Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

Offical implementation of work: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Official Implementation of 'ReliableSwap: Boosting General Face Swapping Via Reliable Supervision'

(CVPR 2023) E4S: Fine-grained Face Swapping via Regional GAN Inversion

An arbitrary face-swapping framework on images and videos with one single trained model!

Unofficial PyTorch Implementation for FaceShifter (https://arxiv.org/abs/1912.13457)

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Official inference repo for FLUX.1 models

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

Google collab version for Follow-Your-Emoji

[Siggraph Asia 2024] Follow-Your-Emoji: This repo is the official implementation of "Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation"

[ECCV 2024] Official repository for "3D Gaussian Parametric Head Model"

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Create images of a given character in different poses

InstantID-ROME: Improved Identity-Preserving Generation in Seconds 🔥

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)

[NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

naive filter of objaverse

Open-Sora: Democratizing Efficient Video Production for All

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation