Wan 2.1 V2V 480p LoRA

Wan 2.1 V2V 480p LoRA

Playground

WAN 2.1 V2V 480p LoRA generates unlimited 480p video-to-video edits with custom LoRA support for tailored styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.1 V2V 480p LoRA — wavespeed-ai/wan-2.1/v2v-480p-lora

Wan 2.1 V2V 480p LoRA is a video-to-video model designed for prompt-guided edits while preserving the original motion and timing of an input video. Upload a source video, describe what should change, and tune the edit strength to control how closely the output follows the original footage. It supports up to 3 LoRAs to enforce a consistent style, character look, or branded aesthetic across the transformed clip.

Key capabilities

• Video-to-video transformation anchored to an input video (480p output)
• Prompt-guided edits while keeping motion continuity and pacing
• Strength control to balance preservation vs. transformation
• LoRA support (up to 3) for stable style/identity steering
• Fine control over motion behavior via flow_shift

Use cases

• Restyle a video while preserving the original motion (cinematic, anime, illustration looks)
• Apply a “house style” consistently across multiple clips using LoRAs
• Enhance mood and lighting (golden hour, noir, neon) without re-animating motion
• Brand-safe content refresh: keep composition, change textures/colors/details
• Creative remixing for social clips and rapid iteration

Pricing

Inputs

• video (required): source video to transform
• prompt (required): what to change and how the result should look
• negative_prompt (optional): what to avoid (artifacts, jitter, unwanted elements)
• loras (optional): up to 3 LoRA items for style/identity steering

Parameters

• num_inference_steps: sampling steps
• duration: output duration (seconds)
• strength: how strongly to transform the input video (lower = preserve more; higher = change more)
• guidance_scale: prompt adherence strength
• flow_shift: motion/flow behavior tuning
• seed: random seed (-1 for random; fixed for reproducible results)

LoRA (up to 3 items):

• loras: list of LoRA entries (max 3)

  • path: owner/model-name or a direct .safetensors URL
  • scale: LoRA strength

Prompting guide (V2V)

To get stable edits, write prompts that separate “preserve” from “change”:

Template: Keep the same camera motion and timing from the input video. Change [style/lighting/wardrobe/environment]. Keep faces natural and consistent. Avoid flicker and warping.

Example prompts

• Keep the original motion and composition. Make the video candid and cinematic with warm sunlight, natural skin texture, gentle film grain, and soft depth of field.
• Preserve timing and camera movement. Restyle the scene into a clean anime look with crisp edges and consistent shading, no flicker.
• Keep the same scene and people. Change the color grade to sunset golden hour, add subtle lens flare, maintain realistic shadows.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/v2v-480p-lora" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "loras": [
        {
            "path": "motimalu/wan-flat-color-v2",
            "scale": 1
        }
    ],
    "num_inference_steps": 30,
    "duration": 5,
    "strength": 0.9,
    "guidance_scale": 5,
    "flow_shift": 3,
    "seed": -1
}'

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