Reference to Video AI

Your subject, your way. One reference works, several work better — MaxH3's reference to video generator locks the face and form across every frame you generate.

20
Reference to Video AI
Model
References*
0/15
Prompt*
0 / 7000
Aspect Ratio
Video Length
4s
Outputs
Resolution
Public Visibility
When enabled, your generated content may appear in the public gallery.
Copy Protection
Prevent others from downloading or copying your generated content.

Please enter a prompt.

Bring In What the Reference Never Had

The reference fixes what must not change — this bottle, its shape, its glass, its light. Everything else is yours to ask for: a model who was never in the frame, a room that did not exist, five scenes that cut together. Name who walks in and what they do, and the product stays the same product from the opening push-in to the last shot.

References

A perfume bottle on a glossy black surface in amber light and golden smoke

Prompt

A Luxury perfume bottle on glossy black surface, warm amber lighting, golden smoke, dark elegant background, soft reflections, cinematic close-up, slow push-in, photorealistic 4K. Confident woman in a burnt-orange satin dress, long dark hair, luxurious dark interior with golden lights, subtle smoke, cinematic medium shot, photorealistic 4K. Close-up of the same woman spraying perfume on her neck. Visible fragrance mist, warm golden light, natural hair movement, shallow depth of field, cinematic beauty ad. Same woman walking confidently toward camera in the luxury interior. Smooth tracking shot, reflective floor, warm golden lighting, subtle smoke, elegant cinematic look. Same perfume bottle centered on glossy black surface with amber crystals and golden smoke. Dramatic spotlight, dark luxury background, slow push-in, photorealistic 4K. Consistency: Keep the same woman, face, hair, skin tone, outfit, and perfume bottle across all scenes. Warm amber lighting, realistic skin and movement. No extra people, distorted hands, duplicate objects, text, or logos. Style: Luxury fragrance commercial, cinematic, photorealistic, 4K.

Output video

The same bottle through a five-scene fragrance ad — the product push-in, a woman in a burnt-orange dress, the spray on her neck, a walk to camera, and back to the bottle

Combine Several Images Into One Video with MaxH3's Reference to Video AI

Hand it a face, a location and an outfit — the reference to video generator merges all three into one continuous clip. Not a slideshow, not three clips cut together: one take, with your subject, your setting and your wardrobe already in it. What happens, and in what order, comes from your prompt. MiniMax H3 reads up to nine reference images, plus reference clips and audio.

References

A studio portrait of a woman with long brown hair, used as the face reference
A modern garden with a reflecting pool, lavender beds and a low glass house, used as the location reference
A flat-lay of cream pleated trousers, a black sleeveless top, a tan crossbody bag, sunglasses and gold hoops, used as the wardrobe reference

Prompt

Close up shot of woman with sunglasses on top of her head, gold hood earrings, is walking in the garden, she is lost and asks where everyone is and what's going on.

Output video

The woman from the portrait, in the flat-lay outfit, walking through the garden from the location reference and speaking to camera

The Same Character, Shot After Shot

A clip that holds together on its own is table stakes. The harder job is take two: a different street, a different time of day, a different line — and the same person walks into frame. Keep the reference set and run it again, and the shots cut together instead of looking like three castings. That is how a series of clips becomes one ad, one episode, one campaign.

References

A model in a dusty-rose suit walking through a white studio, used as the talent reference
A lip-oil bottle in a magenta splash, used as the product reference

