:42 - STATUS - Analyzing Target Image...
[ReActor] 19:27:42 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 19:27:42 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:27:42 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 19:27:42 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:27:42 - STATUS - Swapping...
[ReActor] 19:27:42 - STATUS - Face Boost is enabled
[ReActor] 19:27:42 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 19:27:43 - STATUS - --Done!--
[ReActor] 19:27:43 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 19:27:51 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 5,843,540,914
VRAMdebug: free memory after: 5,843,540,914
VRAMdebug: freed memory: 0
Prompt executed in 52.60 seconds
got prompt
loaded completely 7312.373362350464 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:35<00:00, 1.67it/s]
[ReActor] 19:28:36 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 19:28:39 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 19:28:39 - STATUS - Using Hashed Source Face(s) Model...
[ReActor] 19:28:39 - STATUS - Analyzing Target Image...
[ReActor] 19:28:39 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 19:28:39 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:28:39 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 19:28:39 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:28:39 - STATUS - Swapping...
[ReActor] 19:28:39 - STATUS - Face Boost is enabled
[ReActor] 19:28:39 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 19:28:39 - STATUS - --Done!--
[ReActor] 19:28:39 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 19:28:52 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 5,885,483,954
VRAMdebug: free memory after: 5,885,483,954
VRAMdebug: freed memory: 0
Prompt executed in 59.41 seconds
got prompt
loaded completely 7312.373362350464 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:33<00:00, 1.81it/s]
[ReActor] 19:29:35 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 19:29:38 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 19:29:38 - STATUS - Using Hashed Source Face(s) Model...
[ReActor] 19:29:38 - STATUS - Analyzing Target Image...
[ReActor] 19:29:38 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 19:29:38 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:29:38 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 19:29:38 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:29:38 - STATUS - Swapping...
[ReActor] 19:29:38 - STATUS - Face Boost is enabled
[ReActor] 19:29:38 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 19:29:39 - STATUS - --Done!--
[ReActor] 19:29:39 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 19:29:54 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 5,847,735,218
VRAMdebug: free memory after: 5,847,735,218
VRAMdebug: freed memory: 0
Prompt executed in 58.80 seconds
got prompt
loaded completely 7306.373362350464 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:34<00:00, 1.75it/s]
[ReActor] 19:30:39 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
[ReActor] 19:30:41 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 19:30:41 - STATUS - Using Hashed Source Face(s) Model...
[ReActor] 19:30:41 - STATUS - Analyzing Target Image...
[ReActor] 19:30:41 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 19:30:41 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:30:41 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 19:30:41 - STATUS - OK - Detected Gender matches Condition
[ReActor] 19:30:41 - STATUS - Swapping...
[ReActor] 19:30:41 - STATUS - Face Boost is enabled
[ReActor] 19:30:41 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 19:30:42 - STATUS - --Done!--
[ReActor] 19:30:42 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 19:30:48 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 5,841,443,762
VRAMdebug: free memory after: 5,841,443,762
VRAMdebug: freed memory: 0
Prompt executed in 50.94 seconds
got prompt
loaded completely 7290.373362350464 4897.0483474731445 True
12%|████████████▎ | 7/60 [00:04<00:29, 1.83it/s]
https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
from MS's hugging face it mentioned briefly.
flash_attn==2.5.8 <<--- it seems this is the only mention of flash_attn mentioned in any of the documentations...--->>
below i have updated to show my current flash-attn built from source after installing via pip.
How to Use
Phi-3 Mini-4K-Instruct has been integrated in the 4.41.2 version of transformers. The current transformers version can be verified with: pip list | grep transformers.
Examples of required packages:
**_flash_attn==2.5.8 <<--- it seems this is the only mention of flash_attn mentioned in any of the documentations...--->>_**
torch==2.3.1
accelerate==0.31.0
transformers==4.41.2
Phi-3 Mini-4K-Instruct is also available in [Azure AI Studio](https://aka.ms/try-phi3)
Tokenizer
Phi-3 Mini-4K-Instruct supports a vocabulary size of up to 32064 tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size.
https://github.com/comfyanonymous/ComfyUI/issues/3265#issuecomment-2054219986
this is the only other person who indicated a possibility on how the flash_attn is being used.
this is the only other person who indicated a possibility on how the flash_attn is being used.
2 things i gather:
- Where did my flash-attn build go? is it somewhere that xformers picked up along the way? what version of xformers do i have?
Try installing the flash-attention-2.3.6 py311 ada / sm_89 (not xformers) wheel from my link on the discussions page you posted on (yeah it's from last December, doesn't seem to matter). xformers builds flash-attn-2 in-tree instead of as a dependency and tosses it in an anonymously named .pyd file that nothing else can use.
- if i have an xformers that is not compatible i should be seeing an error too.
Torch (seems) to look for one in the base install via lazy module loading; the error is just misleading. I think I'm still using 2.3.6 because I built a newer version like 2.4.2 around february and tried installing it and something started complaining but xformers is on v2.5.6 now so a newer build might work unless torch requires a specific version.
let's take a look:
ddd insightface ven
Sun Oct 27 09:00:42 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:0B:00.0 On | N/A |
| 0% 39C P0 33W / 320W | 411MiB / 16376MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| No running processes found |
+-----------------------------------------------------------------------------------------+
VIRTUAL_ENV=/home/ks/ven
VIRTUAL_ENV_PROMPT=(ven)
ddd insightface ven
CODEOWNERS app comfyui.prev2.log folder_paths.py new_updater.py requirements.txt tests-unit
CONTRIBUTING.md comfy cuda_malloc.py input node_helpers.py script_examples user
LICENSE comfy_execution custom_nodes latent_preview.py nodes.py server.py utils
README.md comfy_extras execution.py main.py notebooks styles web
__pycache__ comfyui.log extra_model_paths.yaml.example model_filemanager output temp
api_server comfyui.prev.log fix_torch.py models pytest.ini tests
on bash ven 3.12.3 master ≡ ?1 -1 ╰─❯
╭─ 09:00:42 | 27 Oct, Sunday | in ven comf
╰─❯
╰─❯ nvidia-smi
Sun Oct 27 09:04:55 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:0B:00.0 On | N/A |
| 0% 40C P8 3W / 320W | 500MiB / 16376MiB | 1% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 447 G /Xwayland N/A |
+-----------------------------------------------------------------------------------------+
on bash ven 3.12.3 master ≡ ?1 -1 244ms
╭─ 09:04:55 | 27 Oct, Sunday | in ven comf
╰─❯ xformers --version
-bash: xformers: command not found
on bash ven 3.12.3 master ≡ ?1 -1 19ms
╭─ 09:23:18 | 27 Oct, Sunday | in ven comf
╰─❯ pip show xformers
Name: xformers
Version: 0.0.28.post2
Summary: XFormers: A collection of composable Transformer building blocks.
