Image-to-Image Workspace¶
Route: /#/image/image2image
Use this workspace when you already have an input image and want to continue editing from it.
First-time rule of thumb¶
If both are true, this is usually the right page:
- your final output is an image, not text
- you already have one input image as the starting point
Typical use cases¶
- testing prompt versions on the same base image
- comparing image models against the same base image
- style transfer, repainting, or direction-change validation
If you only have text and no input image, use Text-to-Image Workspace.
If you only want the fastest start¶
- upload one input image
- write the image-to-image prompt on the left
- run one left-side analysis or optimization
- keep one image model fixed on the right
- compare
original / workspace / vNthrough real images
What the left side edits¶
The left side edits the image-to-image prompt itself.
The left side uses a text model, not an image model.
What the right side tests¶
The right side tests:
- one prompt version
- the same input image
- one image model
- the real generated image
Recommended workflow¶
- upload one input image
- write the original prompt
- optimize or analyze it once on the left
- keep one image model fixed and compare
original / workspace / vN - select the better prompt version
- then keep that version fixed and compare image models