Edit images
These models allow editing and manipulating images in various ways. Key capabilities include:
- Inpainting & object removal - Remove objects or fill in missing image regions. Useful for removing unwanted elements from photos.
- Background removal - Delete and replace image backgrounds. Isolate subjects onto transparent or alternate backgrounds.
- Guided editing - Make targeted edits to images by adding guiding information like depth maps, sketches, edge detection, human poses, or text prompts. Allows fine-grained creative control.
Note: For face restoration and photo colorization, see our Upscale Images collection.
Our Picks
Best Inpainting Model: logerzhu/ad-inpaint
For removing objects and filling in missing regions of an image, we recommend starting with logerzhu/ad-inpaint. It delivers great results and runs faster than alternatives like instruct-pix2pix.
Best Background Removal: pollinations/modnet
To isolate a subject and replace the background of an image, pollinations/modnet is the clear choice. It’s optimized for this specific task and widely used.
Best Guided Editing: alaradirik/t2i-adapter-sdxl-depth-midas and other t2i-adapter models
For the most control over editing an image, try the alaradirik/t2i-adapter-sdxl-depth-midas model. It lets you modify an image using an automatically generated depth map.
The other models in the t2i-adapter-sdxl-* series are also great for guided editing using different types of inputs:
- alaradirik/t2i-adapter-sdxl-lineart - Edit using line art
- alaradirik/t2i-adapter-sdxl-canny - Edit using edge detection
- alaradirik/t2i-adapter-sdxl-sketch - Edit using sketches
- alaradirik/t2i-adapter-sdxl-openpose - Edit using human pose detection
Promising New Approaches
For even more advanced guided editing, two newer models are worth exploring:
adirik/masactrl-sdxl allows you to edit specific regions of an image using text prompts. It provides fine-grained control for local edits.
adirik/stylemc is a unique model that generates new images in the style of an input image based on a text prompt. While not a traditional editing model, it enables creative exploration.
Recommended models
![](https://tjzk.replicate.delivery/models_models_featured_image/40223a51-a460-4f27-b13a-bf5d6429b686/output_1.png)
tencentarc/gfpgan
Practical face restoration algorithm for *old photos* or *AI-generated faces*
![](https://tjzk.replicate.delivery/models_models_featured_image/0e31af92-963e-4ae3-b900-6104b22f4f7f/012.png)
sczhou/codeformer
Robust face restoration algorithm for old photos / AI-generated faces
![](https://tjzk.replicate.delivery/models_models_featured_image/94040932-a886-4c65-add8-9ea690d8053d/slack-imgs.png)
rossjillian/controlnet
Control diffusion models
![](https://replicate.delivery/pbxt/2hczaMwD9xrsIR8h3Cl8iYGbHaCdFhIOMZ0LfoYfHlKuuIBQA/out.png)
cjwbw/rembg
Remove images background
![](https://replicate.delivery/pbxt/RiurKSg4UNI4D1mwNeFH34k3NNDsxH6yK4m6XbpdEOH05M9HA/out-0.png)
andreasjansson/stable-diffusion-inpainting
Inpainting using RunwayML's stable-diffusion-inpainting checkpoint
![](https://tjzk.replicate.delivery/models_models_featured_image/0bcd2b2e-1d38-42a3-bdaa-0c84c16e7c99/styleclip.jpg)
orpatashnik/styleclip
Text-Driven Manipulation of StyleGAN Imagery
![](https://tjzk.replicate.delivery/models_models_featured_image/ea2dabc5-4973-49e4-9f3a-f73b10ad4ca6/instruct-pix2pix.jpg)
timothybrooks/instruct-pix2pix
Edit images with human instructions
![](https://tjzk.replicate.delivery/models_models_cover_image/bb0ab3e4-5efa-446f-939a-23e78f2b82de/output.png)
pollinations/modnet
A deep learning approach to remove background & adding new background image
![](https://tjzk.replicate.delivery/models_models_featured_image/e21a425b-4cdb-445b-8b2f-5be1b26fb78d/ad_inpaint_2.jpg)
logerzhu/ad-inpaint
Product advertising image generator
![](https://tjzk.replicate.delivery/models_models_featured_image/8d4c8b4c-8006-4577-a6c7-73ba624f1c69/1.webp)
arielreplicate/deoldify_image
Add colours to old images
![](https://pbxt.replicate.delivery/jR6ZtGztysLkJxhSeGHWu25iu9GfopTWIAeb6GSdr5K8xBVjA/out-0.png)
adirik/t2i-adapter-sdxl-depth-midas
Modify images using depth maps
![](https://replicate.delivery/pbxt/LEUR8uWubCLLJ5aebWHGJ8RN1bXZbETzezd3usAV9aHNe2eDB/inpainted.png)
naklecha/fashion-ai
This model can edit clothing found within an image, using a state of the art clothing segmentation algorithm.
