Enter a prompt first.
Result data is only kept for 3 days
Guide
Guide Wan 2.6 R2V with up to five image or video references to preserve a subject, motion language or visual style. Choose Flash or Standard, then control shot structure, audio, duration and aspect ratio.
You upload 1 to 5 reference images or clips β jpg, png, webp, mp4 or mov β and the model learns the subjects, style and elements from them, then generates a new video that stays consistent with what you supplied.
5 or 10 second clips at 720p or 1080p, in a single-shot or multi-shot camera style. Enabling audio generation doubles the credit cost of the job.
By billable duration, which is the length of your input video β counted up to 5 seconds β plus the length of the output. Reference images do not add to the input duration, so image-only references are the cheaper route.
A few high-quality, on-topic references beat many loosely related ones. Show the subject clearly and from the angles you care about, and write a prompt that complements the references rather than describing something they contradict.
You can start for free. New accounts get bonus credits on signup, there is no credit card required, and the free plan has no daily generation limit. You can also claim extra credits every day by checking in. Everything runs in the browser on HeadSwap β no GPU, no install, and no API key.
Yes. Videos generated on a paid HeadSwap plan can be used commercially β ads, social media monetization, client deliverables and product marketing. You keep ownership of the output, with no watermark, no attribution requirement and no per-clip royalties.
Every finished job appears in the My Results tab beside the generator, where you can preview, download, share or delete it. The list keeps the last 3 days of generations, so download anything you want to keep before it rolls off.