Home-page: https://facebookresearch.github.io/xformers/
Author: Facebook AI Research
Author-email: [email protected]
License:
Location: /home/ks/ven/lib/python3.12/site-packages
Requires: numpy, torch
Required-by:
on bash ven 3.12.3 master ≡ ?1 -1 684ms
╭─ 09:23:31 | 27 Oct, Sunday | in ven comf
╰─❯ pip show flash
WARNING: Package(s) not found: flash
on bash ven 3.12.3 master ≡ ?1 -1 202ms
╭─ 09:23:56 | 27 Oct, Sunday | in ven comf
╰─❯ pip show flash-attn
Name: flash_attn
Version: 2.6.3
Summary: Flash Attention: Fast and Memory-Efficient Exact Attention
Home-page: https://github.com/Dao-AILab/flash-attention
Author: Tri Dao
Author-email: [email protected]
License:
Location: /home/ks/ven/lib/python3.12/site-packages
Requires: einops, torch
Required-by:
on bash ven 3.12.3 master ≡ ?1 -1 422ms
╭─ 09:24:02 | 27 Oct, Sunday | in ven comf
╰─❯
on bash ven 3.12.3 master ≡ ?1 -1 202ms
╭─ 09:23:56 | 27 Oct, Sunday | in ven comf
╰─❯ pip show flash-attn
Name: flash_attn
Version: 2.6.3
Summary: Flash Attention: Fast and Memory-Efficient Exact Attention
Home-page: https://github.com/Dao-AILab/flash-attention
Author: Tri Dao
Author-email: [email protected]
License:
Location: /home/ks/ven/lib/python3.12/site-packages
Requires: einops, torch
Required-by:
on bash ven 3.12.3 master ≡ ?1 -1 422ms
╭─ 09:24:02 | 27 Oct, Sunday | in ven comf
╰─❯ pip show einops
Name: einops
Version: 0.8.0
Summary: A new flavour of deep learning operations
Home-page: https://github.com/arogozhnikov/einops
Author: Alex Rogozhnikov
Author-email:
License: MIT
Location: /home/ks/ven/lib/python3.12/site-packages
Requires:
Required-by: flash_attn, spandrel
on bash ven 3.12.3 master ≡ ?1 -1 408ms
╭─ 09:25:13 | 27 Oct, Sunday | in ven comf
╰─❯
on bash ven 3.12.3 master ≡ ?1 -1 279ms
╭─ 09:26:16 | 27 Oct, Sunday | in ven comf
╰─❯ pip show flash-attn
Name: flash_attn
Version: 2.6.3
Summary: Flash Attention: Fast and Memory-Efficient Exact Attention
Home-page: https://github.com/Dao-AILab/flash-attention
Author: Tri Dao
Author-email: [email protected]
License:
Location: /home/ks/ven/lib/python3.12/site-packages
Requires: einops, torch
Required-by:
on bash ven 3.12.3 master ≡ ?1 -1 390ms
╭─ 09:26:21 | 27 Oct, Sunday | in ven comf
╰─❯ pip show torch
Name: torch
Version: 2.5.0
Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration
Home-page: https://pytorch.org/
Author: PyTorch Team
Author-email: [email protected]
License: BSD-3-Clause
Location: /home/ks/ven/lib/python3.12/site-packages
Requires: filelock, fsspec, jinja2, networkx, nvidia-cublas-cu12, nvidia-cuda-cupti-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-runtime-cu12, nvidia-cudnn-cu12, nvidia-cufft-cu12, nvidia-curand-cu12, nvidia-cusolver-cu12, nvidia-cusparse-cu12, nvidia-nccl-cu12, nvidia-nvjitlink-cu12, nvidia-nvtx-cu12, setuptools, sympy, triton, typing-extensions
Required-by: accelerate, bitsandbytes, fairscale, flash_attn, kornia, lpips, open_clip_torch, pytorch-lightning, spandrel, timm, torch_tensorrt, torchaudio, torchmetrics, torchsde, torchvision, ultralytics, ultralytics-thop, xformers
on bash ven 3.12.3 master ≡ ?1 -1 456ms
╭─ 09:26:27 | 27 Oct, Sunday | in ven comf
╰─❯ pip show accelerate
Name: accelerate
Version: 1.0.1
Summary: Accelerate
Home-page: https://github.com/huggingface/accelerate
Author: The HuggingFace team
Author-email: [email protected]
License: Apache
Location: /home/ks/ven/lib/python3.12/site-packages
Requires: huggingface-hub, numpy, packaging, psutil, pyyaml, safetensors, torch
Required-by:
on bash ven 3.12.3 master ≡ ?1 -1 436ms
╭─ 09:27:18 | 27 Oct, Sunday | in ven comf
╰─❯
from here... my assumption is:
torch, accelerate and xformers will somehow figure out where flash-attn is, and somehow would use it automatically. contributing to the speed gain that i am experiencing now.
i have no way of confirming this.
can someone point me in the right direction to confirm?
https://huggingface.co/docs/transformers/en/perf_infer_gpu_one
i feel dumb.
huggingface have descriptions on support for flash_attn.
FlashAttention-2 can only be used when the model’s dtype is fp16 or bf16. Make sure to cast your model to the appropriate dtype and load them on a supported device before using FlashAttention-2.
You can also set use_flash_attention_2=True to enable FlashAttention-2 but it is deprecated in favor of attn_implementation="flash_attention_2".
FlashAttention-2 can only be used when the model’s dtype is fp16 or bf16. Make sure to cast your model to the appropriate dtype and load them on a supported device before using FlashAttention-2.
You can also set use_flash_attention_2=True to enable FlashAttention-2 but it is deprecated in favor of attn_implementation="flash_attention_2".
i guess the below kinda answers my question.
import torch from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("facebook/opt-350m") model = AutoModelForCausalLM.from_pretrained("facebook/opt-350m", torch_dtype=torch.float16).to("cuda")
input_text = "Hello my dog is cute and" inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
- with torch.backends.cuda.sdp_kernel(enable_flash=True, enable_math=False, enable_mem_efficient=False): outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) If you see a bug with the traceback below, try using the nightly version of PyTorch which may have broader coverage for FlashAttention:
Copied RuntimeError: No available kernel. Aborting execution.
install PyTorch nightly
pip3 install -U --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu118 BetterTransformer
https://huggingface.co/docs/transformers/en/perf_infer_gpu_one
i feel dumb.
huggingface have descriptions on support for flash_attn.