![](https://pbxt.replicate.delivery/nuE2A9YWRkLaN1ptkgad1JeHtYJwUWAt6p7Bie0fYDcNlCVjA/out-0.png)
adirik/t2i-adapter-sdxl-openpose
Modify images using human pose
![](https://replicate.delivery/pbxt/f8xV2WI2WdzpdCqOdgdBF4p8AI5LNEPTQ5WWjn62yUzLNQ1IA/out-0.png)
adirik/t2i-adapter-sdxl-lineart
Modify images using line art
![](https://replicate.delivery/mgxm/a3e386e9-e6af-42da-b667-d7c65e55573c/output.png)
storymy/take-off-eyeglasses
Remove eyeglasses and shadows from photo
![](https://replicate.delivery/pbxt/ALPdmbV71P7OAx6kEoiG1vS7H4KBofifF1jGII7g73gZ4gqRA/out-0.png)
adirik/t2i-adapter-sdxl-canny
Modify images using canny edges
![](https://tjzk.replicate.delivery/models_models_cover_image/dd966190-cf47-44f5-89db-1dddc6bf17c6/object-removal.jpg)
sujaykhandekar/object-removal
Removes specified objects from image
![](https://pbxt.replicate.delivery/gK44xIViC3JgK52HohYGBndUX6iXBI54kTggoaxxBfcScQ1IA/out-0.png)
adirik/t2i-adapter-sdxl-sketch
Modify images using sketches
![](https://tjzk.replicate.delivery/models_models_featured_image/e91659f1-956d-4a39-b41d-a6aba0a2c53c/output1.jpeg)
lambdal/image-mixer
Image Mixer Stable Diffusion
![](https://tjzk.replicate.delivery/models_models_cover_image/da33dfd3-13cb-4c07-ab55-bcac2db484a7/Screenshot_from_2023-02-12_10-34-.png)
daanelson/plug_and_play_image_translation
Edit an image using features from diffusion models
![](https://replicate.delivery/pbxt/NZMUartw9GapO9wfD83IDxbaQN1hyA4NspaGcBOj40O0irOIA/reconstruction.png)
cjwbw/pix2pix-zero
Zero-shot Image-to-Image Translation
![](https://replicate.delivery/pbxt/aYXKkkuCWM6WN96DfeKBlVFTle875XmLLmMkJFp7rkNryqfHB/0.png)
adirik/kosmos-g
Kosmos-G: Generating Images in Context with Multimodal Large Language Models
![](https://replicate.delivery/mgxm/136f4904-fb3b-420f-83a5-29510b02c6ce/masked_image.png)
cjwbw/repaint
Inpainting using Denoising Diffusion Probabilistic Models
![](https://replicate.delivery/pbxt/09z14i0H7QZhDtBvCnC1WtH05GpU60ZEliQ3ZNRW4WqEf9fRA/output1.png)
adirik/masactrl-sdxl
Editable image generation with MasaCtrl-SDXL
![](https://replicate.delivery/pbxt/QCxSSQm9H8JpDRZ45fC7ftfRVLnW7zebTQooVzFemFfrGcinE/output.jpg)
adirik/stylemc
Text-guided image generation and editing
![](https://replicate.delivery/pbxt/P9bGwgTxx5LkOtOZot3tCDKUSjiyHIEQ5CjDvfcBL7IOJkfRA/result.png)
adirik/masactrl-stable-diffusion-v1-4
Edit real or generated images