#LCM #A1111 #nvidia #tensorRT #ai #StableDiffusion
Latent Consistency Models x10 speeds 10FPS
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
SOCIAL MEDIA LINKS!
✨ Support my (*・‿・)ノ⌒*:・゚✧
character available at https://ko-fi.com/impactframes/shop
SD related https://civitai.com/user/impactframes
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
VIDEO LINKS📄🖍️o(≧o≦)o🔥
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
https://latent-consistency-models.github.io/
https://github.com/luosiallen/latent-consistency-model
https://github.com/luosiallen/latent-consistency-model
https://github.com/0xbitches/ComfyUI-LCM/tree/main
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
🔥NOTES
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
go to your .cache folder
x:\Users\xxxx\.cache\huggingface\hub\models--SimianLuo--LCM_Dreamshaper_v7\snapshots\c7f9cc72c6ca6c4af5cdss68c9fdssb26eb8\tokenizer
edit the added_tokens.json replace the contents with
{
"<|endoftext|>": 49409,
"<|startoftext|>": 49408
}
for people having issues
kill the comfy cli
X:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LCM
edit the node.py
online 48 and 49
scheduler=self.scheduler,
safety_checker=None,
Make sure to save and reopen to see if changes are persistent
re start confy cli
X:\ComfyUI_windows_portable\python_embeded
Type CMD on the search bar to open command prompt
python.exe -m pip install transformers diffusers accelerate
from diffusers import StableDiffusionPipeline
repo_id = "SimianLuo/LCM_Dreamshaper_v7"
pipe = StableDiffusionPipeline.from_pretrained(repo_id, use_safetensors=True)