Finetune the 1.4B latent diffusion text2img-large checkpoint from CompVis using deepspeed. (work-in-progress)

1.4B latent diffusion model fine tuning

Audio generation using diffusion models, in PyTorch.

Home of `erlich` and `ongo`. Finetune latent-diffusion/glid-3-xl text2image on your own data.

Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.

Robust fine-tuning of zero-shot models

Official Source code of "One-Shot Adaptation of GAN in Just One CLIP" IEEE Transactions on Pattern Anaylsis and Machine Intelligence (TPAMI)

The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"

Ensembling Off-the-shelf Models for GAN Training (CVPR 2022 Oral)

Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" (ACM TOG 2022) https://arxiv.org/abs/2106.05744

[CVPR 2022] Official PyTorch Implementation for DiffusionCLIP: Text-guided Image Manipulation Using Diffusion Models

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Prefix-Tuning: Optimizing Continuous Prompts for Generation

[CVPR 2022 Oral] Official implementation of DN-DETR

Visual Taste Approximator (VTA) is a very simple tool that helps anyone create an automatic replica of themselves that can approximate their own personal visual taste

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

Multi-modality pre-training

Train vision models using JAX and 🤗 transformers

Metric learning and retrieval pipelines, models and zoo.

Official Implementation for "HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks" (NeurIPS 2022)

A python library for self-supervised learning on images.

Code repository for the paper "Meta-Learning via Classifier(-free) Diffusion Guidance"