Bytedance Seedance V1 Pro T2V 1080p

Bytedance Seedance V1 Pro T2V 1080p

Playground

ByteDance Seedance V1 Pro generates coherent multi-shot 1080p videos from text with smooth, stable motion and strong prompt fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Seedance v1 Pro T2V 1080p — bytedance/seedance-v1-pro-t2v-1080p

Seedance v1 Pro T2V 1080p generates high-quality 1080p videos directly from a text prompt, optimized for smooth camera movement and natural motion. Describe the subject, action, scene, lighting, and camera intent, and the model produces a coherent clip suitable for premium story beats, marketing creatives, and cinematic concept previews. Enable camera_fixed when you want motion within the scene while keeping the framing steady.

Key capabilities

• Text-to-video generation in 1080p with strong visual fidelity
• Smooth camera movement and natural motion from well-specified prompts
• Supports common aspect ratios (e.g., 16:9) for standard layouts
• Optional camera_fixed mode for stable framing
• Seed control for reproducible iterations

Use cases

• Cinematic establishing shots and hero moments in 1080p
• Marketing creatives and social ads that need sharper detail
• High-quality pre-visualization for short scenes and trailers
• Generating multiple “takes” by changing seed for creative exploration
• Clean, high-resolution drafts before post-production

Pricing

Parameters

• prompt (required): Describe what happens in the video (subject, action, scene, mood)
• aspect_ratio: Output aspect ratio (e.g., 16:9, 9:16, 1:1)
• duration: Video length in seconds
• camera_fixed: Whether to fix the camera position
• seed: Random seed (-1 for random; fixed value for reproducible results)

Prompting guide (T2V)

Write prompts like a director’s brief:

• Subject: who/what is on screen
• Action: what changes over time (walking, turning, fluttering, reacting)
• Scene: where it happens + time of day
• Lighting: sunrise, neon, soft volumetrics, etc.
• Camera: dolly, orbit, pan, push-in (omit if camera_fixed is on)

Example prompts

• A beautiful lakeside scene at golden hour, gentle wind rippling the water, trees swaying softly, cinematic lighting, camera slow dolly-in, natural motion, smooth stabilization, 1080p.
• A city street at night with neon reflections on wet pavement, light rain drifting, pedestrians passing by, camera slow orbit around the main subject, cinematic mood.
• A cozy interior with warm lamp light, floating dust motes, a person slowly turns and smiles, shallow depth of field, subtle handheld feel.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-pro-t2v-1080p" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "16:9",
    "duration": 5,
    "camera_fixed": false,
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"