GPT Image 2.5 Flare Edit
GPT Image 2.5 Flare Edit applies natural-language instructions to up to 16 reference images, with an optional mask, arbitrary resolutions up to 3840x2160, five quality tiers including xhigh and max, and transparent-background output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Seedance 2.5 Reference-to-Video
Multimodal video generation from reference images, videos, and audio. Supports video editing and extension.
Seedance 2.5 Image-to-Video
Generate videos from a first-frame image (and optional last-frame) with native audio.
Seedance 2.5 Text-to-Video
Generate videos from text prompts with native audio and optional web search.
Seedance 2.0 Mini Reference-to-Video
Lightweight, economical multimodal video generation from reference images, videos, and audio with native audio.
Seedance 2.0 Mini Image-to-Video
Lightweight, economical video generation from a first-frame image (and optional last-frame) with native audio.
Seedance 2.0 Mini Text-to-Video
Lightweight, economical video generation from text prompts with native audio.
Seedance 2.0 Text-to-Video
Generate videos from text prompts with native audio and optional web search.
Seedance 2.0 Image-to-Video
Generate videos from a first-frame image (and optional last-frame) with native audio.
Seedance 2.0 Reference-to-Video
Multimodal video generation from reference images, videos, and audio. Supports video editing and extension.
Seedance 2.0 Fast Text-to-Video
Fast video generation from text prompts with native audio.
Seedance 2.0 Fast Image-to-Video
Fast video generation from first-frame image (and optional last-frame) with native audio.
Seedance 2.0 Fast Reference-to-Video
Fast multimodal video generation from reference images, videos, and audio. Supports video editing and extension.
Seedance v1.5 Pro Image-to-Video
Native audio-visual joint generation model by ByteDance. Supports unified multimodal generation with precise audio-visual sync, cinematic camera control, and enhanced narrative coherence.
Seedance v1.5 Pro Text-to-Video
Native audio-visual joint generation model by ByteDance. Supports unified multimodal generation with precise audio-visual sync, cinematic camera control, and enhanced narrative coherence.
Seedance v1.5 Pro Image-to-Video Fast
Native audio-visual joint generation model by ByteDance. Supports unified multimodal generation with precise audio-visual sync, cinematic camera control, and enhanced narrative coherence.
Seedance v1.5 Pro Text-to-Video Fast
Native audio-visual joint generation model by ByteDance. Supports unified multimodal generation with precise audio-visual sync, cinematic camera control, and enhanced narrative coherence.
Seedance v1 Pro Fast Text-to-video
An efficient text-to-video model geared toward fast, cost-effective generation. Ideal for prototyping short narrative clips (2–12 s) with stylistic flexibility and prompt-faithful motion.
Seedance v1 Pro Fast Image-to-video
Seedance Pro’s image-to-video mode transforms still visuals into cinematic motion, maintaining visual consistency and expressive animation across frames.
Seedance v1 Pro t2v 1080p
A full-fidelity text-to-video model built for cinematic results. Generates multi-shot, 1080p videos with smooth motion, strong prompt adherence, and scene continuity.
Seedance v1 Pro t2v 720p
A full-fidelity text-to-video model built for cinematic results. Generates multi-shot, 1080p videos with smooth motion, strong prompt adherence, and scene continuity.
Seedance v1 Pro t2v 480p
A full-fidelity text-to-video model built for cinematic results. Generates multi-shot, 1080p videos with smooth motion, strong prompt adherence, and scene continuity.
Seedance v1 Pro i2v 720p
Seedance Pro’s image-to-video mode transforms still visuals into cinematic motion, maintaining visual consistency and expressive animation across frames.
Seedance v1 Pro i2v 480p
Seedance Pro’s image-to-video mode transforms still visuals into cinematic motion, maintaining visual consistency and expressive animation across frames.
Seedance v1 Pro i2v 1080p
Seedance Pro’s image-to-video mode transforms still visuals into cinematic motion, maintaining visual consistency and expressive animation across frames.
Food Motion
A Workflow template: one food or drink shot becomes a motion-driven product film. It reads the packaging, picks the sensory beats (pour, splash, steam, crunch), builds white-background reference sheets for identity, then renders with Seedance 2.5 — pick length (4-30s), ratio, resolution and audio. Add a model shot to get a tasting cut. Priced by duration; a failed run is not charged.
Virtual Try-On
A Workflow template: one garment or accessory shot becomes a try-on film. It reads structure and wearing logic, builds product and model reference sheets, locks the fit with a try-on still, then renders with Seedance 2.5 — 55% pure try-on, 30% lifestyle, 15% fabric detail. Bring your own model shot or let it cast one. Priced by duration; a failed run is not charged.
Trend Remix
A Workflow template: feed it one product shot and a reference video that is already working. It reads the reference for structure, pacing, camera language and edit rhythm, then rewrites the whole thing around your product — borrowing the method, never copying the frames. Renders with Seedance 2.5; pick length, ratio, resolution and audio. Priced by duration; a failed run is not charged.
TVC Maker
A Workflow template: one product shot plus a short brand brief becomes a premium commercial. It works through insight, concept, storyline, an audio-visual script and key frames, then renders with Seedance 2.5 — pick length, ratio, resolution and audio. Priced by duration; a failed run is not charged.