Prompt

Ultra-realistic 8K luxury beauty commercial in vertical 9:16, shot on an ARRI Alexa 65 with Cooke S4/i prime lenses, cinematic HDR, premium editorial color grading in warm rose and blush tones, shallow depth of field, realistic optics, natural skin texture, luxury cosmetic campaign quality, smooth gimbal movement, photorealistic physics, no CGI look, no cartoon appearance. Use the exact same female model throughout every shot: an exceptionally beautiful, elegant Caucasian woman, approximately 175 cm tall, slender runway proportions, fair neutral skin with subtle natural freckles, luminous dewy complexion, expressive green-hazel eyes, thick defined brows, long natural lashes, soft naturally pink glossy lips, light brown hair styled in a sleek high ponytail, minimal luxury makeup with champagne highlighter and satin finish, wearing a tailored dusty-rose oversized blazer with matching wide-leg trousers, cropped bandeau top, nude pointed heels, confident editorial expressions. Use the exact same product throughout every shot: luxury transparent glass bottle labeled "MOIST HEIST LIP OIL", metallic silver cylindrical cap, vibrant glossy magenta lip oil inside, perfectly centered logo, premium reflections, identical proportions in every scene. 00:00–00:01 — Fade in from pure black. 00:01–00:02 — Hero product reveal. The lip oil bottle floats in mid-air while an explosive crown splash of glossy magenta liquid erupts around it. Crystal-clear droplets suspend naturally in slow motion with realistic refraction, sparkling highlights, and premium product lighting. Slow cinematic push-in. 00:02–00:03 — The model confidently walks toward the camera through a minimalist white luxury studio with elegant pink architectural panels. Smooth backward gimbal tracking, natural fabric movement, confident eye contact, polished editorial fashion campaign feel. 00:03–00:04 — Medium close-up. The model extends the MOIST HEIST LIP OIL directly toward the lens. Perform a smooth rack focus from her face to the bottle so the product becomes perfectly sharp while her face remains softly blurred behind it. 00:04–00:05 — Clean overhead shot. Elegant hands slowly unscrew the metallic cap. The applicator lifts smoothly from the bottle, creating luxurious glossy lip oil strings with realistic viscosity and fluid dynamics before separating naturally. 00:05–00:06 — Extreme beauty close-up. The plush doe-foot applicator gently glides across the lower lip, depositing a rich glossy magenta lip oil. Hyper-realistic pores, peach fuzz, soft beauty lighting, cinematic macro focus. 00:06–00:07 — Ultra-macro lip shot. Capture every natural lip line while the formula melts smoothly into the lips, creating an intense glass-like shine with bright specular reflections and a hydrated luxury finish. 00:07–00:08 — Fantasy product shot. The bottle floats inside swirling viscous magenta liquid while elegant glossy waves wrap around the glass. Suspended droplets sparkle like gemstones. Slow 180-degree cinematic orbit. 00:08–00:09 — Continue the hero shot. The bottle rotates gracefully as larger floating droplets orbit around it. Tiny beads of moisture shimmer on the metallic cap while the logo remains perfectly readable. Rich reflections, luxury cosmetic advertising quality. 00:09–00:10 — Extreme macro beauty finale. Fully hydrated glossy lips fill the frame with a flawless glass-like finish, multiple sparkling highlights, subtle confident smile, premium editorial beauty lighting.

Output video

One model and one bottle through six shots of a beauty campaign — the product reveal, the walk to camera, the applicator, the macro finish

What Each Model Takes as a Reference

Every model on MaxH3 that reads references, with the limits the uploader actually enforces — how many images, how many clips and how long they can run, how much reference audio, and what comes out the other end.