FlashAttention-2 can only be used when the model’s dtype is fp16 or bf16. Make sure to cast your model to the appropriate dtype and load them on a supported device before using FlashAttention-2. You can also set use_flash_attention_2=True to enable FlashAttention-2 but it is deprecated in favor of attn_implementation="flash_attention_2".
BetterTransformer also converts all attention operations to use the more memory-efficient [scaled dot product attention (SDPA)](https://pytorch.org/docs/master/generated/torch.nn.functional.scaled_dot_product_attention), and it calls optimized kernels like [FlashAttention](https://huggingface.co/papers/2205.14135) under the hood.
okay so someone has made this job easier for me. so this part answers the question how does flash_attn gets loaded into comfyUI when i did not make any changes to my workflow.
so apparently they have updated in pytorch. installing updated pytorch is then key.
https://pytorch.org/blog/a-better-transformer-for-fast-transformer-encoder-inference/
-->> Attention Is All You Need <<--
https://github.com/pytorch/pytorch/tree/main/aten/src/ATen/native/transformers/cuda/flash_attn
so this part will call flash_attn.
https://github.com/pytorch/pytorch/commit/d41558f8d7086874697c3082e5172e519cb426c8#diff-d1bfb425f2c653ff16c5f553eec51cae8be05c881259ec72f84fbd7d929f92b0R70-R80
#ifdef USE_FLASH_ATTENTION
// FlashAttention Specific Imports
#include <ATen/native/transformers/cuda/flash_attn/flash_api.h>
#endif
#ifdef USE_MEM_EFF_ATTENTION
#ifndef USE_ROCM
// MemoryEfficient Attention Specific Imports for CUDA
#include <ATen/native/transformers/cuda/mem_eff_attention/kernel_forward.h>
#include <ATen/native/transformers/cuda/mem_eff_attention/kernels/cutlassF.h>
#include <ATen/native/transformers/cuda/mem_eff_attention/pytorch_utils.h>
#else
ok ok... i'm just surprised that this is not a common knowledge kind of thing... judging from not seeing much information about enabling flash_attention when using ComfyUI.
or am I the one who is late to this game?
https://github.com/Dao-AILab/flash-attention/issues/1308
let's see if updating windows and updating drivers cause any issues...
first... sudo apt update && sudo apt upgrade broke a lot of things...
ddd insightface ven
Thu Oct 31 20:24:45 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.57.01 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:0B:00.0 On | N/A |
| 0% 39C P0 9W / 320W | 724MiB / 16376MiB | 10% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 438 G /Xwayland N/A |
+-----------------------------------------------------------------------------------------+
VIRTUAL_ENV=/home/ks/ven
VIRTUAL_ENV_PROMPT=(ven)
ddd insightface ven
CODEOWNERS app comfyui.prev2.log fix_torch.py models pytest.ini tests
CONTRIBUTING.md comfy comfyui_screenshot.png folder_paths.py new_updater.py requirements.txt tests-unit
LICENSE comfy_execution cuda_malloc.py input node_helpers.py script_examples user
README.md comfy_extras custom_nodes latent_preview.py nodes.py server.py utils
__pycache__ comfyui.log execution.py main.py notebooks styles web
api_server comfyui.prev.log extra_model_paths.yaml.example model_filemanager output temp
on bash ven 3.12.3 master ≡ ?1 1 0ms ╭─ 20:24:45 | 31 Oct, Thursday | in ven comf
╰─❯ python3 -m pip install --upgrade pip
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Requirement already satisfied: pip in /home/ks/ven/lib/python3.12/site-packages (24.3.1)
on bash ven 3.12.3 master ≡ ?1 1 2s 403ms
╭─ 20:25:06 | 31 Oct, Thursday | in ven comf
╰─❯ pip check
ninja 1.11.1.1 is not supported on this platform
on bash ven 3.12.3 master ≡ ?1 1 518ms
╭─ 20:25:14 | 31 Oct, Thursday | in ven comf
╰─❯ pip install ninja
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Requirement already satisfied: ninja in /home/ks/ven/lib/python3.12/site-packages (1.11.1.1)
on bash ven 3.12.3 master ≡ ?1 1 1s 186ms
╭─ 20:25:26 | 31 Oct, Thursday | in ven comf
╰─❯ pip check
ninja 1.11.1.1 is not supported on this platform
on bash ven 3.12.3 master ≡ ?1 1 477ms
╭─ 20:25:32 | 31 Oct, Thursday | in ven comf
╰─❯ sudo apt install ninja-build
[sudo] password for ks:
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
ninja-build is already the newest version (1.11.1-2).
0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
on bash ven 3.12.3 master ≡ ?1 1 2s 996ms
╭─ 20:25:52 | 31 Oct, Thursday | in ven comf
╰─❯ ninja --version
1.12.1
on bash ven 3.12.3 master ≡ ?1 1 32ms
╭─ 20:26:14 | 31 Oct, Thursday | in ven comf
╰─❯ ninja
ninja: error: loading 'build.ninja': No such file or directory
on bash ven 3.12.3 master ≡ ?1 1 0ms
╭─ 20:26:14 | 31 Oct, Thursday | in ven comf
╰─❯ ls
CODEOWNERS app comfyui.prev2.log fix_torch.py models pytest.ini tests
CONTRIBUTING.md comfy comfyui_screenshot.png folder_paths.py new_updater.py requirements.txt tests-unit
LICENSE comfy_execution cuda_malloc.py input node_helpers.py script_examples user
README.md comfy_extras custom_nodes latent_preview.py nodes.py server.py utils
__pycache__ comfyui.log execution.py main.py notebooks styles web
api_server comfyui.prev.log extra_model_paths.yaml.example model_filemanager output temp
on bash ven 3.12.3 master ≡ ?1 1 5ms
╭─ 20:26:21 | 31 Oct, Thursday | in ven comf
╰─❯ python main.py
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-10-31 20:26:27.471142
** Platform: Linux
** Python version: 3.12.3 (main, Sep 11 2024, 14:17:37) [GCC 13.2.0]
** Python executable: /home/ks/ven/bin/python
** ComfyUI Path: /home/ks/ven/comf
** Log path: /home/ks/ven/comf/comfyui.log
Prestartup times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.5 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
Using xformers cross attention
[Prompt Server] web root: /home/ks/ven/comf/web
/home/ks/ven/lib/python3.12/site-packages/kornia/feature/lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
@torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
### Loading: ComfyUI-Manager (V2.51.8)
### ComfyUI Revision: 2790 [9ee0a655] | Released on '2024-10-27'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[comfy_mtb] | INFO -> loaded 86 nodes successfuly
[comfy_mtb] | INFO -> Some nodes (2) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information.
