Seedance 2.0
Integrate the Seedance 2.0 text-to-video model to render hyper-realistic action scenes using our developer-friendly AI API.
Seedance 2.0 (Build 260128)
Call the Dreamina Seedance 2.0 API on GPTProto — ByteDance's text-to-video model with native synchronized audio, 4–15 second clips, from $0.2957/run. One balance, one OpenAI-style key, 200+ models on the same account.
API Usage Examples
curl --request POST "https://gptproto.com/api/v3/doubao/dreamina-seedance-2-0-260128/text-to-video" \
--header "Authorization: Bearer $GPTPROTO_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"prompt": "A tiny origami fox sailing a teacup across a moonlit puddle",
"aspect_ratio": "16:9",
"duration": 5,
"resolution": "720p",
"generate_audio": true,
"camera_fixed": false,
"seed": -1
}'Seedance 2.0 (Build 260128) pricing
Start from the cost of a single sample and pick a testing budget.
Related Models
All Models
| Model | Resolution | Input → Output | ||
|---|---|---|---|---|
| — | $0.07 per second | 480p · 720p · 1080p · 4k | Input: TextInput: ImageInput: VideoInput: Audio Output: Video |
| $0.09 per time | more | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | ||
| — | $0.11 per second | 480p · 720p | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | |
| $0.34 per second | 4k | Input: TextInput: Image Output: Video | ||
| — | $0.02 per second | 480p · 720p | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | |
| $0.34 per second | 4k | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | ||
| — | $0.04 per second | 480p · 720p | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | |
| $0.02 per second | 720p · 1080p · more | Input: ImageInput: VideoInput: Audio Output: Video | ||
| — | $0.07 per second | 480p · 720p · 1080p · 4k | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | |
| — | $0.04 per second | 480p · 720p | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | |
| $0.09 per second | — | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | ||
| $0.03 per second | 540p · 720p · 1080p | Input: TextInput: Image Output: Video | ||
| $0.04 per second | 540p · 720p · 1080p | Input: TextInput: Image Output: Video | ||
| $0.09 per second | 720p · 1080p · 2k | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | ||
| $0.01 per second | 480p · 720p · 1080p | Input: TextInput: Image Output: Video | ||
| — | $0.05 per time | — | Input: Video Output: Video | |
| — | $1.20 per time | — | Input: TextInput: ImageInput: Video Output: Video | |
| — | $3.20 per time | — | Input: TextInput: ImageInput: Video Output: Video | |
| $0.03 per second | 1080p · more | Input: Image Output: Video | ||
| $0.44 per time | — | Input: TextInput: Image Output: Video | ||
| $0.04 per second | — | Input: TextInput: Image Output: Video | ||
| $0.09 per time | 1K · more | Input: TextInput: Image Output: Video | ||
| — | $0.50 per time | — | Input: TextInput: ImageInput: VideoInput: Audio Output: Video | |
| — | $0.30 per second | 720p · 1080p | Input: TextInput: Image Output: Video | |
| — | $0.10 per second | 720p | Input: TextInput: Image Output: Video | |
| $0.28 per time | — | Input: Image Output: Video | ||
| $0.09 per time | — | Input: Image Output: Video | ||
| $0.39 per time | — | Input: Image Output: Video |
Examples
What is Dreamina Seedance 2.0?
Dreamina Seedance 2.0 is ByteDance's second-generation text-to-video model, built by its Seed research team. The same Seedance 2.0 engine powers ByteDance's consumer apps — CapCut and Dreamina (formerly Jimeng AI) — and is exposed for developers through API resellers like GPTProto. On this page the model runs in text-to-video mode: you send a prompt, it returns a finished clip with audio generated in the same pass.
What separates Seedance 2.0 from the 1.x line is one-pass audio-visual generation. Dialogue, sound effects, ambient noise, and music are produced together with the picture in a single generation — no separate audio step, no stitching. The model keeps a character's identity, features, and style consistent across shots, which is the part most short-form pipelines actually struggle with.
On GPTProto you reach dreamina-seedance-2-0-260128 with one model string and your existing balance, so you can route between Dreamina Seedance 2.0, Doubao Seedance 2.0, Sora 2, and Veo 3 without separate accounts or regional sign-up gates.
