stable-diffusion-webui [Bug]: On Macos, image become weird if the width and height is not multiply of 32

[Bug]: On Macos, image become weird if the width and height is not multiply of 32

Open xuhao1 opened this issue 1 year ago • 0 comments

Is there an existing issue for this?

[X] I have searched the existing issues and checked the recent builds/commits

What happened?

On macos, the generation image will become weird if the height and width is not multiply of 32 or 64 on my setup. Everything excepts width and height is same.

620x910, extrme weird 00203-201141319

624x912(16w,16h) 00200-201141319 608x896(32w,32h).This image has issue on human pose. But is not that weird. I found 32 is not safe. 64 is safe. 00201-201141319 640x960 （64w,64h) 00202-201141319

Steps to reproduce the problem

Generation on Macos using. I am on Macbook 16inch M2 Max with 32GB ram.

(masterpiece, best quality, 1girl, solo, intricate details, chromatic aberration, detailed skin), ((realistic)), urban beauty ,((medium breath)),long hair, (silver grey hair), (hair ornament:1.35), red head ornament, hair over one eye, sharp eyes, choker, (tube top, crop top),look at viewer, handbag, full body, (long boots, black boots), ankle, (skinny legs, long legs), (black mini skirt), earrings, oval face,
Negative prompt: sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, bad anatomy,(long hair:1.4),DeepNegative,(fat:1.2),facing away, looking away,tilted head, lowres,bad anatomy,bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worstquality, low quality, normal quality,jpegartifacts,signature, watermark, username,blurry,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,cross-eyed,mutated hands,polar lowres,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit, extra arms, extra leg, extra foot,
Steps: 28, Sampler: DPM++ SDE Karras, CFG scale: 7.5, Seed: 201141319, Size: 620x910, Model hash: 7234b76e42, Model: chilloutmix_Ni, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: panghu(c188991bd755), AddNet Weight A 1: 0.65, AddNet Weight B 1: 0.65, AddNet Module 2: LoRA, AddNet Model 2: koreandolllikeness_V10(e2e472c06607), AddNet Weight A 2: 0.25, AddNet Weight B 2: 0.25, AddNet Module 3: LoRA, AddNet Model 3: jingyijujingyi_juJingyiv10(448f2c32c80f), AddNet Weight A 3: 0.1, AddNet Weight B 3: 0.1, AddNet Module 4: LoRA, AddNet Model 4: shojovibe_v11(65ece304ac27), AddNet Weight A 4: 0.15, AddNet Weight B 4: 0.15

What should have happened?

image should performs same if the width and height is not multiply of 32.

Commit where the problem happens

image become weird if the width and height is not multiply of 32

What platforms do you use to access the UI ?

MacOS

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

./webui.sh --upcast-sampling --opt-sub-quad-attention --use-cpu interrogate

List of extensions

Extension	URL	Version	Update
sd-webui-additional-networks	https://github.com/kohya-ss/sd-webui-additional-networks.git	d2758b6c (Sun Mar 12 10:58:50 2023)	unknown
sd-webui-controlnet	https://github.com/Mikubill/sd-webui-controlnet.git	241c05f8 (Thu Mar 23 15:18:35 2023)	unknown
stable-diffusion-webui-chinese	https://github.com/VinsonLaro/stable-diffusion-webui-chinese	71b7f512 (Sun Mar 5 18:11:02 2023)	unknown
LDSR	built-in
Lora	built-in
ScuNET	built-in
SwinIR	built-in
prompt-bracket-checker	built-in

Extension URL Version Update multidiffusion-upscaler-for-automatic1111 https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 fb5acd08 (Fri Mar 24 06:14:49 2023) unknown sd-webui-additional-networks https://github.com/kohya-ss/sd-webui-additional-networks.git d2758b6c (Sun Mar 12 10:58:50 2023) unknown sd-webui-controlnet https://github.com/Mikubill/sd-webui-controlnet.git 241c05f8 (Thu Mar 23 15:18:35 2023) unknown stable-diffusion-webui-chinese https://github.com/VinsonLaro/stable-diffusion-webui-chinese 71b7f512 (Sun Mar 5 18:11:02 2023) unknown LDSR built-in Lora built-in ScuNET built-in SwinIR built-in prompt-bracket-checker built-in

