> ## Documentation Index > Fetch the complete documentation index at: https://docs.mage.space/llms.txt > Use this file to discover all available pages before exploring further. # MiniMax H3 Image: open-weights 4K images and edits on Mage > MiniMax H3 Image is MiniMax's open-weights image model on Mage: text-to-image and edits from up to 16 reference images, at 2K or native 4K, with Characters, References, and LoRAs. MiniMax H3 Image is MiniMax's open-weights image model, released on November 10, 2026 as part of the MiniMax-H3 family. One model makes images from text and edits or combines up to 16 reference images, at 2K (about 4 megapixels) or its native 4K (about 16 megapixels). It follows long, detailed instructions closely, renders text in the image well, and is strong at photorealism. Mage runs it on its own GPUs, so a 2K image takes a few seconds and a 4K image about 13. It takes Characters, References, and LoRAs. ## Overview | Detail | | | - | - | | Type | Image | | Origin | Open-weights model hosted on Mage's GPUs | | Models | MiniMax H3 Image | | Unlimited from | Pro | ## Unlimited generation by plan Which plan runs each resolution unlimited at launch, at the model's base settings. Gems means that setting always costs Gems on that plan. | Model | Setting | Basic | Pro | Pro Plus | Max | | - | - | - | - | - | - | | MiniMax H3 Image | 2K | Gems | Unlimited | Unlimited | Unlimited | | MiniMax H3 Image | 4K | Gems | Gems | Unlimited | Unlimited | Three or more LoRAs move a run to Pro Plus. On Gems, a text-to-image run costs 15 Gems at 2K and 25 at 4K at launch, and each reference image adds a few Gems; the app shows the price before you generate. ## What it supports on Mage | Feature | Support | | - | - | | Characters and References | Yes | | Reference images | Up to 16 | | Edits an input image | Yes | | LoRAs | Yes | | Negative prompts | No | | Text in the image | Yes | | Resolutions | 2K, 4K | | Aspect ratios | All nine, from 21:9 to 9:21 | ## Best for * Photoreal images with fine detail at a native 16 megapixels * Long, detailed prompts and complex instructions * Posters, signs, labels, and other text in the image * Edits that change one thing, and composites that bring many images into one scene * Styles from MiniMax H3 Image LoRAs ## Writing prompts MiniMax H3 Image does best with a detailed English description of the whole image: the subject, the setting, the composition, the light, the style, and any text that should appear, in quotes. Short prompts work too, with less control over the result. Reference images are `image 1`, `image 2`, and so on, in order: your uploads first, then the Characters you mention, then the References you mention. Write `@image1` for an upload and `@handle` for a Character or Reference, as on other models. For an edit, say what to keep from each image, say what changes, then describe the image you want. ## Example prompts to start from ```text theme={null} An overhead photo of a farmhouse breakfast on a weathered oak table: a cast-iron skillet of fried eggs, a sourdough loaf with a cracked golden crust, a jar of honey with a wooden dipper, and a small card by the plate that reads "GOOD MORNING" in black capitals. Soft morning light from the upper left, long gentle shadows, natural colors. ``` ```text theme={null} Keep the face, hair, and expression of @sasha exactly as they are. Dress her in the red wool coat from @image1 and stand her on a rainy city street at dusk, under a lit shop sign that reads "OPEN LATE". A vertical street photo with wet pavement reflections and warm window light. ``` ## Using LoRAs Pick a MiniMax H3 Image LoRA under **Model → LoRA**, or bring your own on the [Import](https://www.mage.space/import) page by choosing MiniMax H3 Image as its model. Only LoRAs import for this model, not checkpoints. See [LoRAs](https://docs.mage.space/features/loras.md) for how weights and stacking work. ## Limitations * No negative prompt, step count, or guidance scale: the model is distilled to six steps with its guidance built in. To leave something out, describe the image without it. * 2K is the smallest size; there is no 1K option. * Each reference image adds time and Gems, so an edit from many images takes longer than text-to-image. ## Use via API MiniMax H3 Image is available through the [Mage API](https://docs.mage.space/api/overview.md) as the `minimax_h3_image` architecture. Its fields, tokens, defaults, and price are on [its API reference page](https://docs.mage.space/api/models/minimax_h3_image.md). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.