From the model card
Fields below are copied from the tags and counters on the HuggingFace repository DeepBeepMeep/Wan2.1 at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.
- Publisher (HF namespace)
- DeepBeepMeep
- Weight formats
- ONNX, safetensors, GGUF
- Lineage
-
- base model Wan-AI/Wan2.1-T2V-1.3B
- quantized from Wan-AI/Wan2.1-T2V-1.3B
- Downloads (HF counter at last fetch)
- 473,789
- Likes (HF counter at last fetch)
- 49
- Model card
- https://huggingface.co/DeepBeepMeep/Wan2.1
Use cases
- Animating product photography into short video clips
- Creating motion from static concept art in ComfyUI workflows
- Rapid video prototyping from image inputs without custom code
- Social media content creation from still brand imagery
- Testing WAN 2.1 quality before deploying the full multi-file checkpoint
Pros
- Single-file diffusion format loads directly in ComfyUI without weight conversion
- i2v (image-to-video) capability enables animation of existing images
- 38 likes with ComfyUI community use and validation
Cons
- No explicit license; inherits original WAN terms which should be verified
- Single-file format is not suitable for fine-tuning or model modification
- Video generation requires substantial VRAM; consumer GPUs under 16GB will struggle
- Community repackage may lag official WAN 2.1 updates
Tags
diffusion-single-fileonnxsafetensorsggufi2vbase_model:Wan-AI/Wan2.1-T2V-1.3Bbase_model:quantized:Wan-AI/Wan2.1-T2V-1.3Bregion:us