Console logs

./webui.sh --upcast-sampling --opt-sub-quad-attention --use-cpu interrogate

################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################

################################################################
Running on xuhao user
################################################################

################################################################
Repo already cloned, using it as install directory
################################################################

################################################################
Create and activate python venv
################################################################

################################################################
Launching launch.py...
################################################################
Python 3.10.10 (main, Mar 21 2023, 13:41:05) [Clang 14.0.6 ]
Commit hash: a9fed7c364061ae6efb37f797b6b522cb3cf7aa2
Installing requirements for Web UI

Launching Web UI with arguments: --upcast-sampling --opt-sub-quad-attention --use-cpu interrogate --upcast-sampling --no-half-vae --use-cpu interrogate
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
==============================================================================
You are running torch 1.12.1.
The program is tested to work with torch 1.13.1.
To reinstall the desired version, run with commandline flag --reinstall-torch.
Beware that this will cause a lot of large files to be downloaded, as well as
there are reports of issues with training tab on the latest version.

Use --skip-version-check commandline argument to disable this check.
==============================================================================
[AddNet] Updating model hashes...
100%|███████████████████████████████████████████| 4/4 [00:00<00:00, 7043.33it/s]
[AddNet] Updating model hashes...
100%|██████████████████████████████████████████| 4/4 [00:00<00:00, 19691.57it/s]
Loading weights [7234b76e42] from /Users/xuhao/StableDiff/stable-diffusion-webui/models/Stable-diffusion/chilloutmix_Ni.safetensors
Creating model from config: /Users/xuhao/StableDiff/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(0):
Model loaded in 3.0s (load weights from disk: 0.1s, create model: 0.5s, apply weights to model: 1.6s, apply half(): 0.3s, move model to device: 0.4s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 11.6s (import gradio: 6.5s, import ldm: 0.4s, other imports: 1.0s, load scripts: 0.5s, load SD checkpoint: 3.0s, create ui: 0.1s).
                                  Traceback (most recent call last):
  File "/Users/xuhao/miniforge3/envs/stable_diff/lib/python3.10/site-packages/gradio/routes.py", line 337, in run_predict
    output = await app.get_blocks().process_api(
  File "/Users/xuhao/miniforge3/envs/stable_diff/lib/python3.10/site-packages/gradio/blocks.py", line 1015, in process_api
    result = await self.call_function(
  File "/Users/xuhao/miniforge3/envs/stable_diff/lib/python3.10/site-packages/gradio/blocks.py", line 833, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "/Users/xuhao/miniforge3/envs/stable_diff/lib/python3.10/site-packages/anyio/to_thread.py", line 31, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "/Users/xuhao/miniforge3/envs/stable_diff/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
    return await future
  File "/Users/xuhao/miniforge3/envs/stable_diff/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 867, in run
    result = context.run(func, *args)
  File "/Users/xuhao/StableDiff/stable-diffusion-webui/modules/ui.py", line 136, in calc_resolution_hires
    p.init([""], [0], [0])
  File "/Users/xuhao/StableDiff/stable-diffusion-webui/modules/processing.py", line 779, in init
    self.hr_upscale_to_x = int(self.width * self.hr_scale)
