Wan 2.1 V2V 720p LoRA Ultra Fast

Wan 2.1 V2V 720p LoRA Ultra Fast

Playground

Wan 2.1 V2V 720p LoRA Ultra-Fast converts videos to 720p with custom LoRA support and lets you generate unlimited AI videos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.1 V2V 720p LoRA Ultra Fast — wavespeed-ai/wan-2.1/v2v-720p-lora-ultra-fast

Wan 2.1 V2V 720p LoRA Ultra Fast is a speed-optimized video-to-video model that transforms an input video using a text prompt while preserving the original motion and timing. Upload a source video, describe the desired style or changes, and tune strength to balance between “keep the original” and “apply the edit.” It supports up to 3 LoRAs for consistent styling, character look, or branded aesthetics—now with faster turnaround for rapid iteration at 720p.

Key capabilities

• Ultra-fast video-to-video transformation anchored to an input video (720p 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 across clips
• Fine motion behavior tuning via flow_shift

Use cases

• Rapid 720p V2V restyling for social, ads, and creative iteration
• Apply a consistent “house style” across multiple clips using LoRAs
• Upgrade mood and color grade (cinematic, warm window light, neon, noir)
• Brand-safe refresh: keep composition and timing, update textures/colors/details
• Quick A/B testing by changing prompts, LoRAs, or seed

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 + LoRA)

A reliable structure is “preserve + edit + style”:

Template: Keep the original motion and timing. Apply [style/look] and adjust [lighting/colors/textures]. Keep faces natural and stable. Avoid flicker, warping, and jitter.

Example prompts

• Keep the original motion and composition. Apply a warm, cozy studio look with soft window light, visible dust particles, gentle film grain, and natural skin tones.
• Preserve camera motion and timing. Restyle the clip into a flat-color illustration look while keeping clean edges and stable shading.
• Keep the scene and movement. Shift the color grade to golden hour, add subtle bloom and soft shadows, maintain realism.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/v2v-720p-lora-ultra-fast" \
--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}"