Model support
Additional models will be added as they become available and there is public interest in them
See models overview for details on each model, including their architecture, complexity and other info
- RunwayML Stable Diffusion 1.x (all variants)
- StabilityAI Stable Diffusion 2.1 Base and V
- StabilityAI Stable Diffusion XL
- StabilityAI Stable Diffusion 3.0 Medium
- StabilityAI Stable Diffusion 3.5 Medium, Large, Large Turbo
- StabilityAI Stable Cascade Full and Lite
- Black Forest Labs FLUX.1 Dev, Schnell, Fill, Depth, Kontext-Dev
- Black Forest Labs FLUX.2 Dev, Klein and Klein Base
- Black Forest Labs FLUX.3 Klein Base
- lodestones Chroma Standard, Detail Calibrated, Flash, 1 Base, 1 HD and v50 Preview Annealed
- FreePik F-Lite Standard, Texture and 7B
- NVLabs Sana 1.0 and 1.5
- nVidia Cosmos-Predict2 T2I 2B and 14B
- AuraFlow 0.3 and 0.2
- AlphaVLLM Lumina-Next-SFT
- AlphaVLLM Lumina 2
- Playground AI v1, v2 256, v2 512, v2 1024 and latest v2.5
- Tencent HunyuanDiT 1.2 and 1.1
- OmniGen
- Meissonic
- Kwai Kolors
- Ostris Flex 1 Alpha and 2 Preview
- CogView 3 Plus and 4
- LCM: Latent Consistency Models
- aMUSEd 256 and 512
- Segmind Vega
- Segmind SSD-1B
- Segmind SegMoE SD 4x2 and SD-XL 4x2
- Segmind SD Distilled (all variants)
- Kandinsky 2.1, 2.2, 3.0, 5.0
- Z-Image Turbo and Base
- PixArt-α XL 2 Medium and Large
- PixArt-Σ Small, Medium and Large
- Warp Wuerstchen
- Tsinghua UniDiffusion
- DeepFloyd IF Medium and Large
- ModelScope T2V
- BLIP-Diffusion
- InstaFlow 0.9B
- KOALA 700M
- VGen
- SDXS DreamShaper 512 and 1B
- Hyper-SD
- HiDream-I1 Full, Dev, Fast
- HiDream-E1 Full and 1.1
- HiDream-O1 Image
- Wan 2.1 1.3B and 14B T2V models for T2I workflows
- Wan 2.2 5B, A14B T2V/I2V, and 14B VACE
- Bria 3.2 and FIBO 1.0/1.5, FIBO-Edit 1.0/1.5
- Qwen-Image original, 2509, 2511, 2512, 2.1 and Layered
- Qwen-Image-Edit original, 2509 and 2511
- Photoroom PRX Beta and PRXPixel
- Google Gemini 2.5 Flash and 3.0 Pro
- Meituan LongCat Image and Image-Edit
- Z.ai GLM Image
- X-Omni SFT
- HDM-XUT 340M Anime
- ObjectClear
- Hunyuan Image 2.1 and Refiner
- nVidia ChronoEdit 14B
- UltraFlux v1
- AIDC Ovis Image 7B
- VIBE-Edit
- Microsoft Lens and Lens Base
- Anima 1.0 Base, Aesthetic and 2.9B Preview v1
- Boogu Image 0.1 Base and Edit
- Ideogram 4
- Krea 2 Base
- JoyAI Image Edit and Edit Plus
- Microsoft Mage-Flow 4B
- SeFi-Image 1B, 2B, 5B Base and 5B RL
- MiniMax-H3 Base and Ref2VA
- LLaDA-Image
- inclusionAI Ming-Image 0.1 Design
- OpenMOSS MOSS-Image SFT and Base
- StepFun Step1X-Edit v1.1
- Nucleus Image
- ERNIE-Image
- Zeta-Chroma
Support Notes
- HunyuanDit models requires explicit
float16precision
set in settings -> compute settings -> model precision -> fp16 - aMUSEd models require explicit noise generator device to be unset
set in settings -> compute settings -> generator device -> unset