Seedream v4 Image Editor
Edit images using natural language instructions with ByteDance Seedream v4 model
View detailsInputs
Loading workflow structure...
Overview
Seedream v4 Image Editor edits one to ten source images from natural-language instructions and returns edited images with a seed. Use it for product, campaign, social, or brand-asset revisions when you need multi-reference image editing with up to six outputs, auto, preset, or custom sizing, prompt enhancement, safety-checker, and seed controls.
Use cases
- Use several product or brand images to guide a single edited composition.
- Explore prompt-enhanced revisions with standard or fast enhancement.
- Generate up to six edited directions from one brief for comparison.
- Choose auto, preset, or custom sizing when the final layout has specific canvas needs.
Input tips
- Provide 1-10 public image_urls that can be fetched without login.
- Use a prompt of 3-5,000 characters that names desired changes and fixed details.
- Set num_images and max_images from 1-6 when you want several options returned.
- Choose image_size auto, a preset, or custom dimensions when the output canvas matters.
- Use enhance_prompt_mode standard for quality-oriented prompts or fast for speed.
- Use seed when repeatable edit exploration matters.
Expected output
The AI Tool returns edited images with downloadable URLs and optional content type, file name, file size, width, and height, plus the seed used and cost metadata. The shared Seedream output view renders a single image or gallery and shows seed, image count, and the Seedream v4 Image Editor model label.
Caveats
- Input image URLs must be public and reachable.
- Multi-image edits depend on prompt clarity about each reference's role.
- Prompt enhancement can shift emphasis from the original wording.
- Custom sizing can alter framing, composition, edges, or fine details.
- Safety filtering can alter or block some requests.
- Generated text, logos, product details, faces, and image edges should be reviewed before use.
