Aller au contenu
Atlas de l'IA

Édition d’image et inpainting

Modifier une zone de l’image par une consigne écrite

Génération et édition d'imagesDébutant #20
entréeImageTexteImage

Le texte intégral est présenté en anglais ; le titre et le résumé sont localisés.

CE QUE DÉSIGNE CETTE CAPACITÉ

Takes the original image, a written instruction and usually a mask marking the region to change, and outputs the modified image. Unlike image-to-image it has an explicit, local edit intent and should leave unspecified areas untouched; unlike text-to-image it does not generate from scratch but operates surgically on an existing picture.

Comment c'est fait

The base method is inpainting: noise is added and removed only inside the mask while the rest reuses the original latents, with the instruction injected through cross-attention or an adapter. More careful schemes add a reference image and an identity-preservation branch so the edited person keeps the same face; another route hands instruction and image to a multimodal model that predicts the edited latents directly.

Produits représentatifs

5

Organisations concernées

Usages typiques

  • Removing clutter and swapping backgrounds in product photos
  • Portrait retouching and restyling
  • Swapping assets in ads and posters
  • Restoring old photos and filling missing parts

Comment on l'évalue

Edit-direction consistency
Whether the CLIP-space shift matches the instruction direction
FID
Distribution gap to real images, guarding against degrading realism
Human rating
Ratings for instruction completion and preservation

Limites et points difficiles

  • Boundary, lighting and noise in the repainted area often mismatch the surroundings and need several passes
  • Multi-part requests — new outfit, new background, new expression — usually complete only some of them
  • Large edits drift the identity, so the face stops resembling the original person

Concepts sous-jacents