Three new image model families are now live for generation and editing.

Qwen Image 3: bilingual prompt support, automatic prompt expansion, negative prompts, and 1K or 2K output. Text-to-Image Image-to-Image
Muse Image: agentic image generation, precise edits, strong typography, and multi-part prompt following. Text-to-Image Image-to-Image
Nano Banana 2: fast Gemini image generation with resolutions from 0.5K to 4K, optional web grounding, and enhanced reasoning. Text-to-Image Image-to-Image

Edit an existing image in any way you'd like.

powered by Black Forest Labs AI (Apache License 2.0)

Prompt

Describe how the final image should look like

Init image

Upload the original image to be modified.

Max: 512x512px (auto-resized)

Drag and drop files here or click

Available in Power Mode

Count

Number of results to generate in parallel.

More options

Guidance

Adjusts how much the AI tries to fit the prompt (higher = stricter, lower = more freedom). The sweet spot is between 6-10, extreme values may produce more artifacts.

2.0

Acceleration

The acceleration to use for the image generated.

regular

Seed

Unique output seed number. If not provided, the output will be random.

Available in Power Mode

Steps

Number of sampling steps. More steps = more details but also longer computation time.

Format

The encoding format of the generated image.

PNG