TypeError: unsupported operand type(s) for *: 'NoneType' and 'int'
100%|███████████████████████████████████████████| 14/14 [00:12<00:00,  1.11it/s]
 86%|████████████████████████████████████▊      | 12/14 [02:29<00:24, 12.43s/it]
Total progress:  93%|█████████████████████████  | 26/28 [04:28<00:20, 10.32s/it]
Total prTile 1/2093%|█████████████████████████  | 26/28 [04:28<00:23, 11.99s/it]
	Tile 2/20
	Tile 3/20
	Tile 4/20
	Tile 5/20
	Tile 6/20
	Tile 7/20
	Tile 8/20
	Tile 9/20
	Tile 10/20
	Tile 11/20
	Tile 12/20
	Tile 13/20
	Tile 14/20
	Tile 15/20
	Tile 16/20
	Tile 17/20
	Tile 18/20
	Tile 19/20
	Tile 20/20
	Tile 1/20
	Tile 2/20
	Tile 3/20
	Tile 4/20
	Tile 5/20
	Tile 6/20
	Tile 7/20
	Tile 8/20
	Tile 9/20
	Tile 10/20
	Tile 11/20
	Tile 12/20
	Tile 13/20
	Tile 14/20
	Tile 15/20
	Tile 16/20
	Tile 17/20
	Tile 18/20
	Tile 19/20
	Tile 20/20
                                  	Tile 1/20
Total prTile 2/20it [00:00, ?it/s]
	Tile 3/20
	Tile 4/20
	Tile 5/20
	Tile 6/20
	Tile 7/20
	Tile 8/20
	Tile 9/20
	Tile 10/20
	Tile 11/20
	Tile 12/20
	Tile 13/20
	Tile 14/20
	Tile 15/20
	Tile 16/20
	Tile 17/20
	Tile 18/20
	Tile 19/20
	Tile 20/20
SD upscaling will process a total of 16 images tiled as 4x4 per upscale in a total of 16 batches.
LoRA weight_unet: 0.65, weight_tenc: 0.65, model: panghu(c188991bd755)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.65, multiplier_tenc: 0.65
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
original forward/weights is backed up.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model panghu(c188991bd755) loaded: <All keys matched successfully>
LoRA weight_unet: 0.1, weight_tenc: 0.1, model: jingyijujingyi_juJingyiv10(448f2c32c80f)
dimension: {64}, alpha: {32.0}, multiplier_unet: 0.1, multiplier_tenc: 0.1
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model jingyijujingyi_juJingyiv10(448f2c32c80f) loaded: <All keys matched successfully>
LoRA weight_unet: 0.15, weight_tenc: 0.15, model: shojovibe_v11(65ece304ac27)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.15, multiplier_tenc: 0.15
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model shojovibe_v11(65ece304ac27) loaded: <All keys matched successfully>
setting (or sd model) changed. new networks created.
100%|███████████████████████████████████████████| 20/20 [01:01<00:00,  3.10s/it]
  0%|                                                    | 0/20 [00:02<?, ?it/s]
Total progress: 21it [03:28,  9.92s/it]
Total prTile 1/201it [03:28,  4.16s/it]
	Tile 2/20
	Tile 3/20
	Tile 4/20
	Tile 5/20
	Tile 6/20
	Tile 7/20
	Tile 8/20
	Tile 9/20
	Tile 10/20
	Tile 11/20
	Tile 12/20
	Tile 13/20
	Tile 14/20
	Tile 15/20
	Tile 16/20
	Tile 17/20
	Tile 18/20
	Tile 19/20
	Tile 20/20
SD upscaling will process a total of 16 images tiled as 4x4 per upscale in a total of 16 batches.
restoring last networks
original forward/weights is restored.
LoRA weight_unet: 0.65, weight_tenc: 0.65, model: panghu(c188991bd755)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.65, multiplier_tenc: 0.65
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
original forward/weights is backed up.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model panghu(c188991bd755) loaded: <All keys matched successfully>
LoRA weight_unet: 0.25, weight_tenc: 0.25, model: koreandolllikeness_V10(e2e472c06607)
dimension: {128}, alpha: {128.0}, multiplier_unet: 0.25, multiplier_tenc: 0.25
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model koreandolllikeness_V10(e2e472c06607) loaded: <All keys matched successfully>
LoRA weight_unet: 0.1, weight_tenc: 0.1, model: jingyijujingyi_juJingyiv10(448f2c32c80f)
dimension: {64}, alpha: {32.0}, multiplier_unet: 0.1, multiplier_tenc: 0.1
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model jingyijujingyi_juJingyiv10(448f2c32c80f) loaded: <All keys matched successfully>
