advimman/lama Alternatives

choose if you want the AOT-GAN architecture for high-resolution inpainting instead of Fourier convolutions.

[TVCG'2023] AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)

choose if you want a transformer-based large-mask inpainting model.

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

choose if you need the older contextual-attention inpainting baseline in PyTorch.

A PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)

choose if you need the original 2016 context-encoder inpainting baseline for comparison.

[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs

choose if you need the partial-convolution baseline for irregular small holes.

Unofficial pytorch implementation of 'Image Inpainting for Irregular Holes Using Partial Convolutions' [Liu+, ECCV2018]

choose if you need the classic edge-guided image inpainting baseline.

EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212

choose if you need DeepFill v2 gated-convolution reference code.

DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

choose if you need a Keras implementation of partial-convolution inpainting.

Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai

choose if you need the pluralistic/multiple-plausible-completion inpainting method.

[CVPR 2019]: Pluralistic Image Completion

choose if you need an older patch-based high-res inpainting method in Lua.

High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis

choose if you need an efficient mobile-friendly image inpainting baseline.

[ICCV 2023] MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

choose if you want a self-hosted GUI application rather than a library to embed.

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

choose if you want a browser-based client-side inpainting app.

A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。| 基于 Webgpu 技术和 wasm 技术的免费开源 inpainting & image-upscaling 工具, 纯浏览器端实现。