Features

We support various image generation models including finetuned flavors of Stable Diffusion and Flux models. See our complete model list.

Prompt

Create images by simply describing what you want to see. Our models understand natural language prompts and can generate images matching your descriptions. Click on the sample images to get inspired from prompt presets. Art

Negative Prompts (Stable Diffusion Only)

For Stable Diffusion models, you can specify negative prompts - descriptions of elements you don’t want to appear in the generated image. This gives you more control over the final output.

Prompt Weights (Stable Diffusion Only)

Prompt weighting allows you to emphasize or de-emphasize certain parts of a prompt, giving you more control over the generated image. Enclose the word in () to increase its weight. For greater precision, enclose the word or expression followed by ”:” and the weight modifier you wish to add. For example, “Photography of a man wearing jeans and a (pink:1.5) shirt” will increase the weight of the color pink to 150%. To decrease the importance of a word, use a weight less than 1. In practice, (keyword) is equivalent to (keyword:1.1) and [keyword] is equivalent to (keyword:0.9).

Difference between Flux and Stable Diffusion Prompting

See this advanced guide for more information.

API Access

All models are available for API access. See API documentation for more information.

Video Generation

We support multiple video generation models. The generation time is typically a few minutes. Video generation is also available for API access, see Text-to-Video API documentation.