Image Editing

You ever tried to inpaint smaller objects and details into an image? Can be kind of a hit or miss. SOEDiff has been specifically trained to handle these cases and can do a pretty good job at it.

DreamMix is a inpainting method based on the Fooocus model that can add objects from reference images and change their features using text.

SGEdit can add, remove, replace, and adjust objects in images while keeping the quality of the image consistent.

MagicQuill enables efficient image editing with a simple interface that lets users easily insert elements and change colors. It uses a large language model to understand editing intentions in real time, improving the quality of the results.

Face Anon can anonymize faces in images while keeping original facial expressions and head positions. It uses diffusion models to achieve high-quality image results and can also perform face swapping tasks.

ControlAR adds controls like edges, depths, and segmentation masks to autoregressive models like LlamaGen.

State of the art diffusion models are trained on square images. FiT is a new transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios (similar to what Sora does). This enables a flexible training strategy that effortlessly adapts to diverse aspect ratios during both training and inference phases, thus promoting resolution generalization and eliminating biases induced by image cropping.

Stable-Hair can robustly transfer a diverse range of real-world hairstyles onto user-provided faces for virtual hair try-on. It employs a two-stage pipeline that includes a Bald Converter for hair removal and specialized modules for high-fidelity hairstyle transfer.

DisEnvisioner can generate customized images from a single visual prompt and extra text instructions. It filters out irrelevant details and provides better image quality and speed without needing extra tuning.

UniPortrait can customize images of one or more people with high quality. It allows for detailed face editing and uses free-form text descriptions to guide changes.

OmniBooth can generate images with precise control over their layout and style. It allows users to customize images using masks and text or image guidance, making the process flexible and personal.

Love this one! SVGCustomization is a novel pipeline that is able to edit existing vector images with text prompts while preserving the properties and layer information vector images are made of.

Prompt Sliders can control and edit concepts in diffusion models. It allows users to adjust the strength of concepts with just 3KB of storage per embedding, making it much faster than traditional LoRA methods.

InstantDrag can edit images quickly using drag instructions without needing masks or text prompts. It learns motion dynamics with a two-network system, allowing for real-time, photo-realistic editing.

TurboEdit enables fast text-based image editing in just 3-4 diffusion steps! It improves edit quality and preserves the original image by using a shifted noise schedule and a pseudo-guidance approach, tackling issues like visual artifacts and weak edits.

CSGO can perform image-driven style transfer and text-driven stylized synthesis. It uses a large dataset with 210k image triplets to improve style control in image generation.

MagicFace can generate high-quality images of people in any style without needing extra training.

MagicFace can generate high-quality images of people in any style without needing training. It uses special attention methods for precise attribute alignment and feature injection, working for both single and multi-concept customization.

Generative Photomontage can combine parts of multiple AI-generated images using a brush tool. It enables the creation of new appearance combinations, correct shapes and artifacts, and improve prompt alignment, outperforming existing image blending methods.

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.