flux-2/max/text-to-image
Create photoreal visuals with multi-reference, color, and typography precision.
Seedream 5.0 Pro Image Edit is ByteDance's advanced image editing model. It reads a text instruction plus one or more reference images to edit, restyle, and recompose visuals at 1K or 2K resolution, with strong control over composition, spacing, and on-image text. This model page runs the image editing (image-to-image) task.
Beyond simple retouching, Seedream 5.0 Pro Image Edit supports interactive editing with positional and color cues, multi-reference guidance for consistent subjects and styles, and layer separation that exports transparent PNG assets for downstream design.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt * | Yes (*) | string | Editing sample | Up to ~600 English words | Text instruction describing the edit to apply. |
| image * | Yes (*) | array | 1 sample image | 1 to 10 images; jpeg, png, webp, bmp, tiff, gif, heic, heif; <30 MB each; min 14x14 px; aspect ratio 1:16 to 16:1 | Reference images to edit or guide the result. |
| resolution | No | string | 2K | 1K, 2K (describe the aspect ratio in the prompt) | Output resolution level; 1K is billed at $0.05, 2K at $0.10. |
| output_format | No | string | png | png, jpeg | File format of the returned image. |
Seedream 5.0 Pro Image Edit is billed by output resolution: $0.05 per image for outputs up to 2.36M pixels and $0.10 per image for outputs above 2.36M pixels.
Create photoreal visuals with multi-reference, color, and typography precision.
8-step Turbo model enabling rapid, high-quality visual edits for creators
Fast bilingual image creation engine with depth and pose guidance for precise, photoreal visual design.
OpenAI's GPT Image 2 Image Edit: Image-to-image edits with precise text control and in-out painting
Create multilingual, high-fidelity visuals with precise text-driven generation and seamless edit control.
Prompt-driven image editing with Nano Banana 2 Edit, with multi-image input plus aspect ratio, resolution, safety tolerance, and output controls.
Seedream 5.0 Pro Image Edit reshapes and restyles existing images from a text instruction plus reference images. It is built for design-grade editing such as brand-consistent product shots, style transfer, and multilingual posters, where layout precision and clean typography matter.
Seedream 5.0 Pro targets higher fidelity and finer control than the Lite tier, with stronger layout handling, layer separation, and 14-language text rendering. Based on publicly available information, it favors polished single images over grouped or streamed batches, so it suits final assets rather than quick drafts.
Seedream 5.0 Pro Image Edit accepts up to 10 reference images per request. Each image can be jpeg, png, webp, bmp, tiff, or gif, under 10 MB, at least 14 pixels on each side, with an aspect ratio between 1:16 and 16:1.
Yes. It follows positional cues, color references, and multiple markers to place type and objects where you describe them, and it renders letters and numbers across 14 languages. This helps with posters, packaging, infographics, and brand layouts.
You can choose a size tier (2K or 3K, where the model decides width and height) or an exact pixel dimension up to 4704x2016, with aspect ratios from 16:1 to 1:16. For tier options, describe the aspect ratio or purpose in your prompt.
Yes. The model can split a scene into a background plus individual elements and export transparent PNG assets, which is useful for downstream design work that needs editable layers rather than a single flattened render.
Yes. You can prototype in the RunComfy model UI, then call the same model through the RunComfy API using identical parameters. This lets you move from browser experiments to automated production without hosting or scaling the model yourself.
Seedream 5.0 Pro Image Edit is coming soon, and the model behind this page currently runs Seedream 5.0 Lite, billed at $0.028 per output image. Generations draw from your RunComfy credits, and new users typically start with a free trial balance.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