LoRA weight_unet: 0.15, weight_tenc: 0.15, model: shojovibe_v11(65ece304ac27)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.15, multiplier_tenc: 0.15
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model shojovibe_v11(65ece304ac27) loaded: <All keys matched successfully>
setting (or sd model) changed. new networks created.
 75%|████████████████████████████████▎          | 15/20 [00:52<00:17,  3.48s/it]
Total progress:   5%|█▎                        | 16/320 [00:59<18:48,  3.71s/it]
Total prTile 1/20 5%|█▎                        | 16/320 [00:59<16:41,  3.29s/it]
	Tile 2/20
	Tile 3/20
	Tile 4/20
	Tile 5/20
	Tile 6/20
	Tile 7/20
	Tile 8/20
	Tile 9/20
	Tile 10/20
	Tile 11/20
	Tile 12/20
	Tile 13/20
	Tile 14/20
	Tile 15/20
	Tile 16/20
	Tile 17/20
	Tile 18/20
	Tile 19/20
	Tile 20/20
SD upscaling will process a total of 9 images tiled as 3x3 per upscale in a total of 9 batches.
100%|█████████████████████████████████████████████| 6/6 [00:10<00:00,  1.80s/it]
100%|█████████████████████████████████████████████| 6/6 [00:09<00:00,  1.66s/it]
100%|█████████████████████████████████████████████| 6/6 [00:09<00:00,  1.64s/it]
100%|█████████████████████████████████████████████| 6/6 [00:09<00:00,  1.65s/it]
100%|█████████████████████████████████████████████| 6/6 [00:09<00:00,  1.64s/it]
100%|█████████████████████████████████████████████| 6/6 [00:09<00:00,  1.65s/it]
100%|█████████████████████████████████████████████| 6/6 [00:10<00:00,  1.67s/it]
100%|█████████████████████████████████████████████| 6/6 [00:10<00:00,  1.77s/it]
100%|█████████████████████████████████████████████| 6/6 [00:09<00:00,  1.65s/it]
Total progress: 100%|███████████████████████████| 54/54 [01:49<00:00,  2.03s/it]
100%|█████████████████████████████████████████████| 6/6 [01:48<00:00, 18.02s/it]
Total progress: 6it [03:06, 31.11s/it]
100%|█████████████████████████████████████████████| 6/6 [04:18<00:00, 43.15s/it]
Total progress: 100%|█████████████████████████████| 6/6 [04:04<00:00, 40.73s/it]
Loading weights [f93e6a50ac] from /Users/xuhao/StableDiff/stable-diffusion-webui/models/Stable-diffusion/uberRealisticPornMerge_urpmv13.safetensors
Applying sub-quadratic cross attention optimization.
Weights loaded in 6.8s (load weights from disk: 0.2s, apply weights to model: 5.0s, hijack: 0.2s, move model to device: 1.3s).
                                                                               restoring last networks                                    | 0/6 [00:00<?, ?it/s]
original forward/weights is restored.
LoRA weight_unet: 0.65, weight_tenc: 0.65, model: panghu(c188991bd755)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.65, multiplier_tenc: 0.65
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
original forward/weights is backed up.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model panghu(c188991bd755) loaded: <All keys matched successfully>
LoRA weight_unet: 0.25, weight_tenc: 0.25, model: koreandolllikeness_V10(e2e472c06607)
dimension: {128}, alpha: {128.0}, multiplier_unet: 0.25, multiplier_tenc: 0.25
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model koreandolllikeness_V10(e2e472c06607) loaded: <All keys matched successfully>
LoRA weight_unet: 0.1, weight_tenc: 0.1, model: jingyijujingyi_juJingyiv10(448f2c32c80f)
dimension: {64}, alpha: {32.0}, multiplier_unet: 0.1, multiplier_tenc: 0.1
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model jingyijujingyi_juJingyiv10(448f2c32c80f) loaded: <All keys matched successfully>
LoRA weight_unet: 0.15, weight_tenc: 0.15, model: shojovibe_v11(65ece304ac27)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.15, multiplier_tenc: 0.15
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model shojovibe_v11(65ece304ac27) loaded: <All keys matched successfully>
