The models most teams start with.
bytedance/Seedance 2.5
3 modes
Generates video from text, an image, references · 480p to 1080p · 4–30 s · native audio
kling/Kling Video v3 Pro
2 modes
Generates video from text, an image · 1080p · 4–15 s · native audio

google/Nano Banana Pro
2 modes
Generates and edits images · up to 4K · up to 4 per request
alibaba/Wan 3.0
3 modes
Generates video from text, an image, references · 480p to 1080p · 2–30 s · native audio
bytedance/Seedance 2.0 Mini
3 modes
Generates video from text, an image, references · 480p to 720p · 4–15 s · native audio
kling/Kling 3.0 Omni
2 modes
Generates video from text, an image · 720p to 1080p · 3–15 s · native audio
alibaba/Wan 3.0 Prime
2 modes
Generates video from text, an image · 480p to 1080p · 2–30 s · native audio
minimax/MiniMax H3
3 modes
Generates video from text, an image, references · 768p to 4K · 5–15 s · native audio
Generate and edit images from text and references. 21 models.
Turn prompts, stills and references into moving footage. 31 models.
Make a face say an audio track, or burn captions into a video. 18 models.