> ## Documentation Index
> Fetch the complete documentation index at: https://platform.stepfun.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Image Generation & Editing Models

<Note>
  `step-2x-large` and `step-image-edit-2` will be retired on October 10, 2026; `step-1x-edit` is no longer available. The text-to-image, image-to-image, and image editing APIs will stop serving requests. See the [image model retirement notice](/docs/en/guides/image-offline-notice).
</Note>

## Model overview

Our text-to-image models generate high-quality, diverse images from text prompts or other inputs. They are widely applicable for art, design, game development, and beyond.

We currently provide the step-1x and step-2x model series:

## Models

### step-2x-large

Our new-generation image model focused on text-to-image generation. Produces more realistic textures and stronger Chinese/English text rendering.

## Key terms

1. **Image resolution**: Pixel width/height of the output. Higher resolution gives more detail but increases generation time and compute.
2. **Image style**: Visual characteristics such as realistic, abstract, cartoon, etc.
3. **Prompt/description**: The text or reference image describing what to generate. More precise descriptions yield outputs closer to expectations.
4. **Model parameters**: Larger models capture more detail and produce higher-quality results. The step-1x line offers a 2B-parameter model.

## Usage limits

1. **Supported input**: Natural-language descriptions of desired content and style.
2. **Images per request**: step-1x models allow up to 1 image per request.
3. **Resolution limits**: Squares: `256x256`, `512x512`, `768x768`, `1024x1024`; 16:9: `1280x800`, `800x1280`.
4. **Generation time**: Varies with prompt complexity and model throughput.
5. **Quality**: Results depend on prompt specificity and training data; multiple attempts may be needed for the best output.
6. **Copyright and usage**: You own generated images but must not use them for illegal purposes or rights violations. Models are evolving, so evaluate and adjust for your scenario.