Specifications
| Field | Value |
|---|---|
| Provider | ByteDance (Seed team); BytePlus / Volcano Engine stack |
| Web model id | dreamina-seedance-2-0-260128 |
| Input modes | Text-to-video, image-to-video, reference-to-video |
| Inputs accepted | Text, image, video, audio (mode-dependent) |
| Output | Video with native synchronized audio (single pass) |
| Duration | 4–15 s |
| Resolution | 480p / 720p / 1080p |
| Aspect ratio | See ratio table on page (16:9 default) |
| Audio | generate_audio toggle |
| Provenance | C2PA metadata + invisible watermark, enforced via API same as the apps |
Three ways to drive it: text, image & reference
Dreamina Seedance 2.0 exposes three generation endpoints under the same model id. Each takes the same core controls — aspect_ratio, duration, resolution, generate_audio, camera_fixed, seed — and differs only in what you feed it.
Text-to-video — prompt in, clip out. Endpoint: POST /api/v3/doubao/dreamina-seedance-2-0-260128/text-to-video
Image-to-video — animate a still; optionally pin a last_image to control the end frame. Endpoint: POST /api/v3/doubao/dreamina-seedance-2-0-260128/image-to-video
Reference-to-video — pass arrays of images, videos, and audios as references for character and style continuity. Endpoint: POST /api/v3/doubao/dreamina-seedance-2-0-260128/reference-to-video
All three use the same bearer auth and the same submit-and-poll flow shown below — only the input fields change.
Dreamina Seedance 2.0 vs Sora 2, Veo 3 & Doubao Seedance 2.0
All four run on GPTProto under one balance, so the real question is which to route each job to. Prices below are on-site, per run.
| Dreamina Seedance 2.0 | Doubao Seedance 2.0 | Sora 2 | Veo 3 | |
|---|---|---|---|---|
| Maker | ByteDance | ByteDance | OpenAI | Google DeepMind |
| Same core engine? | — | Yes (Doubao route) | No | No |
| Native audio | Yes, single pass | Yes | Yes | Yes |
| Input modes | text / image / reference | text / image / reference | text / image | text / image / reference |
| Max duration | 15 s | 15 s | 12 s | 8 s |
| GPTProto price/run | from $0.2957 | $0.2957 | $0.40 | $0.48 |
| Reach for it when | lowest per-run cost; 3 input modes | same engine, Doubao defaults | OpenAI-native generation | 4K + cinematic control |
Honest read: Dreamina Seedance 2.0 and Doubao Seedance 2.0 are the same ByteDance generation via two brand routes — identical $0.2957/run, differing in platform defaults, not output ceiling. Across these four, Seedance is the lowest per-run option and the only one here with three distinct input modes (text, image, multimodal reference). Veo 3 ($0.48/run) is the pick when you need 4K and tight cinematic control; Sora 2 ($0.40/run) for OpenAI-native generation. A common pattern is drafting on Seedance, then re-rendering the chosen take on a pricier model.
For half-cost drafts, dreamina-seedance-2-0-fast-260128 runs $0.2365/run.
Switching from CapCut / Dreamina to the API
If you've been generating inside CapCut or the Dreamina app, the API drops the per-app sign-up and regional rollout limits without a new SDK to learn. Point your client at https://gptproto.com/api/v3, send your key as a bearer token, and POST to the dreamina-seedance-2-0-260128 task endpoint. One balance then covers every other model, so you can A/B Seedance against Sora 2 or Veo 3 in the same job runner.
Prompt Recipes
Seedance 2.0 responds to explicit, ordered direction: style, then subject, then camera, then lighting, then motion.
- Product hero (locked camera):
cinematic; matte-black wireless earbuds on wet slate, water droplets; locked-off static shot; soft studio key light from left; slow condensation forming— setcamera_fixed: true. - Character short (push-in):
anime style; a courier cycling through a rainy neon alley at night; slow push in; reflections on the road; ambient rain and distant traffic— keepgenerate_audio: truefor the ambient bed. - Reference-driven continuity: Pass two character stills in
images[]and promptsame character, new shot: walking through a morning market, handheld follow— the reference mode holds identity across the cut better than a fresh text prompt.