setting (or sd model) changed. new networks created.
100%|███████████████████████████████████████████| 28/28 [01:04<00:00,  2.31s/it]
  4%|█▍                                       | 1/28 [04:46<2:09:05, 286.88s/it]
Total progress:  54%|██████████████▍            | 30/56 [06:56<06:00, 13.88s/it]
Loading weights [c590550ea5] from /Users/xuhao/StableDiff/stable-diffusion-webui/models/Stable-diffusion/grapefruitHentaiModel_grapefruitv41.safetensors
Applying sub-quadratic cross attention optimization.
Weights loaded in 4.1s (load weights from disk: 0.1s, apply weights to model: 2.7s, move model to device: 1.1s).
restoring last networks
original forward/weights is restored.
LoRA weight_unet: 0.65, weight_tenc: 0.65, model: panghu(c188991bd755)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.65, multiplier_tenc: 0.65
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
original forward/weights is backed up.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model panghu(c188991bd755) loaded: <All keys matched successfully>
LoRA weight_unet: 0.25, weight_tenc: 0.25, model: koreandolllikeness_V10(e2e472c06607)
dimension: {128}, alpha: {128.0}, multiplier_unet: 0.25, multiplier_tenc: 0.25
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model koreandolllikeness_V10(e2e472c06607) loaded: <All keys matched successfully>
LoRA weight_unet: 0.1, weight_tenc: 0.1, model: jingyijujingyi_juJingyiv10(448f2c32c80f)
dimension: {64}, alpha: {32.0}, multiplier_unet: 0.1, multiplier_tenc: 0.1
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model jingyijujingyi_juJingyiv10(448f2c32c80f) loaded: <All keys matched successfully>
LoRA weight_unet: 0.15, weight_tenc: 0.15, model: shojovibe_v11(65ece304ac27)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.15, multiplier_tenc: 0.15
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model shojovibe_v11(65ece304ac27) loaded: <All keys matched successfully>
setting (or sd model) changed. new networks created.
100%|███████████████████████████████████████████| 28/28 [01:12<00:00,  2.58s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:16<00:00,  2.72s/it]
100%|███████████████████████████████████████████| 28/28 [01:17<00:00,  2.77s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:15<00:00,  2.69s/it]
 54%|███████████████████████                    | 15/28 [00:41<00:36,  2.78s/it]
Total progress:  54%|██████████████▍            | 15/28 [00:40<00:35,  2.72s/it]
100%|███████████████████████████████████████████| 28/28 [01:15<00:00,  2.71s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:15<00:00,  2.68s/it]
100%|███████████████████████████████████████████| 28/28 [01:16<00:00,  2.72s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:15<00:00,  2.69s/it]
100%|███████████████████████████████████████████| 28/28 [01:17<00:00,  2.76s/it]
 50%|█████████████████████                     | 14/28 [44:14<44:14, 189.58s/it]
Total progress:  75%|████████████████████▎      | 42/56 [47:06<15:42, 67.30s/it]
Total prTile 1/1575%|███████████████████▌      | 42/56 [47:06<43:09, 185.00s/it]
	Tile 2/15
	Tile 3/15
	Tile 4/15
	Tile 5/15
	Tile 6/15
	Tile 7/15
	Tile 8/15
	Tile 9/15
	Tile 10/15
	Tile 11/15
	Tile 12/15
	Tile 13/15
	Tile 14/15
	Tile 15/15
Loading weights [7234b76e42] from /Users/xuhao/StableDiff/stable-diffusion-webui/models/Stable-diffusion/chilloutmix_Ni.safetensors
Applying sub-quadratic cross attention optimization.
Weights loaded in 6.8s (load weights from disk: 0.2s, apply weights to model: 5.0s, hijack: 0.2s, move model to device: 1.4s).
                                  restoring last networks
original forward/weights is restored.
LoRA weight_unet: 0.65, weight_tenc: 0.65, model: panghu(c188991bd755)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.65, multiplier_tenc: 0.65
