2 months free on annual · see plans
KOANimationSTUDIO
Sign up free
Image → Videowanwan-v2.7-reference-to-video

Wan 2.7 (Reference → Video)

Alibaba Wan 2.7 reference-to-video. Reference images (plus optional reference videos) and a prompt drive the scene.

Open in Video Lab Browse all models~84 cr per run
Wan guideVerified

Alibaba's open-source video model line (Wan 2.1 → 2.7). Strong prompt adherence; the open-source pedigree means heavy community use and well-documented prompting patterns.

Strengths
  • Best-in-class prompt adherence — does what you ask, not what it thinks you want.
  • Wide variant family covers most needs (T2V, I2V, reference, motion control, lipsync).
  • Wan 2.5 and 2.6 catch up to closed-source quality at lower cost.
  • Wan 2.2 Spicy variants for adult creative work.
Weaknesses
  • Older versions (2.1, 2.2) look dated next to current flagship.
  • Stylization quality lags behind Kling and Hailuo.
Best for
  • Precise prompt-driven scene construction
  • Hybrid pipelines where Wan does the heavy lifting and another model polishes
Prompting tips
  • Treat Wan like a brief — itemize what's in frame, the action, the camera.
  • Wan does NOT need flowery language; plain descriptive prose works better.
Parameters
  • reference_image_urls
    array
    Reference images for subject / scene.
  • reference_video_urls
    array
    Optional reference videos for motion.
  • duration
    int
    No description.
    default: 5
    range: 2 … 10
  • resolution
    string
    No description.
    720p1080p
    default: 1080p
You'll need
  • A text prompt
  • Reference images
  • Reference videosoptional
Try now

More from wan

Wan v2.2 5b Text To Image
wan-v2.2-5b-text-to-image
Wan v2.2 A14b Text To Image
wan-v2.2-a14b-text-to-image
Wan v2.2 A14b Text To Image Lora
wan-v2.2-a14b-text-to-image-lora
Wan v2.7 Pro Text To Image
wan-v2.7-pro-text-to-image
Wan v2.7 Text To Image
wan-v2.7-text-to-image
Wan v2.2 A14b Image To Image
wan-v2.2-a14b-image-to-image