WAN 2.7 Image-to-Video logo

WAN 2.7 Image-to-Video

Alibaba DashScope WAN 2.7 animates a single image or short first clip into cinematic motion. It supports bookend frames, audio-driven lip sync, color-consistent sequential shots, and continuation workflows.

Alibaba DashScope Video Context N/A
Get API Key
Deposit $5 to get started Unlock API access and start running inference right away. See how many million tokens $5 gets you

api_example.sh

# ─────────────────────────────────────────
# Case 1: JSON body β€” text / image URL / audio URL (or all together)
# Remove "image" and/or "audio" keys if not needed
# When "image" present β†’ aspect_ratio ignored
# When "audio" present β†’ duration ignored
# ─────────────────────────────────────────
curl -X POST "https://platform.qubrid.com/v1/videos/generations" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-i2v",
    "prompt": "A butterfly flying through a flower garden",
    "duration": 5,
    "resolution": "1080P",
    "fps": 24,
    "aspect_ratio": "16:9",
    "image": "https://example.com/input-image.jpg",
    "audio": "https://example.com/audio.mp3",
    "draft": false,
    "save_audio": true,
    "prompt_upsampling": true
  }'

# ─────────────────────────────────────────
# Case 2: File upload β€” image_file + audio_file (multipart)
# Remove either -F line if only one file is needed
# ─────────────────────────────────────────
curl -X POST "https://platform.qubrid.com/v1/videos/generations" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -F "model=wan2.7-i2v" \
  -F "prompt=A butterfly flying through a flower garden" \
  -F "duration=5" \
  -F "resolution=1080P" \
  -F "fps=24" \
  -F "draft=false" \
  -F "save_audio=true" \
  -F "prompt_upsampling=true" \
  -F "image_file=@/path/to/your/image.jpg" \
  -F "audio_file=@/path/to/your/audio.mp3"

# ─────────────────────────────────────────
# Tip: pass image/audio as URL via form fields (no file upload needed)
# ─────────────────────────────────────────
curl -X POST "https://platform.qubrid.com/v1/videos/generations" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -F "model=wan2.7-i2v" \
  -F "prompt=A butterfly flying through a flower garden" \
  -F "image=https://example.com/input-image.jpg" \
  -F "audio=https://example.com/audio.mp3" \
  -F "resolution=1080P" \
  -F "fps=24" \
  -F "draft=false" \
  -F "save_audio=true" \
  -F "prompt_upsampling=true"

Pricing

Pay-per-use, no commitments

Per Second (720P, Draft Off) $0.014/Second
Per Second (720P, Draft On) $0.014/Second
Per Second (1080P, Draft Off) $0.028/Second
Per Second (1080P, Draft On) $0.028/Second

Technical Specifications

Model Architecture & Performance

Architecture Proprietary multimodal video diffusion architecture
Precision Mixed precision with proprietary optimizations
License Proprietary
Release Date 2026
Developers Alibaba Cloud

API Reference

Complete parameter documentation

Parameter Type Default Description
duration select 5 Output length in seconds. Only 5 or 10 are valid (per API validation).
resolution select 1080P Output resolution. 720P approx $0.014/s, 1080P approx $0.028/s.
prompt_extend boolean true Enable LLM prompt rewriting for better motion and adherence (default on).
watermark boolean false Add an AI Generated watermark to the output video.
seed number 0 Optional reproducibility seed (0-2147483647). Leave at 0 to omit and use random.
negative_prompt string What to avoid in the output. Up to 500 characters.
last_frame string HTTPS URL of the target last frame. Use together with the first-frame image for bookend generation.
first_clip string Set in the playground section First frame or video clip (required). HTTPS URL for continuation; do not use with a first-frame image.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
Handles image-only, bookend, and continuation workflows
Audio conditioning for lip-sync animation
Prompt Extend improves adherence to complex directions
High-quality 1080P output with option for cheaper 720P previews
Either image (or upload) or first_clip must be provided, not both
Duration must be exactly 5 or 10 seconds
Single-clip generation (no multi-scene stitching)

Use cases

Recommended applications for this model

Bring a hero keyframe to life for campaign teasers in seconds
Create lip-synced character clips using reference audio
Storyboard transitions with first and last frame supervision
Extend an existing clip seamlessly by providing a first_clip
Experiment with zero-prompt motion where the model infers movement

Build with WAN 2.7 Image-to-Video faster

Get deployment recipes, benchmark alerts, and GPU pricing updates for WAN 2.7 Image-to-Video (Wan 2.7 I2v) and other video models straight from the Qubrid team.

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid helped us turn a collection of AI scripts into structured production workflows. We now have better reliability, visibility, and control over every run."

AI Infrastructure Team

Automation & Orchestration