Two very different models
Image-01 is built for cheap, everyday images; H3 is MiniMax's newer multimodal model with multi-reference editing. Draft on Image-01 and switch to H3 when you need the same character across scenes.
MiniMax makes H3, a multimodal model that generates and edits images, and Image-01, its first text-to-image model. On Kenerate, MiniMax H3 Image costs 6 credits with up to 9 references; Image-01 is one of the cheapest models here at 1.05.
Quick answer
Updated
MiniMax makes two image models on Kenerate. Image-01 (announced 28 February 2025) was its first text-to-image model, aimed at photoreal people and low cost; it is 1.05 credits here, one of the cheapest models on Kenerate. MiniMax H3 (31 July 2026) is a multimodal model for images and video; MiniMax H3 Image costs 6 credits (18 at 2K) and edits with up to 9 reference images — useful for keeping a character consistent.
About the model
Facts from the maker's own announcement and repository, linked below.
| Maker | MiniMax |
|---|---|
| Image-01 | 28 February 2025 — MiniMax's first text-to-image model; photoreal people and objects |
| MiniMax H3 | 31 July 2026 — a general-purpose multimodal model for images and video |
| On Kenerate | MiniMax H3 Image (6 · 18 at 2K; edits 9+, up to 9 references) and Image-01 (1.05, 1 reference) |
Gallery
Real outputs made on Kenerate. Open any image to copy its prompt and run it yourself.
Same prompt
The same portrait prompt on both MiniMax models.


Portrait of a young woman with freckles and a green knitted scarf in autumn light, 85mm
Models
Every version in the generator, and what each is good at.
From our tests
This model runs through its provider with its own content rules. For adult art, use open models on the uncensored AI image generator (18+).
How to
Try MiniMax Image on your own prompt — 25 free credits on sign-up.
In depth
Background, how to prompt it, and when to pick something else.
Image-01 is built for cheap, everyday images; H3 is MiniMax's newer multimodal model with multi-reference editing. Draft on Image-01 and switch to H3 when you need the same character across scenes.
We only publish real, verified reviews — never invented quotes. Send a line about your result (and whether we may quote you), and it will appear here.
FAQ
4 questions
MiniMax's first text-to-image model, announced on 28 February 2025. On Kenerate it costs 1.05 credits — one of the cheapest models here.
A general-purpose multimodal model from MiniMax (July 2026) for images and video. MiniMax H3 Image on Kenerate costs 6 credits and takes up to 9 references.
Yes — upload reference images to MiniMax H3 Image and refer to them by number, like the barista example.
Image-01 for low-cost photoreal images at 1.05 credits; H3 Image when you need reference images or 2K output (6 credits, 18 at 2K).
Explore
Generators, design tools, photo edits, models and comparisons — all in one studio, on one credit balance.
Written by the Kenerate AI team
We run these models in the Kenerate generator. Model facts come from the makers' own pages; specs and limits were checked against our code; the examples are our own outputs. Last updated 27 September 2026. Corrections: hello@kenerateai.com.
Ready when you are
25 free credits on sign-up. No watermark.