Skywork Ai Skyreels V4 Reference To Video

Skywork Ai Skyreels V4 Reference To Video

Playground

SkyReels V4 Reference to Video is a fast AI reference-to-video generation model that creates high-quality videos from reference images or a reference video and a text prompt using the SkyReels V4 omni-video workflow. Ready-to-use REST inference API for character-consistent videos, product visuals, branded storytelling, social media clips, advertising creatives, concept videos, and professional reference-based video generation workflows with simple integration, no coldstarts, and affordable pricing.

Features

Skywork AI SkyReels V4 Reference-to-Video

Skywork AI SkyReels V4 Reference-to-Video generates videos from reference images, with optional reference video guidance for stronger motion and scene control. It supports standard and fast modes, multiple resolutions, optional sound effects, and prompt-driven generation for character consistency, product motion, scene transfer, and other reference-based video workflows.

Why Choose This?

• Reference-guided video generation Use up to 3 reference images to guide identity, appearance, style, or scene elements.

• Optional reference video support Add up to 1 reference video when you want stronger motion or temporal guidance.

• Two generation modes Choose std for higher-quality output or fast for quicker, lower-cost generation.

• Multiple resolutions Supports 480p, 720p, and 1080p to balance quality and budget.

• Flexible aspect ratios Choose 16:9, 9:16, or 1:1 depending on your target platform.

• Production-ready workflow Suitable for character-driven video, product clips, stylized motion design, and reference-based storytelling.

Parameters

How to Use

1. Write your prompt — describe the motion, scene, camera movement, and visual direction you want.
2. Add reference images (optional) — upload up to 3 images to guide identity, look, or scene consistency.
3. Add a reference video (optional) — upload 1 video if you want stronger motion or temporal guidance.
4. Choose aspect ratio — select 16:9, 9:16, or 1:1.
5. Set duration — choose a clip length between 3 and 15 seconds.
6. Choose resolution — use 480p, 720p, or 1080p depending on quality and cost needs.
7. Choose mode — use std for higher quality or fast for quicker generation.
8. Enable sound (optional) — turn this on if you want generated sound effects. If using fast, keep sound=false.
9. Submit — run the model and download the generated video.

Example Prompt

A cinematic fashion shot with smooth camera movement, elegant character motion, soft studio lighting, premium commercial pacing, and stable identity across the sequence.

Pricing

Pricing depends on duration, resolution, mode, and whether you use a reference video.

Without Reference Video

Standard Mode

Fast Mode

With Reference Video

Standard Mode

Fast Mode

Example Costs

Without Reference Video · Standard Mode

Without Reference Video · Fast Mode

With Reference Video · Standard Mode

With Reference Video · Fast Mode

Billing Rules

• Base multiplier starts from $0.10 per second
• Pricing scales linearly with duration
• Prices differ between std and fast
• Adding a ref_videos input increases the rate
• sound does not affect pricing directly
• fast mode currently requires sound=false

Best Use Cases

• Character consistency — Use reference images to keep the same person or style across a clip.
• Motion-guided generation — Add a reference video when movement or pacing matters.
• Product and fashion videos — Build polished, controlled motion clips from still references.
• Creative prototyping — Use fast mode for quick iteration before moving to std.
• Reference-based storytelling — Combine image identity guidance with optional motion guidance.

Pro Tips

• Use reference images when identity, styling, or appearance matters most.
• Add a reference video only when you need stronger motion or temporal guidance.
• Keep prompts focused on motion, camera behavior, and scene progression.
• Use fast mode for rough iteration, then switch to std for final-quality output.
• Keep sound=false in fast mode.
• Start with shorter durations to validate the concept before generating longer clips.

Notes

• prompt is required.
• images supports up to 3 reference images.
• ref_videos supports up to 1 reference video.
• duration supports 3–15 seconds.
• resolution defaults to 1080p.
• mode defaults to std.
• fast mode currently requires sound=false.
• Pricing depends on duration, resolution, mode, and whether a reference video is included.

Related Models

• Skywork AI SkyReels V4 Text-to-Video — Generate videos directly from text prompts.
• Skywork AI SkyReels V4 Image-to-Video — Generate videos from a first-frame image with optional middle and end frame guidance.
• Skywork AI SkyReels V3 Reference-to-Video — Earlier reference-based video workflow in the SkyReels lineup.
• Skywork AI SkyReels V3 Extend Video — Continue an existing video clip with newly generated footage.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v4/reference-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "16:9",
    "duration": 5,
    "resolution": "1080p",
    "sound": false,
    "mode": "std"
}'

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