Personalized Image Generation

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.

It’s been a while since I last doomed the TikTok dancers. MagicDance is gonna doom them some more. This model can combine human motion with reference images to precisely generate appearance-consistent videos. While the results still contain visible artifacts and jittering, give it a few months and I’m sure we can’t tell the difference no more.

FABRIC can condition diffusion models on feedback images to improve image quality. This method allows users to personalize content through multiple feedback rounds without needing training.

FastComposer can generate personalized images of multiple unseen individuals in various styles and actions without fine-tuning. It is 300x-2500x faster than traditional methods and requires no extra storage for new subjects, using subject embeddings and localized attention to keep identities clear.

LDMs are high-resolution image generators that can inpaint, generate images from text or bounding boxes, and do super-resolution.