Seedream through the Text to Image API
The API reference documents model_id, prompt, aspect_ratio, clarity, quantity, image_file_ids, and the asynchronous task response used by this Workshop.
Read the Text to Image API referenceTurn a written idea into an image with Seedream. Switch between Seedream 5.0, 5.0 Lite, 5.0 Pro, 4.5, and 4.0, choose output settings, and check your account's current credit estimate before submitting.
Start with 3,000 free trial credits for eligible tasks. Compare free credits and usage limits.
Choose a Seedream model, write your prompt, and optionally upload up to eight reference images. The available settings and credit estimate update with your selection.
Sign in to see the current credit cost for each model.
The latest task appears below. Processing continues on the server if you leave this page.
No image yet. Generate one to see it here.
Use the service behind this Workshop in your application or AI agent. Explore the API reference and its corresponding MCP tool before starting an integration.
The API reference documents model_id, prompt, aspect_ratio, clarity, quantity, image_file_ids, and the asynchronous task response used by this Workshop.
Read the Text to Image API referenceUse the corresponding Text to Image MCP tool from a connected agent. Review the published parameters and authentication guide before calling it.
Open the Text to Image MCP toolSwitch among the Seedream models listed on this page. The form shows each model's supported clarity, aspect ratios, image quantities, and current credit cost for your account.
Describe the subject, setting, lighting, and style. Add reference images only if you want to guide the result.
Check the estimated credits, then submit. Follow the task here or in Account Results, and download each completed image.
Explore scenes, lighting, and art direction for a visual brief before choosing a final direction.
Generate distinct compositions from a written description, then compare the results of different Seedream models.
Add reference images when the composition or style should follow existing visual material.
Name the main subject, camera angle, lighting, and background so the image has a clear visual focus.
Available clarity and image quantity vary by model. Review the credit estimate after every model or setting change.
Upload only images you may use, and explain which visual details the result should follow.
Every Medux tool has open examples on GitHub: copy a prompt for Claude or Codex, or start from a working API request.
A ready-to-paste prompt and approval checklist for running medux_image_generate_text_to_image from Claude.
View on GitHubThe same workflow for Codex: expected tool call, arguments to review and how to verify the result.
View on GitHubRequest fields, curl, Python and JavaScript samples, and response handling for this endpoint.
View on GitHubThe model menu reads the current Playground catalog and lists the Seedream models available on this page. Your account's plan and model availability are checked before generation.
Sign in to see your account's current rate and an estimated total. The estimate is calculated by Medux for the selected model, clarity, aspect ratio, and image quantity before you generate.
Yes. Add up to eight PNG, JPG, or WebP images. The model's current input limit is also checked before the request is submitted.
The finished images appear here when the task succeeds. You can also return to this page with the same account or open Account Results to find the task.