sd vae drop down not showing for a week, cant make images

[lgwjames]

i have reinstalled and same thing. seems the sd vae is hidden and cant seem to work out why it is not showing

tried to rename config.jason and nothing on a new one. the drop-down shows if i click SD or all does show when i click XL or FLux

any ideas>?

[Joscpe]

I am having the same issue. I can get "VAE" to show under the 'all' UI, however it only allows for a single item selection. Did the multi select box get broken in the update?

[MisterChief95]

Can you share the UI version? It will be on the bottom of the UI page and be something like version: f2.0.1v1.10.1-previous-659-gc055f2d4. What's curious to me is that in the image above, your Diffusion With Low Bits is a series of checkboxes rather than a dropdown like I have:

Given that you're missing that dropdown + some additional options it seems like it's an older version.

[lgwjames]

API  •  Github  •  Gradio  •  Startup profile  •  Reload UI

version: f2.0.1v1.10.1-previous-224-g900196889  •  python: 3.10.6  •  torch: 2.3.1+cu121  •  xformers: N/A  •  gradio: 4.40.0  •  checkpoint: ac300751f3

been like this for over 2 weeks, each weekend i update, then make images, but now i cant as errors all the time and seems as no vae to pick

[lgwjames]

looks like it wasn't updating? well after 30 mins of searching . im now at

Version: f2.0.1v1.10.1-previous-659-gc055f2d43 Commit hash: c055f2d43b07cbfd87ac3da4899a6d7ee52ebab9 Traceback (most recent call last): File "C:\Users\jessi\Desktop\SD Forge\webui\launch.py", line 54, in main() File "C:\Users\jessi\Desktop\SD Forge\webui\launch.py", line 42, in main prepare_environment() File "C:\Users\jessi\Desktop\SD Forge\webui\modules\launch_utils.py", line 434, in prepare_environment raise RuntimeError( RuntimeError: Your device does not support the current version of Torch/CUDA! Consider download another version: https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/tag/latest

running the user file, now has

venv "C:\Users\jessi\Desktop\SD Forge\webui\venv\Scripts\Python.exe" Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: f2.0.1v1.10.1-previous-659-gc055f2d43 Commit hash: c055f2d43b07cbfd87ac3da4899a6d7ee52ebab9 Fetching updates for huggingface_guess... Checking out commit for huggingface_guess with hash: 84826248b49bb7ca754c73293299c4d4e23a548d... Previous HEAD position was 3f96b28 Update init.py HEAD is now at 8482624 Update model_list.py Installing requirements Launching Web UI with arguments: Total VRAM 12288 MB, total RAM 65414 MB pytorch version: 2.3.1+cu121 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3060 : native Hint: your device supports --cuda-malloc for potential speed improvements. VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16 Installing bitsandbytes==0.45.3 CUDA Using Stream: False Using pytorch cross attention Using pytorch attention for VAE Model selected: {'checkpoint_info': {'filename': 'C:\Users\jessi\Desktop\SD Forge\webui\models\Stable-diffusion\flux1-dev-bnb-nf4-v2.safetensors', 'hash': 'f0770152'}, 'additional_modules': [], 'unet_storage_dtype': None} Using online LoRAs in FP16: False Running on local URL: http://127.0.0.1:7861

To create a public link, set share=True in launch(). Startup time: 75.9s (prepare environment: 49.1s, launcher: 0.6s, import torch: 18.0s, initialize shared: 0.2s, other imports: 0.5s, load scripts: 3.6s, create ui: 2.7s, gradio launch: 0.9s). Environment vars changed: {'stream': False, 'inference_memory': 1024.0, 'pin_shared_memory': False} [GPU Setting] You will use 91.67% GPU memory (11263.00 MB) to load weights, and use 8.33% GPU memory (1024.00 MB) to do matrix computation. Model selected: {'checkpoint_info': {'filename': 'C:\Users\jessi\Desktop\SD Forge\webui\models\Stable-diffusion\flux1-dev-bnb-nf4-v2.safetensors', 'hash': 'f0770152'}, 'additional_modules': [], 'unet_storage_dtype': None} Using online LoRAs in FP16: False Model selected: {'checkpoint_info': {'filename': 'C:\Users\jessi\Desktop\SD Forge\webui\models\Stable-diffusion\flux1-dev-bnb-nf4-v2.safetensors', 'hash': 'f0770152'}, 'additional_modules': [], 'unet_storage_dtype': None} Using online LoRAs in FP16: False

and a drop down :)

going to test and report, thanks for the hint

[lgwjames]

got a photo 👍 , just got to do more settings

[Joscpe]

Can you share the UI version? It will be on the bottom of the UI page and be something like version: f2.0.1v1.10.1-previous-659-gc055f2d4. What's curious to me is that in the image above, your Diffusion With Low Bits is a series of checkboxes rather than a dropdown like I have:

Given that you're missing that dropdown + some additional options it seems like it's an older version.

I should have replied to this thread after, my bad... I found out my issue was in trusting git to update properly. Simply deleting my Forge and then installing the files resolved the missing parts and various issues like sluggishness I was having.