Instructions to use LiconStudio/VBVR-wan2.2-comfy-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LiconStudio/VBVR-wan2.2-comfy-bf16 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("LiconStudio/VBVR-wan2.2-comfy-bf16", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Wan2.2
How to use LiconStudio/VBVR-wan2.2-comfy-bf16 with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Inference settings for VBVR-wan2.2-comfy-bf16.safetensors
Hi, thanks for the model! Could you clarify the recommended settings for ComfyUI?
Specifically, what is the total number of steps required, and how should the steps be distributed between the High Noise and Low Noise models? A sample workflow would be greatly appreciated. Thanks!
Hi, thanks for the model! Could you clarify the recommended settings for ComfyUI?
Specifically, what is the total number of steps required, and how should the steps be distributed between the High Noise and Low Noise models? A sample workflow would be greatly appreciated. Thanks!
The strength range is between 0.7 and 1.0, though you’ll need to adjust and test this based on your specific task. I recommend looking for verified workflows from others on RunningHub or similar platforms. For my own part, I’ve only conducted some simple tests using the official workflow.