Image Edit Turbo API
Use the same image editing endpoint in your application. Upload source images, pass their file IDs with a prompt, and track the asynchronous task result.
Read the Image Edit Turbo API referenceEdit one or more pictures with a text instruction using Qwen Image Edit on Medux. Upload your source images, describe the change, then preview and download the edited result. Each generated image uses 50 credits.
Start with 3,000 free trial credits for eligible tasks. Compare free credits and usage limits.
Upload one to five images to edit, then describe the change you want to see.
The latest task appears below. Processing continues on the server if you leave this page.
Content involving minors, non-consensual intimate imagery, or realistic depictions of real people without their consent is not permitted.
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.
Use the same image editing endpoint in your application. Upload source images, pass their file IDs with a prompt, and track the asynchronous task result.
Read the Image Edit Turbo API referenceThe Image Edit Turbo API reference documents the medux_image_edit MCP tool, its inputs, and authorization requirements.
Open the Image Edit MCP toolChoose one to five PNG, JPG, or WebP images to edit.
Write one clear instruction, such as replacing the background or changing an object's color. Add an optional negative prompt for unwanted details.
Select Edit image to start a Qwen Image Edit task. Follow its status, preview the edited image, and download it. Account Results keeps the task available when you leave the page.
Place the same subject in a new setting, lighting, or season without starting over.
Restyle a photo, change an object's color, or add a missing element with a single instruction.
Polish a portrait or product shot, then use it as a starting image for Lip Sync or Avatar workflows.
A single, clear instruction gives more predictable results than several changes at once.
Mention the parts that should stay unchanged, such as the subject, pose, or composition.
List unwanted details such as blur, artifacts, text, or watermarks, and review each result before using it elsewhere.
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_edit 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 GitHubIt is a browser-based image-editing Workshop using the Qwen Image Edit model (qwen-image-edit) through the Medux Image Edit Turbo service. Upload one or more images, describe the change, then generate, preview, and download the edited result.
Describe a focused change such as replacing the background, changing an object's color, adjusting the style, or adding an element. Keep one clear instruction per task and review each result.
Upload one to five PNG, JPG, or WebP images. At least one source image is required.
Yes. Upload each source image to get a file ID, then call the Image Edit Turbo API with model_id set to qwen-image-edit and the file IDs in image_file_ids. The MCP Tool section documents the corresponding medux_image_edit tool.
Once a task ID is returned, processing continues on the server. Return in the same browser and account to recover your latest submission, or open Account Results to find your running task and completed image.