Edit with a sentence
“Replace the background and keep the subject unchanged.”
agent model
Made Auto chooses the creative workflow for you
Upload an image or describe the result you need. Made Auto interprets the request, selects an available Made tool, and keeps follow-up edits in one conversation.
What you need to start
Add an image for edits, or start with a text request for generation.
Original results
Made Auto examples made in Made
These examples use media produced for Made. Prompts are included when the production record allows them.
Keep refining
“Make the lighting warmer and leave everything else as it is.”
Route to the right tool
“Prepare this portrait for a vertical social post.”
Change a background
“Put the subject in a clean studio setting.”
Clean up a scene
“Remove the distracting objects behind the subject.”
Try a creative direction
“Give this photo a cinematic editorial treatment.”
Where Made Auto fits best
Best uses
- Multi-step edits that combine more than one Made capability
- Natural-language image changes without choosing a tool first
- Resizing, expanding, generating, and refining within one conversation
- People who want the workflow selected automatically
Limits to know
- Automatic routing may choose a different underlying model as Made updates its production workflows.
- Precise manual masking and frame-by-frame video editing are better handled in dedicated editors.
Specifications in Made
These are the controls exposed by Made, which may be narrower than a provider’s full API.
- Aspect ratios
- Depends on the selected workflow
- Resolution
- Depends on the selected workflow
- Duration
- Not applicable
- Output formats
- JPG, PNG, WebP where supported
- Reference images
- 1
- Processing
- Varies by the selected operation; progress appears in the editor.
How to use Made Auto in Made
- 1
Describe the outcome
Write what you want to create or change in everyday language.
- 2
Add source media if needed
Attach an image when the request edits, resizes, or transforms an existing visual.
- 3
Review the selected workflow
Made Auto routes the request and shows progress in the editor.
- 4
Refine or download
Continue with follow-up instructions, then download the result when it is ready.
Approved examples and guides
Workflows tested with Made Auto
Example
Breakfast Still Life Resized for a Web Hero
An overhead editorial food master cropped to a 1600 × 900 WebP while keeping the central bowl, linen, and glass readable across a wide publishing slot.
Example
Breakfast Still Life Square Social Crop
A wide overhead food photograph converted into a 1080 × 1080 square WebP with the bowl retained as the focal subject and supporting props deliberately trimmed.
Example
Circular Profile Photo with Transparent Corners
A wide studio portrait resized into an 800 × 800 circular PNG with the person centered and every pixel outside the circle transparent.
Compare relevant models
image
Flux 1.1 Pro
Flux 1.1 Pro is a flexible image-generation model in Made for polished concepts, product visuals, and photorealistic scenes from descriptive prompts.
Explore model →video
WAN 2.2 Turbo
WAN 2.2 Turbo is Made’s fast iteration option for short text-to-video and image-to-video clips, with portrait and landscape output controls.
Explore model →image
Restore Image
Restore Image is a focused Made workflow for reducing scratches, fading, and visible damage while preserving the recognizable people and composition in a source photo.
Explore model →Continue with a related tool
AI Photo Editor
Skip the complex menus and toolbars. Edit Images With Text Prompts. Our AI photo editor understands what you want. Type "remove the background" or "make it brighter" and watch it happen instantly.
Open tool →Image Resizer
Upload an image, describe the target dimensions or destination, and choose whether Made should fit, crop, stretch, or pad the result.
Open tool →Image Upscaler
Made’s Image Upscaler analyzes a source image, enlarges it, and improves visible detail for a clearer result than ordinary pixel stretching.
Open tool →Made Auto is Made’s orchestration experience. It reads a plain-language request and selects an available generation or editing workflow.