[ReActor] - STATUS - Running v0.5.1-b2 in ComfyUI
Torch version: 2.5.0+cu124
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
[rgthree-comfy] Loaded 42 magnificent nodes. 🎉
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `/home/ks/ven/comf/custom_nodes/was-node-suite-comfyui/was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 218 nodes successfully.
"Don't be afraid to give up the good to go for the great." - John D. Rockefeller
/home/ks/ven/comf/custom_nodes/blibla-comfyui-extensions/extensions
/home/ks/ven/comf/web/extensions/failfast-comfyui-extensions
FaceDetailer: Model directory already exists
FaceDetailer: Model already exists
Import times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/websocket_image_save.py
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-NodeAligner
0.0 seconds: /home/ks/ven/comf/custom_nodes/cg-use-everywhere
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-ZeroShot-MTrans
0.0 seconds: /home/ks/ven/comf/custom_nodes/Skimmed_CFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_JPS-Nodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-AutomaticCFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-instantId-faceswap
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Image-Saver
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Custom-Scripts
0.0 seconds: /home/ks/ven/comf/custom_nodes/blibla-comfyui-extensions
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-browser
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-KJNodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-faceless-node
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui_face_parsing
0.0 seconds: /home/ks/ven/comf/custom_nodes/facerestore_cf
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-NuA-FlashFace
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_ExtraModels
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_cspnodes
0.1 seconds: /home/ks/ven/comf/custom_nodes/comfyui-reactor-node
0.3 seconds: /home/ks/ven/comf/custom_nodes/DZ-FaceDetailer
0.3 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_omost
0.3 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Facerestore-Tensorrt
0.6 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Phi-3-mini
0.6 seconds: /home/ks/ven/comf/custom_nodes/was-node-suite-comfyui
0.8 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-SUPIR
1.9 seconds: /home/ks/ven/comf/custom_nodes/comfy_mtb
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/extension-node-map.json [DONE]
Update ComfyUI
Install: pip packages
[ComfyUI-Manager] skip black listed pip installation: 'torch'
[ComfyUI-Manager] skip black listed pip installation: 'torchsde'
[ComfyUI-Manager] skip black listed pip installation: 'torchvision'
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'torchaudio']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'einops']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'transformers>=4.28.1']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'tokenizers>=0.13.3']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'sentencepiece']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'safetensors>=0.4.2']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'aiohttp']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'pyyaml']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'Pillow']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'scipy']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'tqdm']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'psutil']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Line is comment...skipping
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'kornia>=0.7.1']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'spandrel']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'soundfile']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Update ComfyUI
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/.cache/1514988643_custom-node-list.json [DONE]
Updating: /home/ks/ven/comf/custom_nodes/Skimmed_CFGInstall: pip packages
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'GitPython']
Updating: /home/ks/ven/comf/custom_nodes/rgthree-comfy Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Updating: /home/ks/ven/comf/custom_nodes/ComfyUI-KJNodes
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'PyGithub']
Updating: /home/ks/ven/comf/custom_nodes/ComfyUI-SUPIR Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Updated: /home/ks/ven/comf/custom_nodes/cg-use-everywhere
Updating: /home/ks/ven/comf/custom_nodes/comfyui-browserInstall: pip packages
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'pillow>=10.3.0']
Updating: /home/ks/ven/comf/custom_nodes/comfyui_face_parsing
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'matrix-client==0.4.0']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Updating: /home/ks/ven/comf/custom_nodes/ComfyUI-Facerestore-Tensorrt
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'scipy']
Updating: /home/ks/ven/comf/custom_nodes/comfyui-instantId-faceswap[ComfyUI-Manager] skip black listed pip installation: 'transformers'
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'huggingface-hub>0.20']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Updating: /home/ks/ven/comf/custom_nodes/ComfyUI_cspnodesInstall: pip packages
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'piexif']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'color-matcher']
Updating: /home/ks/ven/comf/custom_nodes/ComfyUI_omost Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Updated: /home/ks/ven/comf/custom_nodes/ComfyUI-Image-Saver
Updating: /home/ks/ven/comf/custom_nodes/comfyui-faceless-node
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'matplotlib']
Updating: /home/ks/ven/comf/custom_nodes/ComfyUI-NuA-FlashFace
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'typer']
Updating: /home/ks/ven/comf/custom_nodes/ComfyUI-NodeAligner Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'huggingface_hub']
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'rich']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'mss']
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'typing-extensions']
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
## ComfyUI-Manager: EXECUTE => ['/home/ks/ven/bin/python', '-m', 'pip', 'install', 'opencv-python']
Updated: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Updated: /home/ks/ven/comf/custom_nodes/ComfyUI-KJNodes
Update done.
Restarting... [Legacy Mode]
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-10-31 20:28:01.098550
** Platform: Linux
** Python version: 3.12.3 (main, Sep 11 2024, 14:17:37) [GCC 13.2.0]
** Python executable: /home/ks/ven/bin/python
** ComfyUI Path: /home/ks/ven/comf
** Log path: /home/ks/ven/comf/comfyui.log
Prestartup times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.5 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
Using xformers cross attention
[Prompt Server] web root: /home/ks/ven/comf/web
/home/ks/ven/lib/python3.12/site-packages/kornia/feature/lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
@torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
### Loading: ComfyUI-Manager (V2.51.9)
### ComfyUI Revision: 2801 [f2aaa0a4] | Released on '2024-10-31'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[comfy_mtb] | INFO -> loaded 86 nodes successfuly
[comfy_mtb] | INFO -> Some nodes (2) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information.
[ReActor] - STATUS - Running v0.5.1-b2 in ComfyUI
Torch version: 2.5.0+cu124
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.0+cu124
xformers version: 0.0.28.post2
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
[rgthree-comfy] Loaded 42 epic nodes. 🎉
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `/home/ks/ven/comf/custom_nodes/was-node-suite-comfyui/was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 218 nodes successfully.
