MiniMax H3 Image
par MiniMax
Sixteen reference images keep one face across every frame.
Native 4K, drawn in about twenty seconds.

Points clés
One face, many frames
Give it up to sixteen reference images, such as a character sheet, a location and the previous frame, and it keeps the person, the costume and the room consistent from shot to shot.
Native 1K, 2K and 4K
Every size is generated at full resolution rather than upscaled. 4K is about sixteen megapixels, enough to crop a close-up out of a wide frame.
Fast
A 2K frame with two reference images came back in about twenty-three seconds in our test, two to three times faster than the GPT Image tier Dimly uses by default.
Range of looks
Film photography, painterly light, paper-cutout sets and neon nights from plain-language prompts, so a whole video can hold one visual language.
Chinese and English text
MiniMax pitches it on reasoned text rendering for signs and posters in both languages. Short words came out right in our tests, though it sometimes adds small made-up text around them.
Open weights
MiniMax publishes the weights: a 33-billion-parameter diffusion transformer that draws in six steps, from the same family as the H3 video model.
Caractéristiques techniques
H3 Image
MiniMax's open-weights text-to-image and edit model
16 references
Public image URLs, up to 20 MB each
1K / 2K / 4K
About 1, 4 and 16 megapixels, all native
21:9 to 9:16
Eleven aspect ratios, or a custom size
~23 s
A 2K frame with two references, measured
PNG or JPEG
One image per request
5,000 characters
Prompt length, Chinese or English
6 steps
No negative prompt; describe what you want in the frame
Exemples de prompts
Night bus
She sits alone at the back of an empty night bus, bass case on the seat beside her, orange sodium streetlights streaking across the windows, looking out at the city
Modifier le promptRooftop at dawn
She stands on a tar rooftop at dawn playing the bass, the city skyline soft and pink behind her, wind in her hair. Vertical frame, full figure, natural light
Modifier le promptDesert blue hour
A lone white tour van parked on an empty desert highway at blue hour, headlights on, a single figure sitting on the roof looking at the first stars
Modifier le promptNeon sign
A rain-slicked alley at night with a red neon sign over a diner door that reads exactly "OPEN LATE". No other words anywhere in the frame
Modifier le promptPaper set
A paper-cutout stop-motion set: a cardboard moon hanging on a string above layered paper waves, a tiny paper boat with a glowing lantern
Modifier le promptForest choir
A dozen people in white shirts singing together in a misty pine forest in the morning, light beams through the trees, shot from low
Modifier le promptCas d’usage

Keyframes that keep the cast
Draw each shot of a verse from the same character sheet, and the singer looks like the same person on the bus, on the stage and on the roof.

Live-show frames
Stage light, haze and a crowd in silhouette for the performance shots between the story scenes.

Wide establishing shots
Open a video on a place, like a desert road at blue hour, before the first face appears.