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
original forward/weights is backed up.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model panghu(c188991bd755) loaded: <All keys matched successfully>
LoRA weight_unet: 0.1, weight_tenc: 0.1, model: jingyijujingyi_juJingyiv10(448f2c32c80f)
dimension: {64}, alpha: {32.0}, multiplier_unet: 0.1, multiplier_tenc: 0.1
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model jingyijujingyi_juJingyiv10(448f2c32c80f) loaded: <All keys matched successfully>
LoRA weight_unet: 0.15, weight_tenc: 0.15, model: shojovibe_v11(65ece304ac27)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.15, multiplier_tenc: 0.15
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model shojovibe_v11(65ece304ac27) loaded: <All keys matched successfully>
setting (or sd model) changed. new networks created.
 64%|███████████████████████████▋               | 18/28 [02:55<01:37,  9.74s/it]
Total progress: 18it [04:45, 15.88s/it]
restoring last networks4:45,  9.36s/it]
original forward/weights is restored.
LoRA weight_unet: 0.65, weight_tenc: 0.65, model: panghu(c188991bd755)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.65, multiplier_tenc: 0.65
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
original forward/weights is backed up.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model panghu(c188991bd755) loaded: <All keys matched successfully>
LoRA weight_unet: 0.25, weight_tenc: 0.25, model: koreandolllikeness_V10(e2e472c06607)
dimension: {128}, alpha: {128.0}, multiplier_unet: 0.25, multiplier_tenc: 0.25
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model koreandolllikeness_V10(e2e472c06607) loaded: <All keys matched successfully>
LoRA weight_unet: 0.1, weight_tenc: 0.1, model: jingyijujingyi_juJingyiv10(448f2c32c80f)
dimension: {64}, alpha: {32.0}, multiplier_unet: 0.1, multiplier_tenc: 0.1
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model jingyijujingyi_juJingyiv10(448f2c32c80f) loaded: <All keys matched successfully>
LoRA weight_unet: 0.15, weight_tenc: 0.15, model: shojovibe_v11(65ece304ac27)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.15, multiplier_tenc: 0.15
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model shojovibe_v11(65ece304ac27) loaded: <All keys matched successfully>
setting (or sd model) changed. new networks created.
100%|███████████████████████████████████████████| 28/28 [04:46<00:00, 10.24s/it]
Total progress: 100%|███████████████████████████| 28/28 [04:42<00:00, 10.09s/it]
restoring last networks█████████████████████████| 28/28 [04:42<00:00,  9.82s/it]
original forward/weights is restored.
LoRA weight_unet: 0.65, weight_tenc: 0.65, model: panghu(c188991bd755)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.65, multiplier_tenc: 0.65
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
original forward/weights is backed up.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model panghu(c188991bd755) loaded: <All keys matched successfully>
LoRA weight_unet: 0.1, weight_tenc: 0.1, model: jingyijujingyi_juJingyiv10(448f2c32c80f)
dimension: {64}, alpha: {32.0}, multiplier_unet: 0.1, multiplier_tenc: 0.1
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model jingyijujingyi_juJingyiv10(448f2c32c80f) loaded: <All keys matched successfully>
LoRA weight_unet: 0.15, weight_tenc: 0.15, model: shojovibe_v11(65ece304ac27)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.15, multiplier_tenc: 0.15
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model shojovibe_v11(65ece304ac27) loaded: <All keys matched successfully>
setting (or sd model) changed. new networks created.
 96%|█████████████████████████████████████████▍ | 27/28 [01:22<00:03,  3.06s/it]
