Hugging Face's logo

Kijai
/
SkyReels-V1-Hunyuan_comfy

GGUF
Model card Files Community
8
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

https://huggingface.co/Skywork/SkyReels-V1-Hunyuan-I2V

https://huggingface.co/Skywork/SkyReels-V1-Hunyuan-T2V

Converted from the diffusers format to the original HunyuanVideo format, which works with both my wrapper ComfyUI nodes, and native ComfyUI HunyuanWorkflows.

In native workflows you'd feed the image in using "InstructPixtoPixConditioning" or similar node that adds an encoded image as extra conditioning.

Example workflow: https://huggingface.co/Kijai/SkyReels-V1-Hunyuan_comfy/resolve/main/skyreels_hunyuan_I2V_native_example_01.json

GGUF version created with help from city96 and using his conversion scripts, works with his nodes: https://github.com/city96/ComfyUI-GGUF

Downloads last month
17,746
GGUF
Model size
12.8B params
Architecture
hyvid

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.