๐ฅ Wan2.1_14B_T2V-FusionX - Formerly named MasterModel, which served as a placeholder. Its the exact same model, just a new name.
A powerful merged text-to-video model based on the original WAN 2.1 T2V model, enhanced using multiple open-source components and LoRAs to boost motion realism, temporal consistency, and expressive detail. multiple open-source models and LoRAs to boost temporal quality, expressiveness, and motion realism.
๐ง Model Blend Includes:
- ๐ AccVideo
- ๐ MoviiGen1.1
- ๐ CausVid
- ๐ MPS Rewards LoRA
- โจ Custom detail-enhancer LoRAs I created specifically for this merge
- Only 8-10 steps are needed to get great results!
- All are under Apache 2.0 or MIT licenses and fully permitted for merge and reuse.
๐ผ๏ธ Example Prompt
Prompt:
Tight close-up of her smiling lips and sparkling eyes, catching golden hour sunlight. She wears a white sundress with floral prints and a wide-brimmed straw hat. Camera pulls back in a dolly motion, revealing her twirling under a cherry blossom tree. Petals flutter in the air, casting playful shadows. Soft lens flares enhance the euphoric, dreamlike vibe.
Negative Prompt (CN):
่ฒ่ฐ่ณไธฝ๏ผ่ฟๆ๏ผ้ๆ๏ผ็ป่ๆจก็ณไธๆธ ๏ผๅญๅน๏ผ้ฃๆ ผ๏ผไฝๅ๏ผ็ปไฝ๏ผ็ป้ข๏ผ้ๆญข๏ผๆดไฝๅ็ฐ๏ผๆๅทฎ่ดจ้๏ผไฝ่ดจ้๏ผJPEGๅ็ผฉๆฎ็๏ผไธ้็๏ผๆฎ็ผบ็๏ผๅคไฝ็ๆๆ๏ผ็ปๅพไธๅฅฝ็ๆ้จ๏ผ็ปๅพไธๅฅฝ็่ธ้จ๏ผ็ธๅฝข็๏ผๆฏๅฎน็๏ผๅฝขๆ็ธๅฝข็่ขไฝ๏ผๆๆ่ๅ๏ผ้ๆญขไธๅจ็็ป้ข๏ผๆไนฑ็่ๆฏ๏ผไธๆก่ ฟ๏ผ่ๆฏไบบๅพๅค๏ผๅ็่ตฐ
๐งฐ How to Use (ComfyUI)
- Download the
.safetensorsfile from the Files tab. - Place it into your
ComfyUI/models/diffusion_models/folder. - Restart ComfyUI.
- Use the Checkpoint Loader node and connect it to your text-to-video workflow.
- Since CausVid is merged into this model, you only need no more than 10 steps to get great results.
๐ฆ Downloads
Weights available in .safetensors format
๐ Download here
โ ๏ธ License Notice
This merged model combines components licensed under Apache 2.0 and MIT โ both of which are permissive open-source licenses.
โ You are allowed to:
- Use, modify, and redistribute the model (including commercial use)
- Integrate it into your own projects or tools
๐ You must:
- Include original license notices if you redistribute the model
- Avoid implying endorsement or affiliation with the original authors (as required by Apache 2.0)
๐ Output Content:
- Generated videos are not licensed by the modelโs open-source license
- If any merged model relied on datasets with restrictions, those rules may still apply to the outputs
This model is intended for research and creative exploration, not guaranteed for production use without further validation.
๐ Thanks To
- Alibaba-PAI
- aejion
- ZuluVision
- Tianwei Yin (CausVid)
- Kaji
Big thanks to all original devs โ this merge wouldn't be possible without your amazing work.