"Art is not freedom from discipline, but disciplined freedom." - John F. Kennedy
/home/ks/ven/comf/custom_nodes/blibla-comfyui-extensions/extensions
/home/ks/ven/comf/web/extensions/failfast-comfyui-extensions
FaceDetailer: Model directory already exists
FaceDetailer: Model already exists
Import times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-NodeAligner
0.0 seconds: /home/ks/ven/comf/custom_nodes/websocket_image_save.py
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-ZeroShot-MTrans
0.0 seconds: /home/ks/ven/comf/custom_nodes/Skimmed_CFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/cg-use-everywhere
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-instantId-faceswap
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-AutomaticCFG
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_JPS-Nodes
0.0 seconds: /home/ks/ven/comf/custom_nodes/blibla-comfyui-extensions
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Custom-Scripts
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-browser
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Image-Saver
0.0 seconds: /home/ks/ven/comf/custom_nodes/rgthree-comfy
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui-faceless-node
0.0 seconds: /home/ks/ven/comf/custom_nodes/facerestore_cf
0.0 seconds: /home/ks/ven/comf/custom_nodes/comfyui_face_parsing
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-NuA-FlashFace
0.0 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-KJNodes
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_ExtraModels
0.1 seconds: /home/ks/ven/comf/custom_nodes/comfyui-reactor-node
0.1 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_cspnodes
0.2 seconds: /home/ks/ven/comf/custom_nodes/DZ-FaceDetailer
0.2 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Facerestore-Tensorrt
0.2 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI_omost
0.3 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-Phi-3-mini
0.5 seconds: /home/ks/ven/comf/custom_nodes/was-node-suite-comfyui
0.5 seconds: /home/ks/ven/comf/custom_nodes/ComfyUI-SUPIR
1.2 seconds: /home/ks/ven/comf/custom_nodes/comfy_mtb
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: /home/ks/ven/comf/custom_nodes/ComfyUI-Manager/extension-node-map.json [DONE]
got prompt
model weight dtype torch.float16, manual cast: None
model_type EPS
Using xformers attention in VAE
Using xformers attention in VAE
[ReActor] 20:28:36 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
0: 640x480 1 face, 39.1ms
0: 640x480 1 face, 39.1ms
Speed: 2.1ms preprocess, 39.1ms inference, 11.7ms postprocess per image at shape (1, 3, 640, 480)
Speed: 2.1ms preprocess, 39.1ms inference, 11.7ms postprocess per image at shape (1, 3, 640, 480)
Requested to load SDXLClipModel
Loading 1 new model
loaded completely 0.0 1560.802734375 True
Requested to load SDXL
Loading 1 new model
loaded completely 0.0 4897.0483474731445 True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 60/60 [00:32<00:00, 1.86it/s]
Requested to load AutoencoderKL
Loading 1 new model
loaded completely 0.0 159.55708122253418 True
[ReActor] 20:29:21 - STATUS - Restoring with GFPGANv1.4.pth | Face Size is set to 512
Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.
# redacted information
[ReActor] 20:29:24 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 20:29:24 - STATUS - Analyzing Source Image...
[ReActor] 20:29:25 - STATUS - Trying to halve 'det_size' parameter
[ReActor] 20:29:29 - STATUS - Analyzing Target Image...
[ReActor] 20:29:32 - STATUS - Source Face 0: Detected Gender -M-
[ReActor] 20:29:32 - STATUS - OK - Detected Gender matches Condition
[ReActor] 20:29:33 - STATUS - Target Face 0: Detected Gender -M-
[ReActor] 20:29:33 - STATUS - OK - Detected Gender matches Condition
[ReActor] 20:29:33 - STATUS - Swapping...
[ReActor] 20:29:33 - STATUS - Face Boost is enabled
[ReActor] 20:29:34 - STATUS - Boosting the Face with codeformer-v0.1.0.pth | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 20:29:35 - STATUS - --Done!--
[ReActor] 20:29:35 - STATUS - Restoring with GPEN-BFR-2048.onnx | Face Size is set to 2048
[ReActor] 20:29:54 - STATUS - Restoring with GPEN-BFR-512.onnx | Face Size is set to 512
VRAMdebug: free memory before: 2,378,621,714
VRAMdebug: free memory after: 2,387,591,954
VRAMdebug: freed memory: 8,970,240
Saved workflow to /home/ks/ven/comf/output/2024-10-31XXXXXXX.json
Prompt executed in 85.32 seconds
let's delete everything and start all over again to confirm that yes, there is a speed difference before installing flash_attn...
also... i needed conda to help install a software that is obscure... let's do this.
since there is no space for me to setup a conda environment... i think the next best step for me is to simply delete everything and start from scratch.
okay. so we are deleting the original virtual environment where i have installed ComfyUI.
Create an environment containing the package 'sqlite'::
conda create -n myenv sqlite
Create an environment (env2) as a clone of an existing environment (env1)::
conda create -n env2 --clone path/to/file/env1
on bash base 3.12.7 225ms
╭─ 15:49:57 | 2 Nov, Saturday | in ven
╰─❯ conda create -n ven2 --clone /home/ks/ven
Source: /home/ks/ven
Destination: /home/ks/.conda/envs/ven2
Packages: 0
Files: 175465
NoSpaceLeftError: No space left on devices.
on bash base 3.12.7 11s 563ms
╭─ 15:52:42 | 2 Nov, Saturday | in ven
╰─❯ cd ..
on bash 3ms
╭─ 17:04:32 | 2 Nov, Saturday | in
╰─❯ ls
comf ddd insightface miniconda3 ven
on bash 7ms
╭─ 17:04:33 | 2 Nov, Saturday | in
╰─❯ sudo rm -r ven
[sudo] password for ks:
on bash 2s 251ms
╭─ 17:04:46 | 2 Nov, Saturday | in
╰─❯ ls
comf ddd insightface miniconda3
on bash 5ms
╭─ 17:04:48 | 2 Nov, Saturday | in
╰─❯ dir
comf ddd insightface miniconda3
on bash 10ms
╭─ 17:04:49 | 2 Nov, Saturday | in
╰─❯ ls
comf ddd insightface miniconda3
on bash 5ms
╭─ 17:04:51 | 2 Nov, Saturday | in
╰─❯
comf ddd insightface miniconda3
Sat Nov 2 17:13:21 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.57.01 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:0B:00.0 On | N/A |
| 0% 42C P5 31W / 320W | 566MiB / 16376MiB | 2% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| No running processes found |
+-----------------------------------------------------------------------------------------+
comf ddd insightface miniconda3
-bash: cd: ven/comf/: No such file or directory
comf ddd insightface miniconda3
on bash 0ms
╭─ 17:13:23 | 2 Nov, Saturday | in
╰─❯
first, uninstall everything and start from fresh.
winget install wsl
Multiple packages found matching input criteria. Please refine the input.
Name Id Source
-------------------------------------------------
Arch WSL 9MZNMNKSM73X msstore
Windows Subsystem for Linux Microsoft.WSL winget
winget install Microsoft.WSL
Found Windows Subsystem for Linux [Microsoft.WSL] Version 2.1.5.0
This application is licensed to you by its owner.
Microsoft is not responsible for, nor does it grant any licenses to, third-party packages.
