Instructions to use TheDenk/wan2.2-ti2v-5b-controlnet-depth-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TheDenk/wan2.2-ti2v-5b-controlnet-depth-v1 with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("TheDenk/wan2.2-ti2v-5b-controlnet-depth-v1") pipe = StableDiffusionControlNetPipeline.from_pretrained( "fill-in-base-model", controlnet=controlnet ) - Wan2.2
How to use TheDenk/wan2.2-ti2v-5b-controlnet-depth-v1 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
will there be a tile lora for wan2.2 5b?
that will be pretty awesome
I'm not sure, but it is good idea, thanks :)
I'm not sure, but it is good idea, thanks :)
how to use this in comfyui?
I have tried everything to get this working inside Comfyui. Have tried countless node configurations including the ComfyUI-WanVidieoWrapper. I cannot get this to work. After searching the web I came to the conclusion that noone has managed to get this to work with Comfyui. Could you please help?
@WernerrenreW
Hey, thanks for this notice. I've opened PR to fix some problems for wan controlnet. You can see here. I've also added workflow examples to Github repo and Huggingface cards.
Thank you!
https://huggingface.co/TheDenk/wan2.2-ti2v-5b-controlnet-tile-v1
thanks for your effort,,,and I foud the output video changed a lot, far from the input one
It's March 18, 2026 now. Do you have any better models to recommend for ti2v-depth control?