image-to-video
Seedance 1.5 Pro Fast Image-to-Video transforms a single image (plus optional text prompt) into cinematic, live-action-leaning clips while preserving subject identity, composition, and first-frame fidelity. It supports 4–12s duration control, adaptive aspect ratios that follow the input image, expressive yet stable motion, and seed-based reproducibility—ideal for ad creatives and short-drama beats anchored by a strong visual. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.
Idle
Your request will cost $0.2 per run.
For $10 you can run this model approximately 50 times.
One more thing::
ExamplesView all
README
ByteDance Seedance V1.5 Pro Fast — Image-to-Video
Seedance V1.5 Pro Fast (Image-to-Video) generates short, cinematic clips from a text prompt + a first-frame image. It’s built for rapid iteration while keeping strong subject consistency, coherent motion, and a polished, live-action–leaning look.
Use it to animate a keyframe: keep the composition and identity from the input image, then direct motion, camera behavior, and style with your prompt.
Key capabilities
-
Image-anchored animation Animates from a single reference image while preserving subject, lighting, and composition.
-
Prompt-guided motion + camera Responds well to shot-style prompts describing what moves and how the camera behaves (dolly-in, orbit, locked-off, handheld feel).
-
Short-form duration control Designed for concise, shot-based clips with controllable duration.
-
Framing control via aspect ratio Supports common aspect ratios for vertical, square, and widescreen delivery.
-
Optional audio generation Toggle generate_audio on/off depending on whether you want sound included.
-
Seeded iteration Fix seed to compare prompt tweaks fairly and reduce randomness between runs.
Parameters
| Parameter | Description |
|---|---|
| prompt* | Text direction for the shot (subject + motion + camera + look). |
| image* | First-frame reference image that anchors composition and identity. |
| last_image | Optional ending frame to steer the final composition (if supported by the endpoint). |
| aspect_ratio | Output framing (e.g., 21:9, 16:9, 4:3, 1:1, 3:4, 9:16). |
| duration | Output duration in seconds (available values depend on the endpoint UI/validator). |
| resolution | Output resolution: 720p or 1080p. |
| generate_audio | Whether to generate audio (true/false). |
| camera_fixed | Whether to lock camera position (true/false). |
| seed | Random seed (-1 for random; fixed integer for reproducible results). |
How to use
-
Upload the image you want to animate (clean subject, strong composition works best).
-
Write a prompt as a single shot direction: what moves, how it moves, and the vibe.
-
(Optional) Add a last_image if you need a specific ending pose/framing.
-
Choose aspect_ratio to match your target platform (9:16 for shorts, 16:9 for YouTube).
-
Set duration (start short for iteration, then increase once the motion looks right).
-
Pick resolution (720p for drafts, 1080p for finals).
-
Toggle generate_audio:
- true for audio-included clips
- false for silent clips (cheaper)
-
Use camera_fixed for tripod-like stability, or keep it off if you describe camera motion.
-
Set a seed to iterate reliably, or keep -1 for new variations each run.
Prompt tips
A reliable structure:
- Subject & setting — who/what, where, time/lighting
- Motion — clear verbs + intensity (slowly, subtly, rapidly)
- Camera — locked-off / slow dolly-in / orbit / handheld
- Look — cinematic, soft rim light, 35mm film grain, etc.
Example:
Futuristic orbital living room interior. Soft sunlight, vast luminous planet outside the panoramic window. Slow dolly-in, subtle floating dust, gentle parallax, cinematic color grade, calm mood.
Practical tips:
- Prefer one shot per prompt. For multiple beats, list them in order as short sentences.
- If you want a locked shot, say “locked-off / tripod” and set camera_fixed = true.
- Keep prompts positive and specific; avoid long “don’t” lists.
Pricing
Effective rates
| Resolution | Generate audio | Price per 5 seconds | Price per second |
|---|---|---|---|
| 720p | true | $0.20 | $0.04 |
| 720p | false | $0.10 | $0.02 |
| 1080p | true | $0.30 | $0.06 |
| 1080p | false | $0.15 | $0.03 |
Example costs
| Duration | Resolution | Generate audio | Cost per run |
|---|---|---|---|
| 5s | 720p | true | $0.20 |
| 5s | 720p | false | $0.10 |
| 10s | 720p | true | $0.40 |
| 10s | 1080p | true | $0.60 |
| 12s | 1080p | false | $0.36 |
Notes
- If motion looks jittery, simplify action/camera instructions first, then add complexity gradually.
- Set aspect_ratio early so you don’t optimize a shot that later needs reframing.
- Keep seed fixed while refining prompts to make results comparable.
Related Models
- Seedance V1.5 Pro (Image-to-Video) — Higher-fidelity image-to-video when you want maximum detail and polish.
- Seedance V1.5 Pro Fast (Text-to-Video) — Fast text-only video generation for rapid concept exploration.
- Seedance V1.5 Pro (Text-to-Video) — Full-quality text-to-video for more refined outputs.
- ByteDance Video Upscaler — Upscale generated clips when you like the motion but need higher clarity.