ModelReference imagesReference clipsReference audioOutput lengthResolution
MiniMax H393 · 2–15s each · 15s total3 · 15s total4–15s768P · 2K
Seedance 2.53010 · 2–30s each · 30s total10 · 30s total4–30s480p · 720p · 1080p
Gemini Omni 1.1 Flash103—3–10s360p · 720p · 1080p · 4k
Wan 3.0 Prime105 · 1–15s each · 15s total5 · 15s total2–15s480p · 720p · 1080p
Wan 3.0105 · 1–15s each · 15s total5 · 15s total2–15s480p · 720p · 1080p
Seedance 2.093 · 2–15s each · 15s total3 · 15s total4–15s480p · 720p · 1080p · 4k
Seedance 2.0 Fast93 · 2–15s each · 15s total3 · 15s total4–15s480p · 720p
Seedance 2.0 Mini93 · 2–15s each · 15s total3 · 15s total4–15s480p · 720p
HappyHorse 1.19——3–15s720p · 1080p
HappyHorse 1.09——3–15s720p · 1080p
MiniMax H3 Max93 · 2–15s each · 15s total3 · 15s total5–15s480P · 768P
Kling V3 Omni71—3–15s720p · 1080p · 4k
Grok Imagine7——6–15s480p · 720p
Kling O171—3–10s720p · 1080p
Wan 2.755—2–10s720p · 1080p
Veo 3.13——8s720p · 1080p · 4k
Veo 3.1 Fast3——8s720p · 1080p · 4k
Veo 3.1 Lite3——8s720p · 1080p · 4k

How to Make Consistent Character Videos with Omni Reference

1
Lock What Must Not Change

One clean image per thing you are holding steady — the face, the outfit, the product, the set. One subject per frame, front-facing and evenly lit: that image is what every shot gets matched against, so a crowded or dim reference costs you likeness later.

2
Load the Set Into Omni Reference

Drop the set into the prompt box. Omni Reference takes more than pictures: MiniMax H3 reads up to nine images to hold a face or a product, three reference clips to hand it motion, and three audio files — mixed in the same generation, each with its own limit. Wan 3.0, Seedance 2.5 and Veo 3.1 read references too; the picker shows what each one accepts.

3
Direct the Rest, Then Reuse the Set

The prompt supplies everything the references do not: the action, the camera, the order of the shots. Finish a line naming what must stay identical, run it, then run the next shot on the same set — that is what makes the takes cut together.

Ready to keep one character across every shot?

FAQs

When something in the shot already exists and has to come back exactly — a face, a product, a set. A prompt alone re-invents it every run; reference to video generates from what you hand over. The subject stays the subject, and the scene, camera and action come from your prompt.

It depends on the model, and the range is wide: MiniMax H3 takes up to nine images, Wan 3.0 ten, Seedance 2.5 thirty. Several models also read reference clips and reference audio alongside the images — H3 takes three of each. The table above lists every model's limits, and the picker enforces them at upload.

Yes, on the models that declare it. That is what Omni Reference means on MiniMax H3 — images, clips and audio in the same generation, each capped on its own: nine images, three clips of 2 to 15 seconds each (15 seconds in total), three audio files. An image locks appearance; a clip is the natural way to hand over motion or a camera move.

One subject per image, front-facing, evenly lit, at a size the model can read — every side between 256 and 5760 pixels, at an aspect between 0.4 and 2.5 on H3. Variety beats repetition: three angles of the same jacket teach more than the same photo three times. Keep the face, the wardrobe and the location as separate references so each one carries a single job.

Keep the reference set and run it again. Consistency inside one clip is the model's job; consistency across takes comes from feeding the same references to each run, changing only the prompt. That is what lets a set of clips cut together into one ad or one episode instead of looking like three castings.

Fifteen of the video models on MaxH3 read references, MiniMax H3, Wan 3.0, Seedance 2.5, Veo 3.1 and Kling among them — not every model does, so the picker only offers the ones that can. Your references stay loaded when you switch, so you can run the same set through a second model without re-uploading anything.

A new account gets free credits, enough to run a short clip on the lighter models, and no card is needed to start. Credits are priced per second and vary by model and resolution; the generator shows the cost before you run it. Downloading without the MaxH3 watermark needs a plan or a credit pack.

Product films where one bottle has to look identical in every shot, campaign sets where one model appears across a season of posts, character work where the same face carries an episode, and mock-ups where a real product is dropped into a scene that was never shot. Anything where the thing on screen has to be recognisably the same thing twice.

Cast Your Subject Once, Keep It Everywhere

Upload a reference. MaxH3 handles the rest of the shoot.