Image-to-Image

StoryMaker can generate a series of images with consistent characters across multiple images. It keeps the same facial features, clothing, hairstyles, and body types, allowing for cohesive storytelling.

MagicMan can generate high-quality 3D images and normal maps of humans from a single photo.

Text2Place can place any human or object realistically into diverse backgrounds. This enables scene hallucination by generating compatible scenes for the given pose of the human, text-based editing of the human and placing multiple persons into a scene.

Diffusion2GAN is a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference while preserving image quality. This enables one-step 512px/1024px image generation at an interactive speed of 0.09/0.16 second as well as 4k image upscaling!

tps-inbetween can generate high-quality intermediate frames for animation line art. It effectively connects lines and fills in missing details, even during fast movements, using a method that models keypoint relationships between frames.

Filtered Guided Diffusion shows that image-to-image translation and editing doesn’t necessarily require additional training. FGD simply applies a filter to the input of each diffusion step based on the output of the previous step in an adaptive manner which makes this approach easy to implement.

DreamMover can generate high-quality intermediate images and short videos from image pairs with large motion. It uses a flow estimator based on diffusion models to keep details and ensure consistency between frames and input images.

HairFastGAN can transfer hairstyles from one image to another in near real-time. It handles different poses and colors well, achieving high quality in under a second on an Nvidia V100.

CharacterFactory can generate endless characters that look the same across different images and videos. It uses GANs and word embeddings from celebrity names to ensure characters stay consistent, making it easy to integrate with other models.

MOWA is a multiple-in-one image warping model that can be used for various tasks such as rectangling panoramic images, unrolling shutter images, rotating images, fisheye images, and image retargeting.

[ControlNet++] can improve image generation by ensuring that generated images match the given controls, like segmentation masks and depth maps. It shows better performance than its predecessor, ControlNet, with improvements of 7.9% in mIoU, 13.4% in SSIM, and 7.6% in RMSE.

ID2Reflectance can generate high-quality facial reflectance maps from a single image.

Desigen can generate high-quality design templates, including background images and layout elements. It uses advanced diffusion models for better control and has been tested on over 40,000 advertisement banners, achieving results similar to human designers.

Intrinsic Image Diffusion can generate detailed albedo, roughness, and metallic maps from a single indoor scene image.

AnimeInbet is a method that is able to generate inbetween frames for cartoon line drawings. Seeing this, we’ll hopefully be blessed with higher framerate animes in the near future.

[Total Selfie] can generate high-quality full-body selfies from close-up selfies and background images. It uses a diffusion-based approach to combine these inputs, creating realistic images in desired poses and overcoming the limits of traditional selfies.

Scenimefy can turn real-world images and videos into high-quality anime scenes. It uses a smart method that keeps important details and produces better results than other tools.

Interpolating between Images with Diffusion Models can generate smooth transitions between two images using latent diffusion models. It allows for high-quality results across different styles and subjects while using CLIP to select the best images for interpolation.

CSD-Edit is a multi modality editing approach that compared to other methods works great on images bigger than the traditional 512x512 limitation and can edit 4k or large panorama images, has improved temporal consistency on video frames as well as improved view consistency when editing or generating 3D scenes.

Ray Conditioning is a lightweight and geometry-free technique for multi-view image generation. You have that perfect portrait shot of a face but the angle is not right? No problem, just use that shot as an input image and generate the portrait from a another angle. Done.