This package requires the following dependencies:
- Windows Features
Microsoft-Windows-Subsystem-Linux
VirtualMachinePlatform
Enabling [Microsoft-Windows-Subsystem-Linux]...
Enabling [VirtualMachinePlatform]...
Successfully enabled Windows Features dependencies
Downloading https://github.com/microsoft/WSL/releases/download/2.1.5/wsl.2.1.5.0.x64.msi
██████████ 43.0 MB / 127 MB
i reset everything and reinstalled from scratch.
and to save space... i am moving everything i can elsewhere using system settings in windows 11.
PowerShell 7.5.0-preview.5
Loading personal and system profiles took 774ms.
wsl --list --all
Windows Subsystem for Linux has no installed distributions.
Use 'wsl.exe --list --online' to list available distributions
and 'wsl.exe --install <Distro>' to install.
Distributions can also be installed by visiting the Microsoft Store:
https://aka.ms/wslstore
Error code: Wsl/WSL_E_DEFAULT_DISTRO_NOT_FOUND
wsl --list --online
The following is a list of valid distributions that can be installed.
Install using 'wsl.exe --install <Distro>'.
NAME FRIENDLY NAME
Ubuntu Ubuntu
Debian Debian GNU/Linux
kali-linux Kali Linux Rolling
Ubuntu-18.04 Ubuntu 18.04 LTS
Ubuntu-20.04 Ubuntu 20.04 LTS
Ubuntu-22.04 Ubuntu 22.04 LTS
Ubuntu-24.04 Ubuntu 24.04 LTS
OracleLinux_7_9 Oracle Linux 7.9
OracleLinux_8_7 Oracle Linux 8.7
OracleLinux_9_1 Oracle Linux 9.1
openSUSE-Leap-15.6 openSUSE Leap 15.6
SUSE-Linux-Enterprise-15-SP5 SUSE Linux Enterprise 15 SP5
SUSE-Linux-Enterprise-15-SP6 SUSE Linux Enterprise 15 SP6
openSUSE-Tumbleweed openSUSE Tumbleweed
wsl --install Ubuntu-24.04
Installing: Ubuntu 24.04 LTS
[===== 9.0% ]
you can move your files accordingly so do that if you want to save space or whatever.
and make sure you update accordingly... and set sparse if you need to...
PowerShell 7.5.0-preview.5
Loading personal and system profiles took 829ms.
winget update --all
No installed package found matching input criteria.
wsl --update
Checking for updates.
Updating Windows Subsystem for Linux to version: 2.3.24.
.
.
.
.
.
wsl --manage Ubuntu-24.04 --set-sparse true
Conversion in progress, this may take a few minutes.
The operation completed successfully.
pwsh MEM: 14% | 11/79GB 41ms
╭─ ♥ 05:34 |
╰─
and for windows users i strongly recommend installing xfe so that you don't have to worry too much about using the command line to get things done...
ks@4080SUPER:~$ curl -s https://ohmyposh.dev/install.sh | bash -s
unzip is required to install Oh My Posh. Please install unzip and try again.
ks@4080SUPER:~$ sudo apt install unzip
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
Suggested packages:
zip
The following NEW packages will be installed:
unzip
0 upgraded, 1 newly installed, 0 to remove and 0 not upgraded.
Need to get 174 kB of archives.
After this operation, 384 kB of additional disk space will be used.
Get:1 http://archive.ubuntu.com/ubuntu noble-updates/main amd64 unzip amd64 6.0-28ubuntu4.1 [174 kB]
Fetched 174 kB in 1s (182 kB/s)
Selecting previously unselected package unzip.
(Reading database ... 40787 files and directories currently installed.)
Preparing to unpack .../unzip_6.0-28ubuntu4.1_amd64.deb ...
Unpacking unzip (6.0-28ubuntu4.1) ...
Setting up unzip (6.0-28ubuntu4.1) ...
Processing triggers for man-db (2.12.0-4build2) ...
ks@4080SUPER:~$ curl -s https://ohmyposh.dev/install.sh | bash -s
⚠️ Installation directory /home/ks/.local/bin is not in your $PATH, add it using
export PATH=$PATH:/home/ks/.local/bin
ℹ️ Installing oh-my-posh for linux-amd64 in /home/ks/.local/bin
⬇️ Downloading oh-my-posh from https://github.com/JanDeDobbeleer/oh-my-posh/releases/latest/download/posh-linux-amd64
🎨 Installing oh-my-posh themes in /home/ks/.cache/oh-my-posh/themes
🚀 Installation complete.
You can follow the instructions at https://ohmyposh.dev/docs/installation/prompt
to setup your shell to use oh-my-posh.
If you want to use a built-in theme, you can find them in the /home/ks/.cache/oh-my-posh/themes directory:
oh-my-posh init {shell} --config /home/ks/.cache/oh-my-posh/themes/{theme}.omp.json
ks@4080SUPER:~$ sudo apt install xfe
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
The following additional packages will be installed:
turns out, xfe does pretty much how a windows user expects files to be moved around without much issues or headaches. i like it!
also, use miniconda. turns out... it is a much better method to manage your environments... but you do you~!
https://docs.anaconda.com/miniconda/
┏[ ks from 4080SUPER][ 0s][ RAM: 0/39GB][ Monday at 5:51:27 AM]
┖[~]
└─Δ mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm ~/miniconda3/miniconda.sh
--2024-11-04 05:52:49-- https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
Resolving repo.anaconda.com (repo.anaconda.com)... 104.16.32.241, 104.16.191.158, 2606:4700::6810:bf9e, ...
Connecting to repo.anaconda.com (repo.anaconda.com)|104.16.32.241|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 148337011 (141M) [application/octet-stream]
Saving to: ‘/home/ks/miniconda3/miniconda.sh’
/home/ks/miniconda3/miniconda.sh 100%[================================================================>] 141.46M 10.9MB/s in 13s
2024-11-04 05:53:01 (10.9 MB/s) - ‘/home/ks/miniconda3/miniconda.sh’ saved [148337011/148337011]
PREFIX=/home/ks/miniconda3
Unpacking payload ...
Installing base environment...
Preparing transaction: ...working... done
Executing transaction: ...working... done
installation finished.
┏[ ks from 4080SUPER][ 0.035s][ RAM: 1/39GB][ Monday at 5:53:07 AM]
┖[~]
└─Δ
and don't forget that conda should be the preferred method to install as much of the dependencies as possible. for eg, pytorch:
┏[ ks from 4080SUPER][ 0.004s][ RAM: 0/39GB][ Monday at 6:37:33 AM]
┖[~]
└─Δ conda install pytorch torchvision torchaudio pytorch-cuda=12.4 -c pytorch-nightly -c nvidia
Channels:
- pytorch-nightly
- nvidia
- defaults
Platform: linux-64
Collecting package metadata (repodata.json): done
Solving environment: done
## Package Plan ##
environment location: /home/ks/ven
added / updated specs:
- pytorch
- pytorch-cuda=12.4
- torchaudio
- torchvision
.
