Personalized Image Generation

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.

TweedieMix can generate images and videos that combine multiple personalized concepts.

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.

ProCreate boosts the diversity and creativity of diffusion-based image generation while avoiding the replication of training data. By pushing generated image embeddings away from reference images, it improves the quality of samples and lowers the risk of copying copyrighted content.

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.

TextBoost can enable one-shot personalization of text-to-image models by fine-tuning the text encoder. It generates diverse images from a single reference image while reducing overfitting and memory needs.

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.

ViPer can personalize image generation by capturing individual user preferences through a one-time commenting process on a selection of images. It utilizes these preferences to guide a text-to-image model, resulting in generated images that align closely with users’ visual tastes.

MasterWeaver can generate photo-realistic images from a single reference image while keeping the person’s identity and allowing for easy edits. It uses an encoder to capture identity features and a unique editing direction loss to improve text control, enabling changes to clothing, accessories, and facial features.

IMAGDressing-v1 can generate human try-on images from input garments. It is able to control different scenes through text and can be combined with IP-Adapter and ControlNet pose to enhance the diversity and controllability of generated images.

DMD2 is a new improved distillation method that can turn diffusion models into efficient one-step image generators.

RectifID is yet another personalization method from user-provided reference images of human faces, live subjects, and certain objects for diffusion models.

ConsistentID can generate diverse personalized ID images from text prompts using just one reference image. It improves identity preservation with a facial prompt generator and an ID-preservation network, ensuring high quality and variety in the generated images.

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.

Parts2Whole can generate customized human portraits from multiple reference images, including pose images and various aspects of human appearance. The method is able to generate human images conditioned on selected parts from different humans as control conditions, allowing you to create images with specific combinations of facial features, hair, clothes, etc.

FlashFace can personalize photos by using one or a few reference face images and a text prompt. It keeps important details like scars and tattoos while balancing text and image guidance, making it useful for face swapping and turning virtual characters into real people.

StableIdentity is a method that can generate diverse customized images in various contexts from a single input image. The cool thing about this method is, that it is able to combine the learned identity with ControlNet and even inject it into video (ModelScope) and 3D (LucidDreamer) generation.

InstantID is a ID embedding-based method that can be used to personalize images in various styles using just a single facial image, while ensuring high fidelity.

Custom Diffusion can quickly fine-tune text-to-image diffusion models to generate new variations from just a few examples in about 6 minutes on 2 A100 GPUs. It allows for the combination of multiple concepts and requires only 75MB of storage for each additional model, which can be compressed to 5-15MB.