Compatibility Matrix#
The table below shows every supported model and optimizations supported for them.
The symbols used have the following meanings:
✅ = Full compatibility
❌ = No compatibility
⭕ = Does not apply to this model
Models x Optimization#
The HuggingFace Model ID
can be directly pass to from_pretrained()
methods and FastVideo will use the optimal default parameters when initializing and generating videos.
Model Name |
HuggingFace Model ID |
Resolutions |
TeaCache |
Sliding Tile Attn |
Sage Attn |
Video Sparse Attention (VSA) |
---|---|---|---|---|---|---|
FastWan2.1 T2V 1.3B |
|
480P |
⭕ |
⭕ |
⭕ |
✅ |
FastWan2.2 TI2V 5B Full Attn* |
|
720P |
⭕ |
⭕ |
⭕ |
✅ |
Wan2.2 TI2V 5B |
|
720P |
⭕ |
⭕ |
✅ |
⭕ |
Wan2.2 T2V A14B |
|
480P |
❌ |
❌ |
✅ |
⭕ |
Wan2.2 I2V A14B |
|
480P |
❌ |
❌ |
✅ |
⭕ |
HunyuanVideo |
|
720px1280p |
❌ |
✅ |
✅ |
⭕ |
FastHunyuan |
|
720px1280p |
❌ |
✅ |
✅ |
⭕ |
Wan2.1 T2V 1.3B |
|
480P |
✅ |
✅* |
✅ |
⭕ |
Wan2.1 T2V 14B |
|
480P, 720P |
✅ |
✅* |
✅ |
⭕ |
Wan2.1 I2V 480P |
|
480P |
✅ |
✅* |
✅ |
⭕ |
Wan2.1 I2V 720P |
|
720P |
✅ |
✅ |
✅ |
⭕ |
StepVideo T2V |
|
768px768px204f |
❌ |
❌ |
✅ |
⭕ |
Note: Wan2.2 TI2V 5B has some quality issues when performing I2V generation. We are working on fixing this issue.
Special requirements#
StepVideo T2V#
The self-attention in text-encoder (step_llm) only supports CUDA capabilities sm_80 sm_86 and sm_90
Sliding Tile Attention#
Currently only Hopper GPUs (H100s) are supported.