Instructions to use Alissonerdx/BFS-Best-Face-Swap-Video with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Alissonerdx/BFS-Best-Face-Swap-Video with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2.3", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Alissonerdx/BFS-Best-Face-Swap-Video") prompt = "A man with short gray hair plays a red electric guitar." input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png") image = pipe(image=input_image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
help with ComfyUI-Ollama-Describer
It's me again, also having problems with ComfyUI-Ollama-Describer in v3. I was able to get the other node to install fine but this one is not working. It installed but every restart still shows it's missing. Any ideas? Thanks.
I figured it out, git cloneing it was important, comfyui manager was installing an old incomplete version.
Root Cause: The installed version of comfyui-ollama-describer was an old version that was missing several nodes including OllamaVideoDescriber (which your workflow uses), OllamaAgent, OllamaVideoDescriber, and others. It also had WEB_DIRECTORY commented out and no js/ folder.
What was fixed:
Removed the old, outdated files from the node folder
Cloned the latest version (commit c332a56) fresh from GitHub
Verified all requirements are satisfied (ollama 0.6.0 >= required 0.4.8)
Confirmed OllamaVideoDescriber and WEB_DIRECTORY = "./js" are present in the new version