Instructions to use dashtoon/hunyuan-video-keyframe-control-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dashtoon/hunyuan-video-keyframe-control-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dashtoon/hunyuan-video-keyframe-control-lora", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Are there any plan to open training source code
#2
by HighCWu - opened
I'm glad that your model uses the same idea as my open source project control-lora-v3. I'm glad that you open sourced the weights. I wonder if you have plans to open source the training code? It would be great to the open source community.
yes we are working on a training code release and a blog. It will be released soon
hi @HighCWu we have released the tranining code here : https://github.com/dashtoon/hunyuan-video-keyframe-control-lora
Well done. I believe this will help the open source community explore more possibilities of hunyuanvideo
HighCWu changed discussion status to closed