update comfui_stablediffusion, add checkpoints and lora

[pschroedl]

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

[leszko]

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"

1. For the sake of consistency, can we change everything to get downloaded with huggingface-cli? This what I suggested worked for me
2. Do I understand correctly that the streamdiffusion node takes models from /models/checkpoints and not from the comfyui workspace directory /comfui/models?

[leszko]

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]

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?