txtovid's reference images to video generator solves the hardest problem in AI video: keeping the same face, character, product or art style consistent across an entire clip. Instead of one starting frame, you feed HappyHorse 1.1 up to 9 reference images — different angles, poses or lighting of the same subject — and a free-form prompt of up to 2,500 characters describing the scene you want.
The model extracts the identity from your reference images and re-stages it in a completely new setting: your mascot walking through Tokyo at night, your product on a beach at golden hour, your comic character in a car chase. Unlike image-to-video, the references don't constrain the composition — they constrain who or what appears, while your prompt directs everything else including aspect ratio (16:9, 9:16 or 1:1).
For best results upload sharp images with a resolution of 720p or higher, a shorter side above 400 pixels, and aspect ratios close to your target video ratio. Pricing is transparent: $0.14/second at 720P or $0.18/second at 1080P (HappyHorse 1.1 list price) plus a flat $0.05/second platform fee — always shown before you generate. Public sharing saves 10%, and your first 3-second reference-to-video clip is free.
Every public video on txtovid ships with its full prompt, so you can study how creators combine reference images with scene prompts — then remix the technique with your own characters.
Every great AI video starts with a great prompt. Steal these to get going — then make them your own.
3–9 references from different angles and poses give the model a full picture of your subject — one image works, more is better.
All images should show the same subject in similar quality. Mixing different people or products confuses identity extraction.
References with an aspect ratio close to your video format (e.g. portrait refs for 9:16) frame the subject best.
720p+ resolution, good lighting and a clear subject matter more than artistic filters.
You have 2,500 characters — describe setting, action, camera and lighting in detail. The references handle the who, you write the what.
Phrases like “the character from the references” or “the product shown in the images” anchor the subject in your scene.
Reference-to-video shines with a single consistent hero. For multi-character scenes, generate separately and edit together.
Keep the same references and vary only the prompt — perfect for building a series with a consistent character.
Free 3-second test video. Then pay per second from $5 top-ups — or save 5–7% with a plan and download without watermark.
Describe it. Generate it. Share it. No credit card required for your free test video.
Get started freeYour References => Video
Upload up to 9 reference images of your character, product or style and let HappyHorse 1.1 or Wan 2.7 keep them consistent in a brand-new AI video. Your first 3-second video is free.