.
.
.
.
.
after installing all the relevant softwares and dependencies
. .bash_history .bashrc .conda .config .motd_shown .profile .tcshrc .zshrc ven
.. .bash_logout .cache .condarc .local .nv .sudo_as_admin_successful .xonshrc miniconda3
Mon Nov 4 07:24:24 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.51.01 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:0B:00.0 On | N/A |
| 0% 40C P0 13W / 320W | 685MiB / 16376MiB | 7% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| No running processes found |
+-----------------------------------------------------------------------------------------+
. .bash_history .bashrc .conda .config .motd_shown .profile .tcshrc .zshrc ven
.. .bash_logout .cache .condarc .local .nv .sudo_as_admin_successful .xonshrc miniconda3
. .requirements.txt.swp comfy fix_torch.py node_helpers.py temp
.. CODEOWNERS comfy_execution folder_paths.py nodes.py tests
.ci CONTRIBUTING.md comfy_extras input notebooks tests-unit
.git LICENSE comfyui_screenshot.png latent_preview.py output user
.gitattributes README.md cuda_malloc.py main.py pytest.ini utils
.github __pycache__ custom_nodes model_filemanager requirements.txt web
.gitignore api_server execution.py models script_examples
.pylintrc app extra_model_paths.yaml.example new_updater.py server.py
Use the following command to check which environment you have activated: conda info --envs
Use the following command to check which environment you have activated: conda activate <FOLLOWED BY THE env NAME from above>
-bash: /home/ks/.cargo/env: No such file or directory
┏[ ks from 4080SUPER][ 0s][ RAM: 16/39GB][ Monday at 7:24:25 AM][ master ≡ ?1]
┖[~/ven/comf]
└─Δ conda activate ~/ven
┏[ ks from 4080SUPER][ 0.215s][ RAM: 16/39GB][ Monday at 7:24:36 AM][ master ≡ ?1]
┖[~/ven/comf]
└─Δ conda info --envs
# conda environments:
#
base /home/ks/miniconda3
* /home/ks/ven
┏[ ks from 4080SUPER][ 0.626s][ RAM: 16/39GB][ Monday at 7:24:45 AM][ master ≡ ?1]
┖[~/ven/comf]
└─Δ pip install torchaudio
Requirement already satisfied: torchaudio in /home/ks/ven/lib/python3.12/site-packages (2.5.0.dev20241103)
Requirement already satisfied: torch in /home/ks/ven/lib/python3.12/site-packages (from torchaudio) (2.5.1)
Requirement already satisfied: filelock in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (3.13.1)
Requirement already satisfied: typing-extensions>=4.8.0 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (4.11.0)
Requirement already satisfied: networkx in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (3.2.1)
Requirement already satisfied: jinja2 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (3.1.4)
Requirement already satisfied: fsspec in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (2024.3.1)
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (12.4.127)
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (12.4.127)
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (12.4.127)
Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (9.1.0.70)
Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (12.4.5.8)
Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (11.2.1.3)
Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (10.3.5.147)
Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (11.6.1.9)
Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (12.3.1.170)
Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (2.21.5)
Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (12.4.127)
Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (12.4.127)
Requirement already satisfied: triton==3.1.0 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (3.1.0)
Requirement already satisfied: setuptools in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (75.1.0)
Requirement already satisfied: sympy==1.13.1 in /home/ks/ven/lib/python3.12/site-packages (from torch->torchaudio) (1.13.1)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /home/ks/ven/lib/python3.12/site-packages (from sympy==1.13.1->torch->torchaudio) (1.3.0)
Requirement already satisfied: MarkupSafe>=2.0 in /home/ks/ven/lib/python3.12/site-packages (from jinja2->torch->torchaudio) (2.1.3)
┏[ ks from 4080SUPER][ 0.419s][ RAM: 16/39GB][ Monday at 7:24:59 AM][ master ≡ ?1]
┖[~/ven/comf]
└─Δ pip uninstal torchaudio
ERROR: unknown command "uninstal" - maybe you meant "uninstall"
┏[ ks from 4080SUPER][ 0.144s][ RAM: 16/39GB][ Monday at 7:25:06 AM][ master ≡ ?1][ Error, check your command]
┖[~/ven/comf]
└─Δ pip uninstall torchaudio
Found existing installation: torchaudio 2.5.0.dev20241103
Uninstalling torchaudio-2.5.0.dev20241103:
Would remove:
/home/ks/ven/lib/python3.12/site-packages/torchaudio
/home/ks/ven/lib/python3.12/site-packages/torchaudio-2.5.0.dev20241103-py3.12.egg-info
/home/ks/ven/lib/python3.12/site-packages/torio
Proceed (Y/n)? y
Successfully uninstalled torchaudio-2.5.0.dev20241103
┏[ ks from 4080SUPER][ 0.916s][ RAM: 16/39GB][ Monday at 7:25:12 AM][ master ≡ ?1]
┖[~/ven/comf]
└─Δ pip install torchaudio
Collecting torchaudio
Downloading torchaudio-2.5.1-cp312-cp312-manylinux1_x86_64.whl.metadata (6.4 kB)
Requirement already satisfied: torch==2.5.1 in /home/ks/ven/lib/python3.12/site-packages (from torchaudio) (2.5.1)
Requirement already satisfied: filelock in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (3.13.1)
Requirement already satisfied: typing-extensions>=4.8.0 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (4.11.0)
Requirement already satisfied: networkx in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (3.2.1)
Requirement already satisfied: jinja2 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (3.1.4)
Requirement already satisfied: fsspec in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (2024.3.1)
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (12.4.127)
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (12.4.127)
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (12.4.127)
Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (9.1.0.70)
Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (12.4.5.8)
Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (11.2.1.3)
Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (10.3.5.147)
Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (11.6.1.9)
Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (12.3.1.170)
Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (2.21.5)
Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (12.4.127)
Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (12.4.127)
Requirement already satisfied: triton==3.1.0 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (3.1.0)
Requirement already satisfied: setuptools in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (75.1.0)
Requirement already satisfied: sympy==1.13.1 in /home/ks/ven/lib/python3.12/site-packages (from torch==2.5.1->torchaudio) (1.13.1)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /home/ks/ven/lib/python3.12/site-packages (from sympy==1.13.1->torch==2.5.1->torchaudio) (1.3.0)
Requirement already satisfied: MarkupSafe>=2.0 in /home/ks/ven/lib/python3.12/site-packages (from jinja2->torch==2.5.1->torchaudio) (2.1.3)
Downloading torchaudio-2.5.1-cp312-cp312-manylinux1_x86_64.whl (3.4 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.4/3.4 MB 9.6 MB/s eta 0:00:00
Installing collected packages: torchaudio
Successfully installed torchaudio-2.5.1
┏[ ks from 4080SUPER][ 1.144s][ RAM: 16/39GB][ Monday at 7:25:17 AM][ master ≡ ?1]
┖[~/ven/comf]
└─Δ pyhon main.py
pyhon: command not found
┏[ ks from 4080SUPER][ 0.122s][ RAM: 16/39GB][ Monday at 7:25:21 AM][ master ≡ ?1][ Error, check your command]
┖[~/ven/comf]
└─Δ python main.py
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.5.1+cu124
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
Using pytorch cross attention
[Prompt Server] web root: /home/ks/ven/comf/web
/home/ks/ven/lib/python3.12/site-packages/kornia/feature/lightglue.py:44: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
@torch.cuda.amp.custom_fwd(cast_inputs=torch.float32)
Import times for custom nodes:
0.0 seconds: /home/ks/ven/comf/custom_nodes/websocket_image_save.py
Starting server
To see the GUI go to: http://127.0.0.1:8188
so installation works fine.
