The table below shows every supported model and the optimizations supported for them.
Key:
Yes = CompatibleNo = IncompatibleN/A = Not applicable
Models x Optimization
The HuggingFace Model ID can be passed directly to from_pretrained() methods, and sglang-diffusion will use the optimal default parameters when initializing and generating videos.
Video Generation Models
| Model Name | HuggingFace Model ID | Resolutions | TeaCache | Sliding Tile Attn | Sage Attn | Video Sparse Attention (VSA) | Sparse Linear Attention (SLA) | Sage Sparse Linear Attention (SageSLA) | Sparse Video Gen 2 (SVG2) |
|---|
| FastWan2.1 T2V 1.3B | FastVideo/FastWan2.1-T2V-1.3B-Diffusers | 480p | N/A | N/A | N/A | Yes | No | No | No |
| FastWan2.2 TI2V 5B Full Attn | FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers | 720p | N/A | N/A | N/A | Yes | No | No | No |
| Wan2.2 TI2V 5B | Wan-AI/Wan2.2-TI2V-5B-Diffusers | 720p | N/A | N/A | Yes | N/A | No | No | No |
| Wan2.2 T2V A14B | Wan-AI/Wan2.2-T2V-A14B-Diffusers | 480p, 720p | No | No | Yes | N/A | No | No | No |
| Wan2.2 I2V A14B | Wan-AI/Wan2.2-I2V-A14B-Diffusers | 480p, 720p | No | No | Yes | N/A | No | No | No |
| HunyuanVideo | hunyuanvideo-community/HunyuanVideo | 720x1280, 544x960 | No | Yes | Yes | N/A | No | No | Yes |
| FastHunyuan | FastVideo/FastHunyuan-diffusers | 720x1280, 544x960 | No | Yes | Yes | N/A | No | No | Yes |
| Wan2.1 T2V 1.3B | Wan-AI/Wan2.1-T2V-1.3B-Diffusers | 480p | Yes | Yes | Yes | N/A | No | No | Yes |
| Wan2.1 T2V 14B | Wan-AI/Wan2.1-T2V-14B-Diffusers | 480p, 720p | Yes | Yes | Yes | N/A | No | No | Yes |
| Wan2.1 I2V 480P | Wan-AI/Wan2.1-I2V-14B-480P-Diffusers | 480p | Yes | Yes | Yes | N/A | No | No | Yes |
| Wan2.1 I2V 720P | Wan-AI/Wan2.1-I2V-14B-720P-Diffusers | 720p | Yes | Yes | Yes | N/A | No | No | Yes |
| TurboWan2.1 T2V 1.3B | IPostYellow/TurboWan2.1-T2V-1.3B-Diffusers | 480p | Yes | No | No | No | Yes | Yes | N/A |
| TurboWan2.1 T2V 14B | IPostYellow/TurboWan2.1-T2V-14B-Diffusers | 480p | Yes | No | No | No | Yes | Yes | N/A |
| TurboWan2.1 T2V 14B 720P | IPostYellow/TurboWan2.1-T2V-14B-720P-Diffusers | 720p | Yes | No | No | No | Yes | Yes | N/A |
| TurboWan2.2 I2V A14B | IPostYellow/TurboWan2.2-I2V-A14B-Diffusers | 720p | Yes | No | No | No | Yes | Yes | N/A |
- Wan2.2 TI2V 5B has known quality issues for some I2V workloads.
- SageSLA is based on SpargeAttn. Install SpargeAttn first with
pip install git+https://github.com/thu-ml/SpargeAttn.git --no-build-isolation.
Image Generation Models
| Model Name | HuggingFace Model ID | Resolutions |
|---|
| FLUX.1-dev | black-forest-labs/FLUX.1-dev | Any resolution |
| FLUX.2-dev | black-forest-labs/FLUX.2-dev | Any resolution |
| FLUX.2-Klein | black-forest-labs/FLUX.2-klein-4B | Any resolution |
| Z-Image-Turbo | Tongyi-MAI/Z-Image-Turbo | Any resolution |
| GLM-Image | zai-org/GLM-Image | Any resolution |
| Qwen Image | Qwen/Qwen-Image | Any resolution |
| Qwen Image 2512 | Qwen/Qwen-Image-2512 | Any resolution |
| Qwen Image Edit | Qwen/Qwen-Image-Edit | Any resolution |
Verified LoRA Examples
This section lists example LoRAs that have been explicitly tested and verified with each base model in the SGLang Diffusion pipeline.
LoRAs that are not listed here are not necessarily incompatible.
In practice, most standard LoRAs are expected to work, especially those following common Diffusers or SD-style conventions.
The entries below simply reflect configurations that have been manually validated by the SGLang team.
Verified LoRAs by Base Model
| Base Model | Supported LoRAs |
|---|
| Wan2.2 | lightx2v/Wan2.2-Distill-Loras
Cseti/wan2.2-14B-Arcane_Jinx-lora-v1 |
| Wan2.1 | lightx2v/Wan2.1-Distill-Loras |
| Z-Image-Turbo | tarn59/pixel_art_style_lora_z_image_turbo
wcde/Z-Image-Turbo-DeJPEG-Lora |
| Qwen-Image | lightx2v/Qwen-Image-Lightning
flymy-ai/qwen-image-realism-lora
prithivMLmods/Qwen-Image-HeadshotX
starsfriday/Qwen-Image-EVA-LoRA |
| Qwen-Image-Edit | ostris/qwen_image_edit_inpainting
lightx2v/Qwen-Image-Edit-2511-Lightning |
| Flux | dvyio/flux-lora-simple-illustration
XLabs-AI/flux-furry-lora
XLabs-AI/flux-RealismLora |
Special requirements
Sliding Tile Attention
- Currently, only Hopper GPUs (H100s) are supported.
