Seedream 5.0 Pro generates images from a written brief and edits one to ten ordered reference images. Describe the subject, composition, materials, lighting and any text the image should contain, then choose one of eight aspect ratios, 1K or 2K resolution and JPEG or PNG output. Use Text to Image for a new illustration, infographic or photographic concept, or Image Editing to change the environment, light or content of prepared images while specifying the details to preserve.
Seedream 5.0 Pro is developed by ByteDance Seed. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Use Text to Image to build a composition from your description. Use Image Editing when prepared images establish objects, appearance or a scene, and state the purpose of each reference in order. Both tasks provide the same aspect-ratio, resolution and file-format controls.
The ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.
The ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.
The text task uses your description to establish visual content. The editing task combines a prompt with one to ten ordered image URLs, allowing you to assign separate references for subjects, objects and settings. Open a task to review its documented inputs and settings.
| Model / task | Input and workflow |
|---|---|
| Seedream 5.0 Pro Text-to-Image | The ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs. |
| Seedream 5.0 Pro Image Edit | The ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs. |
Use precise relationships and material descriptions to guide a new image, then use an existing image when the arrangement should anchor an edit. Review the actual examples for text layout, surface detail and changes in lighting.
Describe the title, labels, diagram and their positions in the prompt. The light-anatomy record requests a bilingual scientific infographic with a glass prism and light paths. Inspect the generated wording and visual relationships when preparing an educational illustration.
Supply the still-life image and describe the new illumination while naming the objects and composition to preserve. The blue-hour record requests cool window light, a restrained warm reflection and rain bokeh, giving you lighting changes to compare with the source.
Identify the glass thickness, ceramic glaze, linen fibers, wood grain and object positions that matter in the reference. These concrete details give the editing brief a clear preservation target and help you assess the resulting surfaces and arrangement.
Describe the exact object count, surface properties, viewpoint and daylight. The recorded still life requests one clear glass vase, one celadon bowl and one folded linen cloth on an oak table. Review how the generated image represents transparency, reflections and fabric texture.
Select one of eight aspect ratios, 1K or 2K resolution and JPEG or PNG. A vertical field-guide page and a wide infographic call for different frame shapes; choose the layout before reviewing the generated text, image detail and final file.
The generation record describes a glass vase, celadon bowl and folded linen cloth in north-window daylight. The editing record supplies a still-life image and asks for blue-hour lighting after rain while preserving its objects, arrangement and viewpoint. Read both complete prompts and inspect the actual files for surface texture, reflections, shadows and the requested lighting change.
Create a quiet editorial material-study still life, not an advertisement. On a worn oak worktable place exactly one hand-blown clear glass vase, one matte celadon ceramic bowl, and one folded undyed linen cloth. Soft north-window daylight reveals realistic glass thickness, subtle liquid refraction, tiny artisan bubbles, ceramic glaze variation, wood grain, and natural fabric fibers. Three-quarter eye-level composition, calm museum-study atmosphere, restrained neutral palette, physically believable shadows, photographic realism. No people, no brand, no logo, no packaging, no sales styling, no promotional text, no watermark.
Edit only the environment and lighting of this still-life image. Preserve exactly the same clear glass vase, celadon bowl, folded linen cloth, object count, object shapes, surface textures, relative positions, camera angle, crop, and focal length. Change the north-window daylight into a quiet blue-hour scene after rain: cool ambient light from the window, a subtle warm reflection from outside the frame, faint raindrop bokeh beyond the window, and physically believable reflections on the glass and glaze. Keep the oak table and museum-study mood. Do not add or remove objects. No people, no brand, no logo, no packaging, no text, no advertisement, no watermark.
Prepare a detailed written layout or source images, explain the visual relationships and select the output shape and format. Create educational graphics, field-guide pages, still-life studies or lighting revisions, then review text accuracy and image detail before using the result in a project.
Prepare the topic, exact labels and a description of the diagram’s parts. Generate a suitable layout and check the scientific relationships and rendered text before placing the image in teaching material.
Write the organisms, title, labels and page hierarchy, then choose a portrait aspect ratio. Review anatomy, spacing and wording before using the result as a guide-page concept.
Describe a small object arrangement with glass, ceramic, wood or fabric and specify its lighting. Generate a photographic concept and inspect refraction, glaze and fibers for a material reference board.
Supply an existing scene and describe the intended illumination, reflections and atmosphere. Identify the composition to preserve and review the revised image for a lighting proposal.
Prepare images for the subject, object or setting and assign each a clear role in the prompt. Generate a unified composition and inspect scale, perspective and lighting before using it as a scene concept.
Test the prompt, references, aspect ratio, resolution and format online. Retain those settings for an API request and retrieve the finished image URLs for the creation workflow in your application.
Seedream 5.0 Pro uses a per-image price for both generation and editing. Its current Vidgo configuration applies the same image rate to the supported 1K and 2K options. The dynamic table below reads the latest catalog price for each task; open the selected task and review its estimate before submitting the request.
| Model | Provider | Workflow | Max image inputs | Max output resolution | Starting rate |
|---|---|---|---|---|---|
| Seedream 5.0 Pro Text-to-Image | ByteDance | Text to Image | Not applicable | 2K | $0.075 / image |
| Seedream 5.0 Pro Image Edit | ByteDance | Image Editing | 10 | 2K | $0.075 / image |
Test your creative brief online, then bring the verified request into your application.
Enter the prompt, provide one to ten ordered images for editing and select an aspect ratio, 1K or 2K resolution and JPEG or PNG. Review the estimate, generate the image and inspect text, object relationships, materials and the requested changes.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose Text to Image when the composition starts with a written brief. Choose Image Editing when photographs, illustrations or other references already define the subject, object, setting or visual style. Explain the role of each input and the result you want to create.
Open the matching task, enter your brief and supply the required images. Review the generated result against subject appearance, composition and the requested changes before carrying the workflow into a project.
Choose the output size and file format on the task page, then review the per-image estimate. Use the current rate and the planned image count to budget generation and editing tests.
Read the actual prompt and inspect its source images and result together. Use those examples to understand how to assign input roles and describe the details to preserve or change in your own request.
Retain the task ID returned by the API to query status and retrieve completed file URLs. Use your online generation history to review earlier results and the creative direction you tested.
Use the documentation linked from each task for its exact model identifier, accepted inputs, authentication and response format. Integrate the same task you tested online so its media and settings match the request.
Seedream 5.0 Pro is a ByteDance Seed image model. Vidgo provides text-to-image generation and editing with one to ten ordered references, eight aspect ratios, 1K or 2K resolution and JPEG or PNG output. Describe the composition and details to create, or provide images and explain the changes to make.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