::editted:: i regret installing conda... so many broken dependencies issue... stick to pure python and create your environment in venv the only problem arising is when you need to install other tools in other languages and that's where conda come in. one of the modern attention methods requires a software that can be found in conda library but not pypi... so... will come to that bridge and solve it then. for now... back to python, create env using venv, and stick with pip.
. .. .bash_history .bash_logout .bashrc .cache .config .local .motd_shown .profile .pyenv .sudo_as_admin_successful comf
Running (pyenv virtualenvs) this Lists all Python virtualenvs found in (/home/k/.pyenv/versions/*) in the next line
Running now.
3.12.7/envs/ven (created from /home/k/.pyenv/versions/3.12.7)
ven (created from /home/k/.pyenv/versions/3.12.7)
We are running (pyenv activate) to activate the listed environment (ven) next.
Running now
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Fri_Jan__6_16:45:21_PST_2023
Cuda compilation tools, release 12.0, V12.0.140
Build cuda_12.0.r12.0/compiler.32267302_0
Tue Nov 5 23:55:31 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.51.01 Driver Version: 565.90 CUDA Version: 12.7 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:0B:00.0 On | N/A |
| 0% 39C P0 14W / 320W | 718MiB / 16376MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 403 G /Xwayland N/A |
+-----------------------------------------------------------------------------------------+
VIRTUAL_ENV=/home/k/.pyenv/versions/3.12.7/envs/ven
PYENV_VIRTUAL_ENV=/home/k/.pyenv/versions/3.12.7/envs/ven
3.12.7/envs/ven (created from /home/k/.pyenv/versions/3.12.7)
* ven (created from /home/k/.pyenv/versions/3.12.7)
. .. .bash_history .bash_logout .bashrc .cache .config .local .motd_shown .profile .pyenv .sudo_as_admin_successful comf
. .pylintrc comfy extra_model_paths.yaml.example models requirements.txt
.. CODEOWNERS comfy_execution fix_torch.py new_updater.py script_examples
.ci CONTRIBUTING.md comfy_extras folder_paths.py node_helpers.py server.py
.git LICENSE comfyui_screenshot.png input nodes.py tests
.gitattributes README.md cuda_malloc.py latent_preview.py notebooks tests-unit
.github api_server custom_nodes main.py output utils
.gitignore app execution.py model_filemanager pytest.ini web
(ven) k@4080SUPER:~/comf$
the next comment will be about installing comfyui and comparing a fresh install with and without flash_attn.
Stay tune~!
All extensions are already up-to-date.
Restarting... [Legacy Mode]
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2024-11-06 00:12:25.402474
** Platform: Linux
** Python version: 3.12.7 (main, Nov 5 2024, 23:19:51) [GCC 13.2.0]
** Python executable: /home/k/.pyenv/versions/ven/bin/python
** ComfyUI Path: /home/k/comf
** Log path: /home/k/comf/comfyui.log
Prestartup times for custom nodes:
0.0 seconds: /home/k/comf/custom_nodes/rgthree-comfy
0.6 seconds: /home/k/comf/custom_nodes/ComfyUI-Manager
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.6.0.dev20241105+cu124
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
Using pytorch cross attention
[Prompt Server] web root: /home/k/comf/web
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `/home/k/comf/custom_nodes/was-node-suite-comfyui/was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 218 nodes successfully.
"Art is the mirror that reflects the beauty within us." - Unknown
[comfy_mtb] | INFO -> loaded 86 nodes successfuly
[comfy_mtb] | INFO -> Some nodes (2) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information.
Total VRAM 16376 MB, total RAM 40071 MB
pytorch version: 2.6.0.dev20241105+cu124
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 SUPER : cudaMallocAsync
[rgthree-comfy] Loaded 42 epic nodes. 🎉
### Loading: ComfyUI-Manager (V2.51.9)
### ComfyUI Revision: 2811 [8afb97cd] | Released on '2024-11-05'
[ReActor] - STATUS - Running v0.5.1-b2 in ComfyUI
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
Torch version: 2.6.0.dev20241105+cu124
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
Import times for custom nodes:
0.0 seconds: /home/k/comf/custom_nodes/websocket_image_save.py
0.0 seconds: /home/k/comf/custom_nodes/ComfyUI_JPS-Nodes
0.0 seconds: /home/k/comf/custom_nodes/ComfyUI-Image-Saver
0.0 seconds: /home/k/comf/custom_nodes/rgthree-comfy
0.0 seconds: /home/k/comf/custom_nodes/ComfyUI-KJNodes
0.0 seconds: /home/k/comf/custom_nodes/ComfyUI-Manager
0.0 seconds: /home/k/comf/custom_nodes/comfyui_face_parsing
0.2 seconds: /home/k/comf/custom_nodes/comfyui-reactor-node
1.0 seconds: /home/k/comf/custom_nodes/was-node-suite-comfyui
1.3 seconds: /home/k/comf/custom_nodes/comfy_mtb
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: /home/k/comf/custom_nodes/ComfyUI-Manager/extension-node-map.json [DONE]
okay. so i will use a freshly installed WSL2 with Ubuntu and a clean fresh new install of ComfyUI with all dependencies for the above image generations first.