State camera moves literally ("slow push in", "tracking shot", "locked off") and name the lighting directly. Vague prompts drift; specific ones hold.
What to expect: speed, audio & aspect ratios
Generation time. Because clips render asynchronously, plan for a wait, not an instant response. Standard shorts return quickest; long 15-second clips with multiple references take the longest — size your polling interval and any progress UI accordingly.
Audio. With generate_audio: true the model writes dialogue, effects, ambient sound, and music to match the picture in the same pass. Set it false for a silent clip when you'll mix your own track — common for music videos or branded content with a fixed audio bed.
Aspect ratio. Pick the target ratio at submit time rather than cropping afterward; the model frames the action for the canvas it's given. 16:9 is the default; the full ratio list is in the on-page table.
Dreamina-Seedance-2.0 Frequently Asked Questions
Common questions about using the Dreamina-Seedance-2.0 video model on GPTProto.
What is Dreamina Seedance 2.0?
ByteDance's second-generation video model, generating 4–15 s clips with synchronized native audio in one pass. It powers CapCut and Dreamina (formerly Jimeng AI) and is callable here as dreamina-seedance-2-0-260128.
How much does the Dreamina Seedance 2.0 API cost?
From $0.2957/run, billed per run on resolution × duration. At 480p that's about $0.077 per extra second — a 480p · 5 s clip is $0.3867; a 720p · 5 s clip about $0.8316.
Does it support image-to-video and reference-to-video?
Yes — three endpoints under one model id: text-to-video, image-to-video (with optional last_image), and reference-to-video (arrays of image/video/audio references). Image-to-video has its own subpage.
How do I use Seedance 2.0 from Dreamina in my own code?
POST to the task endpoint with your bearer key, then poll …/predictions/{id}/result — no CapCut/Dreamina app account or regional rollout needed.
Dreamina Seedance 2.0 vs Doubao Seedance 2.0?
Same ByteDance engine via two brand routes; both $0.2957/run on GPTProto, differing in platform defaults rather than output ceiling.
Dreamina Seedance 2.0 vs Sora 2 vs Veo 3 — which is cheaper?
On GPTProto, Seedance is the lowest per run (from $0.2957) versus Sora 2 ($0.40) and Veo 3 ($0.48). Veo 3 adds 4K; pick by need, not just price.
Why do some of my generations get blocked?
The usual trigger is the real-face restriction or unauthorized IP — deliberate safety guards, enforced on the API as in the apps. Work from generated or licensed source material. We don't publish techniques for defeating these systems.
Can I turn the audio off?
Yes — set generate_audio: false.
Is there a cheaper option for drafts?
Yes — dreamina-seedance-2-0-fast-260128 at $0.2365/run.
Is Dreamina-Seedance-2.0 better for realistic or stylized content?
Dreamina-Seedance-2.0 excels at both, but its realistic rendering of light and texture makes it a favorite for photorealistic cinematic projects.
Further Reading
Guides, comparisons, and updates related to this model.
All Articles
seedance 2.0: Pro AI Video Realities
ByteDance's seedance 2.0 delivers unmatched AI video realism, but demands heavy prompt control and high costs. Learn how to master it for your projects.
Seedance 2.0 Guide: Transform Your Video Content with Advanced Multimodal AI Controls
Discover how Seedance 2.0 is revolutionizing the world of AI video. This comprehensive guide covers multimodal inputs, motion replication, and cinematic rendering techniques to help you create professional, high-quality video content using the latest generative tools and GPTProto efficiency.
Seedance 2.0: The Cinematic AI Revolution
ByteDance's Seedance 2.0 is a massive leap forward for AI video generation, offering professional cinematography, emotive combat sequences, and the potential for digital immortality. Discover how this tool is transforming content creation and the future of human-AI collaboration.
Seedance 2.0 vs Disney: What the Copyright Dispute Means
ByteDance's Seedance 2.0 went viral fast — and landed in legal trouble even faster. Here's what the Disney dispute is about, what makes this AI video model stand out, and how developers can access the Seedance 2.0 API today.