Downloads · 30 days
1.5K
10% of all-time downloads
Wan2.1-T2V-14B-Diffusers-DF11
DFloat11/Wan2.1-T2V-14B-Diffusers-DF11
Wan2.1-T2V-14B-Diffusers-DF11 is a text-to-image model from DFloat11. Use it when you need an image from a text prompt. It is set up for diffusers.
This model uses DFloat11 lossless compression. It's 30% smaller than the original BFloat16 model, yet produces bit-identical outputs and runs efficiently on GPUs.
All-time downloads
14.1K
Public
Parameters
233M
19.4 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors19.4 GB · 100%
Parameter types
How the weights are stored.
BF16205M · 88%
Base models
Model card
From the Hugging Face model README
DFloat11 Compressed Model: Wan-AI/Wan2.1-T2V-14B-Diffusers
This model uses DFloat11 lossless compression. It's 30% smaller than the original BFloat16 model, yet produces bit-identical outputs and runs efficiently on GPUs.
📊 Performance Comparison
| Metric | Wan2.1-T2V-14B (BFloat16) | Wan2.1-T2V-14B (DFloat11) |
|---|---|---|
| Model Size | 28.64 GB | 19.39 GB |
| Peak GPU Memory<br>(2s 480p Video) | 30.79 GB | 22.22 GB |
| Generation Time<br>(an A100 GPU) | 339 seconds | 348 seconds |
🔍 How It Works
We apply Huffman coding to the exponent bits of BFloat16 model weights, which are highly compressible. We leverage hardware-aware algorithmic designs to enable highly efficient, on-the-fly weight decompression directly on the GPU. Find out more in our research paper.
🔧 How to Use
A complete usage guide is available in our GitHub repository: https://github.com/LeanModels/DFloat11/tree/master/examples/wan2.1.
📄 Learn More
- Task
- Text-to-Image
- Library
- diffusers
- Type
- llama
- Created
- May 23, 2025
- Updated
- May 23, 2025