63+ MODELS LIVE — TRY THE AUDIO LAB
STUDIO
Image → Videowanwan-lora-video-custom

Wan 2.2 LoRA (Custom Character)

Wan 2.2 image-to-video with your trained character/style LoRA. Pick a video-kind character from /studio/characters to keep that subject consistent across motion.

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
  • image_url
    string
    No description.
  • loras
    array
    Set automatically by the Character picker — usually you don't edit this directly.
  • num_frames
    int
    No description.
    default: 81
    range: 17 161
  • frames_per_second
    int
    No description.
    default: 16
    range: 8 24
  • resolution
    string
    No description.
    480p720p
    default: 720p
  • aspect_ratio
    string
    No description.
    auto16:99:161:1
    default: auto
  • num_inference_steps
    int
    No description.
    default: 27
    range: 8 40
  • guidance_scale
    number
    No description.
    default: 3.5
    range: 1 10
  • acceleration
    string
    No description.
    noneregular
    default: regular
You'll need
  • A text prompt
  • Source image
Try now

More from wan