image-to-video
WAN 2.1 Image-to-Video (i2v) 720P Ultra-Fast converts images into 720P videos with ultra-fast inference and supports unlimited AI video generation for high-throughput workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
Ihre Anfrage kostet $0.225 pro Durchlauf.
Für $10 können Sie dieses Modell ungefähr 44 Mal ausführen.
Noch etwas::
BeispieleAlle anzeigen
README
Wan 2.1 I2V 720p Ultra Fast — wavespeed-ai/wan-2.1/i2v-720p-ultra-fast
Wan 2.1 I2V 720p Ultra Fast is a fast image-to-video model that animates a single reference image into a short clip guided by your prompt. It’s optimized for quick turnaround at 720p while keeping the input image as the visual anchor—ideal for rapid storyboarding, motion exploration, and production-friendly iteration.
Key capabilities
- Image-to-video (I2V) generation at 720p
- Strong image anchoring for subject consistency
- Prompt-driven motion and camera direction (follow, dolly, orbit, pan/tilt)
- Tunable motion behavior with guidance and flow controls
- Great for quick drafts, fast iterations, and high-throughput generation
Use cases
- Turn key art into short motion clips for ads, social posts, and previews
- Animate characters and products while keeping the original look
- Test different camera moves (push-in, rise, follow, orbit) from the same image
- Generate multiple motion variants quickly for editing and selection
- Previsualization for longer or higher-cost renders
Pricing
| Resolution | Duration | Price per run | Effective price per second |
|---|---|---|---|
| 720p | 5s | $0.225 | $0.045/s |
| 720p | 10s | $0.338 | $0.034/s |
Inputs
- image (required): reference image that anchors subject and composition
- prompt (required): describe action + camera + environment motion
- negative_prompt (optional): suppress artifacts like blur, jitter, distortions
Parameters
- size: output resolution preset (e.g., 1280×720)
- duration: video length (commonly 5s or 10s)
- num_inference_steps: more steps can improve detail and motion stability
- guidance_scale: prompt adherence strength (higher = follows prompt more)
- flow_shift: motion behavior tuning (useful for more/less dynamic motion)
- seed: set for reproducible results (-1 for random)
Prompting guide (I2V)
Write prompts like a shot list:
- Subject + action: what the subject does over time
- Camera movement: “camera rises”, “follows behind”, “slow dolly-in”, “orbit”
- Motion constraints: “smooth motion”, “stable framing”, “no jitter”
- Environment: weather, particles, crowd, lighting shifts for realism
Example prompt
LEGO minifigure snowboarding on a mountain ridge, carving smooth S-turns while staying sideways on the board. The camera starts low in front, then rises and follows as the rider moves left and right across the slope. Snow sprays from the board, wind-blown powder in the air, dynamic action, smooth motion, stable framing, cinematic winter lighting.