Leave unselected for Auto. Auto lets the model choose dimensions within the selected resolution tier. Pick a ratio to use the preset size for that tier.

Resolution tier. Auto aspect mode uses this tier while dimensions are chosen automatically.

Split one attached image into a base image plus up to 16 transparent PNG layers, delivered as separate attachments. Attach exactly one image. The prompt is optional: leave it empty to let the model choose the elements, or name the ones to separate.

Keep the alpha channel so the result has no background. Needs one attached image that already has transparency, and PNG output.

Add an 'AI generated' watermark to the bottom-right corner.

Settings

Seedream 5.0 Flash creates and edits images quickly from text prompts and up to 10 reference images.

Generation & Editing
- Generate from a text prompt
- Edit or combine one to ten attached images
- Mark an area with a sketch, arrow, or coordinates to edit it precisely
- Separate one attached image into a base image plus up to 16 transparent layers
- Render text in Chinese, English, and 14 other languages

This bot supports optional parameters for additional customization.

Poe - Fast AI Chat

Poe API

Seedream-5.0-Flash

More from EmpirioLabs AI