Every model, in one Studio and one API.
Video, image, lipsync and captions models from every lab Sume runs. Pick one and start, or let the agents pick.
Video
- Genjutsu Motion TransferHiggsfield
- Seedance 2.5ByteDance
- Seedance 2.0 MiniByteDance
- Seedance 2.0ByteDance
- Seedance 2.0 FastByteDance
- Kling Video v3 ProKling
- Wan 3.0Alibaba
- Grok Imagine Video 1.5xAI
- MiniMax H3MiniMax
- MiniMax H3 MaxMiniMax
- Gemini Omni Flash 1.1Google
- H3 Max RecastMiniMax
- Vidu Q4Vidu
- Vidu Q4 ReferenceVidu
- Veo 3.1Google
- Veo 3.1 FastGoogle
- Veo 3.1 Lite (Preview)Google
- WAND-Vega 1.0 LiteTencent
- WAND-Vega 1.0 ProTencent
- WAND-Vega 1.5 ProTencent
- Mingmou 1Tencent
- Hunyuan 1.5Tencent
- Hailuo H3 RegenMiniMax
- HeyGen Video 1HeyGen
Image
- Soul (Higgsfield)Higgsfield
- ChatGPT Image 2.5OpenAI
- ChatGPT Image 2.5 SunburstOpenAI
- ChatGPT Image 2OpenAI
- Nano Banana 2.1Google
- Nano Banana ProGoogle
- Seedream 5.0 LiteByteDance
- Seedream 4.5ByteDance
- Grok ImaginexAI
- Seedream 4.0ByteDance
- Qwen ImageAlibaba
- Imagen 4 FastGoogle
- Imagen 4 UltraGoogle
- Flux 2 ProBlack Forest Labs
- Flux 2 FlexBlack Forest Labs
- Ideogram V3Ideogram
- Recraft V4Recraft
- Qwen Image MaxAlibaba
- Qwen Image LayeredAlibaba
- Ideogram 4.5Ideogram
Lipsync
- VEED Fabric 1.0VEED
- VEED Fabric 1.0 FastVEED
- MiniMax H3 Max Lip SyncMiniMax
- Kling Avatar 2.0 ProKling
- Kling Avatar 2.0Kling
- InfiniteTalkMeiGen
- OmniHuman 1.5ByteDance
- Creatify AuroraCreatify
- Wan 2.2 Speech to VideoAlibaba
- Sync Lipsync 3Sync Labs
- Sync Lipsync 2 ProSync Labs
- Sync Lipsync 2Sync Labs
- Kling LipsyncKling
- LatentSyncByteDance
- VEED LipsyncVEED
- InfiniteTalk VideoMeiGen
- PixVerse LipsyncPixVerse