Total progress:  96%|██████████████████████████ | 27/28 [01:21<00:03,  3.01s/it]
restoring last networks████████████████████████ | 27/28 [01:21<00:02,  3.00s/it]
original forward/weights is restored.
LoRA weight_unet: 0.65, weight_tenc: 0.65, model: panghu(c188991bd755)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.65, multiplier_tenc: 0.65
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
original forward/weights is backed up.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model panghu(c188991bd755) loaded: <All keys matched successfully>
LoRA weight_unet: 0.25, weight_tenc: 0.25, model: koreandolllikeness_V10(e2e472c06607)
dimension: {128}, alpha: {128.0}, multiplier_unet: 0.25, multiplier_tenc: 0.25
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model koreandolllikeness_V10(e2e472c06607) loaded: <All keys matched successfully>
LoRA weight_unet: 0.1, weight_tenc: 0.1, model: jingyijujingyi_juJingyiv10(448f2c32c80f)
dimension: {64}, alpha: {32.0}, multiplier_unet: 0.1, multiplier_tenc: 0.1
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model jingyijujingyi_juJingyiv10(448f2c32c80f) loaded: <All keys matched successfully>
LoRA weight_unet: 0.15, weight_tenc: 0.15, model: shojovibe_v11(65ece304ac27)
dimension: {32}, alpha: {32.0}, multiplier_unet: 0.15, multiplier_tenc: 0.15
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
shapes for 0 weights are converted.
LoRA model shojovibe_v11(65ece304ac27) loaded: <All keys matched successfully>
setting (or sd model) changed. new networks created.
 82%|███████████████████████████████████▎       | 23/28 [01:16<00:16,  3.34s/it]
Total progress:  82%|██████████████████████▏    | 23/28 [01:16<00:16,  3.32s/it]
100%|███████████████████████████████████████████| 28/28 [01:42<00:00,  3.67s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:41<00:00,  3.61s/it]
100%|███████████████████████████████████████████| 28/28 [01:30<00:00,  3.22s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:27<00:00,  3.12s/it]
100%|███████████████████████████████████████████| 28/28 [01:36<00:00,  3.43s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:35<00:00,  3.42s/it]
100%|███████████████████████████████████████████| 28/28 [01:34<00:00,  3.39s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:34<00:00,  3.38s/it]
 61%|██████████████████████████                 | 17/28 [00:58<00:37,  3.44s/it]
Total progress:  61%|████████████████▍          | 17/28 [00:58<00:37,  3.44s/it]
 43%|██████████████████▍                        | 12/28 [00:41<00:54,  3.43s/it]
Total progress:  43%|███████████▌               | 12/28 [00:41<00:55,  3.44s/it]
100%|███████████████████████████████████████████| 28/28 [01:32<00:00,  3.31s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:32<00:00,  3.30s/it]
100%|███████████████████████████████████████████| 28/28 [01:27<00:00,  3.14s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:27<00:00,  3.14s/it]
100%|███████████████████████████████████████████| 28/28 [01:41<00:00,  3.61s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:42<00:00,  3.65s/it]
Total progress: 100%|███████████████████████████| 28/28 [01:42<00:00,  3.65s/it]

Additional information

No response

Mar 25 '23 10:03 xuhao1

stable-diffusion-webui stable-diffusion-webui copied to clipboard

[Bug]: On Macos, image become weird if the width and height is not multiply of 32

Is there an existing issue for this?

What happened?

Steps to reproduce the problem

What should have happened?

Commit where the problem happens

What platforms do you use to access the UI ?

What browsers do you use to access the UI ?

Command Line Arguments

List of extensions

Console logs

Additional information

stable-diffusion-webui
stable-diffusion-webui copied to clipboard