Character sheets
A clean, well-lit portrait of the lead is the reference every later frame is drawn from.
Présentation
MiniMax H3 Image is MiniMax's open-weights image model, built from the same family as its H3 video model. It turns a prompt into a picture, or edits from up to sixteen reference images at once, at native 1K, 2K or 4K. It is a 33-billion-parameter diffusion transformer that draws in six steps, which is why a 2K frame takes seconds rather than a minute.
Why sixteen references matter for a music video
A music video is dozens of frames of the same people in different places. Each frame needs the character sheet for every person in the shot, the location, and often the previous frame, so the light carries over. Most image models cap references at eight or fewer. Sixteen leaves room for a two-person shot without dropping anything.
The four bassist frames on this page were drawn from one portrait: the same face, haircut, jacket and bass on a night bus, a rooftop, a laundromat and a stage.
Lettering and prompt rewriting
Kie, the API Dimly calls it through, rewrites prompts into a longer description by default. In our tests that rewriting once dropped a letter from the words we asked for, so Dimly always turns it off. With it off, short words came out right, but the model sometimes adds small made-up text around them, so Dimly keeps keyframes with lyrics in the frame on GPT Image 2.6.
MiniMax H3 Image and Dimly
Every Dimly music video starts as images: character sheets, look previews and one keyframe per shot, which a video model then animates. You don't pick the image model in the studio. Dimly's director draws with GPT Image 2.6 by default and can be switched to MiniMax H3 Image, which costs half the credits per keyframe and draws two to three times faster.
For the motion, see MiniMax H3, the video model from the same family.
Tarification simple
Préparez votre vidéo gratuitement, puis choisissez le plan adapté à votre calendrier de sortie.
Starter
Un mois régulier de Chorus Cuts, ou une chanson plus courte.
- 600 crédits, valables 30 jours
- ≈ 8 Chorus Cuts (15 s)
- ou une chanson allant jusqu’à 2:20
- Tous les modèles et toutes les résolutions · 3 rendus à la fois
Pro
Une chanson complète par mois avec de la marge pour refaire des prises, et plus de crédits quand une sortie en a besoin.
Crédits par mois
- 1 000 crédits, valables 30 jours
- ≈ 14 Chorus Cuts (15 s)
- ou 1 chanson complète (3:45)
- Tous les modèles et toutes les résolutions · 4 rendus à la fois
Creator
Plusieurs chansons complètes par mois, jusqu’en 4K.
- 5 000 crédits, valables 30 jours
- ≈ 72 Chorus Cuts (15 s)
- ou ≈ 5 chansons complètes (3:45)
- Tous les modèles et toutes les résolutions · 8 rendus à la fois
Chanson complète, Chorus Cut, vidéo lyrics ou visualiseur · Exports sans filigrane sur tous les forfaits · Les droits d’export dépendent de vos autorisations sur la source et des conditions des fournisseurs
Packs de crédits
Payez une fois, sans abonnement. Pensé pour un effet vidéo IA ou une chanson ; si vous comptez en créer plusieurs, un plan ci-dessus est plus avantageux.
À l’unité
Une vidéo d’effet IA, comme Hotel Lobby ou AI Rap Duo.
- 250 crédits, valables 1 an
- 1 vidéo d’effet IA (Hotel Lobby, AI Rap Duo)
- ou ≈ 3 Chorus Cuts (15 s)
- Les exports portent le filigrane Dimly
- Sans abonnement, jamais renouvelé
Chanson
Un clip complet (une chanson jusqu’à 3:45), ou quatre effets IA.
- 1 000 crédits, valables 1 an
- 4 vidéos d’effet IA (Hotel Lobby, AI Rap Duo)
- ou 1 chanson complète (3:45)
- Exports sans filigrane
- Sans abonnement, jamais renouvelé
Studio
Une chanson complète en 2K avec de la marge pour refaire des prises, ou deux chansons.
- 2 000 crédits, valables 1 an
- 8 vidéos d’effet IA (Hotel Lobby, AI Rap Duo)
- ou ≈ 2 chansons complètes (3:45)
- Exports sans filigrane
- Sans abonnement, jamais renouvelé
Les estimations utilisent MiniMax H3 en 768P avec des plans de 5 secondes (un Chorus Cut de 15 secondes compte pour trois), une keyframe par plan, deux planches de référence et aucune reprise ; une chanson complète dure 3:45, la durée typique des chansons qu’on nous apporte. Les résolutions supérieures et les autres modèles coûtent plus cher par vidéo. Vous voyez le devis exact avant tout rendu, et les rendus échoués sont remboursés.
FAQ
MiniMax's open-weights image generation and editing model. It takes a prompt and up to sixteen reference images and draws one image at native 1K, 2K or 4K.
No. MiniMax H3 is the video model; H3 Image is the image model from the same family. In Dimly, an image model draws the keyframes and a video model such as MiniMax H3 animates them.
Not as a choice in the studio: you don't pick the image model. Dimly's director draws character sheets, look previews and keyframes with GPT Image 2.6 by default and can be set to use MiniMax H3 Image instead. Keyframes with lyrics in the frame stay on GPT Image either way.
One to sixteen, passed as public image URLs of up to 20 MB each. MiniMax refers to them in the prompt as Picture 1, Picture 2 and so on, in order.
Native 1K, 2K and 4K (about 1, 4 and 16 megapixels) in eleven aspect ratios from 21:9 to 9:16, or a custom width and height of up to 8,192 pixels a side.
Dimly generated them with MiniMax H3 Image at 2K on 15 November 2026, through the same Kie route the studio uses, and downscaled them for the web. The four bassist frames share one reference image, the rehearsal-room portrait.
Autres modèles
Voir tous les modèlesMiniMax H3
MiniMax
Reference-driven video with native stereo sound. Your track drives the picture, 768P up to 4K.
Seedance 2.5
ByteDance
First-and-last-frame moves up to thirty seconds, audio-driven at 480p/720p — your song muxed back intact.
Kling 4.0
Kuaishou
Kuaishou's long-take video model: up to thirty seconds in one pass, ten keyframes and Omni Reference with up to fifteen inputs.
Seedream 5.5
ByteDance Seed
ByteDance Seed's image model: natural skin and light, edits that leave the rest of the frame alone, and dense small text that stays legible.




