update comfui_stablediffusion, add checkpoints and lora #364
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
pschroedl
requested review from
leszko,
emranemran,
eliteprox and
ad-astra-video
leszko
reviewed
Dec 13, 2024
runner/dl_checkpoints.sh
Outdated
Comment on lines
108
to
115
| huggingface-cli download KBlueLeaf/kohaku-v2.1 --local-dir models/ComfyUI--models/checkpoints --include "*.safetensors" | ||
| huggingface-cli download stabilityai/sd-turbo --local-dir models/ComfyUI--models/checkpoints --include "*.safetensors" | ||
|
|
||
| # ComfyUI_StreamDIffusion is loading single file safetensors from /models/checkpoints | ||
| wget -P models/checkpoints/ https://huggingface.co/KBlueLeaf/kohaku-v2.1/resolve/main/kohaku-v2.1.safetensors | ||
| wget -P models/checkpoints/ https://huggingface.co/stabilityai/sd-turbo/resolve/main/sd_turbo.safetensors | ||
| # chenxxiao/3dCartoonVision_v10 | ||
| wget -P models/checkpoints https://huggingface.co/chenxxiao/3dCartoonVision_v10/resolve/main/3dCartoonVision_v10.safetensors?download=true --content-disposition |
There was a problem hiding this comment.
Suggested change
| huggingface-cli download KBlueLeaf/kohaku-v2.1 --local-dir models/ComfyUI--models/checkpoints --include "*.safetensors" | |
| huggingface-cli download stabilityai/sd-turbo --local-dir models/ComfyUI--models/checkpoints --include "*.safetensors" | |
| # ComfyUI_StreamDIffusion is loading single file safetensors from /models/checkpoints | |
| wget -P models/checkpoints/ https://huggingface.co/KBlueLeaf/kohaku-v2.1/resolve/main/kohaku-v2.1.safetensors | |
| wget -P models/checkpoints/ https://huggingface.co/stabilityai/sd-turbo/resolve/main/sd_turbo.safetensors | |
| # chenxxiao/3dCartoonVision_v10 | |
| wget -P models/checkpoints https://huggingface.co/chenxxiao/3dCartoonVision_v10/resolve/main/3dCartoonVision_v10.safetensors?download=true --content-disposition | |
| huggingface-cli download KBlueLeaf/kohaku-v2.1 --local-dir models/checkpoints --include "*.safetensors" | |
| huggingface-cli download stabilityai/sd-turbo --local-dir models/checkpoints --include "*.safetensors" | |
| # chenxxiao/3dCartoonVision_v10 | |
| huggingface-cli download chenxxiao/3dCartoonVision_v10 --local-dir models/checkpoints --include "*.safetensors" |
- For the sake of consistency, can we change everything to get downloaded with
huggingface-cli? This what I suggested worked for me - Do I understand correctly that the streamdiffusion node takes models from
/models/checkpointsand not from the comfyui workspace directory/comfui/models?
There was a problem hiding this comment.
Created HF-hub repos for checkpoints and Loras to get rid of wget downloads.
The streamdiffusion node takes models the comfyui workspace directory /comfui/models/checkpoints.
leszko
reviewed
Dec 13, 2024
runner/dl_checkpoints.sh
Outdated
|
|
||
| function download_stable_diffusion_loras() { | ||
| # ral-dissolve-sd15 LoRA | ||
| wget -P models/loras https://civitai.com/api/download/models/314246?type=Model&format=SafeTensor --content-disposition |
There was a problem hiding this comment.
Suggested change
| wget -P models/loras https://civitai.com/api/download/models/314246?type=Model&format=SafeTensor --content-disposition | |
| wget -P models/loras https://civitai.com/api/download/models/314246?type=Model\&format=SafeTensor --content-disposition |
This does not work for me, it requires some civitai authentication. I get the following error:
Username/Password Authentication Failed.
leszko
reviewed
Dec 13, 2024
There was a problem hiding this comment.
Thanks for the PR. Added some comments. Other than that I tried to test it, but was not sure which API JSON is the one I should try.
I see that now you have a lot of them in the examples directory. I tried no_acceleration.json, but got the following error:
Cannot execute because node StreamDiffusionConfig does not exist.
Could you point me to the API JSON workflow that I can test?
All should be updated now to use the correctly named nodes.
I've removed the older, outdated workflows from the repo |
leszko
reviewed
Dec 17, 2024
leszko
approved these changes
Dec 17, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Performance updates to ComfyUI_StableDiffusion from:
pschroedl/ComfyUI-StreamDiffusion#6
Example Workflow Updates:
pschroedl/ComfyUI-StreamDiffusion#7
Node now loads safetensor files ( full huggingface checkpoint loading is broken ), this PR adds checkpoints for:
sd_turbo.safetensors, kohaku_v2.1.safetensors and
https://huggingface.co/chenxxiao/3dCartoonVision_v10
and lora : ral-dissolve1.5
https://civitai.com/models/245889?modelVersionId=314246