From product stills to campaign concepts.
Create square, portrait and landscape images. Use a reference when the result needs to follow a specific product, garment, person or look.
Start with a value option or select more detail, motion and reference control. The models listed here match Studio's current model selector; available settings and credits depend on the model.
Create square, portrait and landscape images. Use a reference when the result needs to follow a specific product, garment, person or look.
Create clips with model-specific durations, ratios and resolutions. Some models accept opening images or multiple visual references; the composer shows supported settings.
Choose for speed, reference flexibility or fine detail. The final result can vary between generations.
Original Gemini 2.5 Flash Image · lower cost · up to 3 references
Tongyi-MAI · fast concepts and variations · 1K · text only
Alibaba · natural textures, portraits and text · 1K or 2K · text only
Low or medium quality · square, portrait or landscape · up to 4 references
1K, 2K or 4K · up to 6 image references · token-billed estimate
Gemini 3.1 Flash Image · 1K, 2K or 4K · up to 6 references
Product-ready images · 2K · supports reference photos
Alibaba · multilingual text, detailed layouts and portraits · 1K or 2K · up to 3 references
ByteDance · complex briefs, typography and precise editing · 1K or 2K · up to 6 references
Detailed images and typography · high quality · up to 6 references
Duration, native audio, reference support and cost differ by model. Check the studio quote before starting a paid generation.
Portrait + speech audio · audio sets duration · 480P to 2K
Talking avatar · portrait + speech audio · automatic framing · lower cost
Portrait + speech · humans, animals or stylized characters · automatic framing
Premium avatar option · portrait + speech · automatic framing
ByteDance · audio-driven expressions and movement · audio under 60s at 720p or 30s at 1080p
Fast · 480P, 768P or 1080P · 5–15 seconds · start and end images · keyframes fitted to your selected ratio without cropping
Subject/style references · up to 6 images · native audio · reference-size optimization keeps cost predictable
Low-cost subject references · up to 6 images · 480p or 720p · 5–10 seconds · native audio
Consistent subjects · up to 6 images · fixed 5-second clip · no dialogue control
1080p to 4K · native audio · 6–20 seconds
Cinematic motion · native audio · up to 6 image references · 5–15 seconds
Standard · 480p or 720p · 5–15 seconds
Fast · 480p or 720p · 5–15 seconds
Mini · 480p or 720p · 5–15 seconds
Premium references · 480p or 720p · up to 6 image references · 5–30 seconds
Motion-focused video · 5 or 10 seconds · no native audio · keyframes fitted to your selected ratio without cropping
Native audio · 5–15 seconds · keyframes fitted to your selected ratio without cropping
Native audio · 5–15 seconds · keyframes fitted to your selected ratio without cropping
480P, 768P or 1080P · 5–15 seconds · keyframes fitted to your selected ratio without cropping
Explore image and video examples in the public showcase. Sign in to access industry templates and their reusable prompts. Avatar models are available under Creative task → Avatar creation; music models appear in the Music tab. Generation requires an eligible account, sufficient credits and an available service budget.
Explore the showcase ↗