Home

Awesome

Awesome-AI-Generated-Image-Tasks

Awesome visitors

A collection of AI-generated images papers and corresponding source code/demo program, including text-to-image, image translation (e.g., text-, image, or other multimodality-guided), image inpainting, image colorization, and image editing.

Feel free to create a PR or an issue. (Pull Request is preferred)

Fig

Outline


1. Text-to-Image

PaperSourceCode/Project Link
High-Resolution Image Synthesis with Latent Diffusion ModelsCVPR 2022[project] [code]
Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingNeurIPS 2022[code]
GLIDE: towards photorealistic image generation and editing with text-guided diffusion modelsICML 2022[code]
LAFITE: Towards language-free training for text-to-image generationCVPR 2022[code]
Subject-diffusion: Open domain personalized text-to-image generation without test-time fine-tuningarxiv 2023[project] [code]
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained DiffusionICCV 2023[code]
Adding Conditional Control to Text-to-Image Diffusion ModelsICCV 2023[code]

2. Image Translation

PaperSourceCode/Project Link
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial NetworksICCV 2017[project] [code]
Image-to-Image Translation with Conditional Adversarial NetworksCVPR 2017[project] [code]
DeepFaceDrawing: Deep generation of face images from sketchesSIGGRAPH/TOG 2020[project] [code]
CoCosNet: Cross-domain Correspondence Learning for Exemplar-based Image TranslationCVPR 2020[project] [code]
CoCosNet v2: Full-Resolution Correspondence Learning for Image TranslationCVPR 2021[code]
StyleCLIP: Text-Driven Manipulation of StyleGAN ImageryICCV 2021[code]
Encoding in Style: a StyleGAN Encoder for Image-to-Image TranslationCVPR 2021[code]
RABIT: Bi-level Feature Alignment for Versatile Image Translation and ManipulationECCV 2022[code]
DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image GenerationECCV 2022[code]
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image ManipulationCVPR 2022[code]
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable and Controllable Text-Guided Face ManipulationSIGGRAPH 2023[project] [code]
Masked and Adaptive Transformer for Exemplar Based Image TranslationCVPR 2023[code]
Diffusion-based Image Translation using Disentangled Style and Content RepresentationICLR 2023[code]

3. Image Inpainting

PaperSourceCode/Project Link
RePaint: Inpainting using Denoising Diffusion Probabilistic ModelsCVPR 2022[code]
MAT: Mask-Aware Transformer for Large Hole Image InpaintingCVPR 2022[code]
Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image InpaintingCVPR 2023[project]
SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model CVPR 2023Not open-sourced

4. Image Colorization

PaperSourceCode/Project Link
Disentangled Image Colorization via Global AnchorsSIGGRAPH Asia/TOG 2022[project] [code] [demo]
BigColor:Colorization using a Generative Color Prior for Natural ImagesECCV 2022[code]
Unsupervised Deep Exemplar Colorization via Pyramid Dual Non-local AttentionTIP 2023[code]
DDColor: Towards Photo-Realistic Image Colorization via Dual DecodersICCV 2023[code] [demo]

5. Image Editing

PaperSourceCode/Project Link
User-Controllable Latent Transformer for StyleGAN Image Layout EditingComputer Graphics Forum 2022[code]
InstructPix2Pix: Learning to Follow Image Editing InstructionsCVPR 2023[code]
MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image EditingNeurIPS 2023[project] [code]
Diffusion Self-Guidance for Controllable Image GenerationNeurIPS 2023[project] [demo]
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image ManifoldSIGGRAPH 2023[project] [code]
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingarxiv 2023[code]
DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Modelsarxiv 2023[project] [code]
FreeDrag: Point Tracking is Not What You Need for Interactive Point-based Image Editingarxiv 2023[project] [code] [demo]