Wan 2.1 V2V 720p

Wan 2.1 V2V 720p

Playground

Wan 2.1 V2V converts source videos into AI 720p outputs for scalable video-to-video production and unlimited video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.1 V2V 720p — wavespeed-ai/wan-2.1/v2v-720p

Wan 2.1 V2V 720p is a video-to-video model for prompt-guided transformations while preserving the original motion and timing of an input clip. Upload a source video, describe the desired changes (style, lighting, atmosphere, details), and tune strength to control how closely the output follows the original footage. It’s a solid default choice when you want higher clarity than 480p and don’t need LoRA.

Key capabilities

• Video-to-video transformation anchored to an input video (720p output)
• Preserves motion continuity and pacing from the original clip
• Prompt-guided edits for style, lighting, mood, and scene details
• Strength control to balance “keep original” vs. “transform”
• Motion behavior tuning via flow_shift

Use cases

• Restyle a video while keeping original motion (cinematic, dreamy, stylized looks)
• Improve mood/lighting (sunset grade, neon night, warm indoor) without changing timing
• Brand-safe refresh: keep composition, update colors/textures/details
• Social and marketing variations from the same base footage
• Quick iteration: change prompts and seeds to generate multiple creative takes

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)

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)

Prompting guide (V2V)

Write prompts that explicitly separate preservation from transformation:

Template: Keep the original motion and timing. Change [style/lighting/environment/details]. Keep faces stable and natural. Avoid flicker, warping, and jitter.

Example prompts

• Keep the original dance motion and camera timing. Apply a warm golden-hour cinematic color grade, soft bloom from streetlights, subtle film grain, and realistic shadows.
• Preserve motion and composition. Restyle the scene into a clean illustrated look with stable edges and no flicker.
• Keep the same choreography and timing. Add light rain, wet pavement reflections, and moody neon lighting while maintaining natural skin tones.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/v2v-720p" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "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}"