艾梦

ControlLoRA. ControlLoRA: A Lightweight Neural Network To Control Stable Diffusion Spatial Information

anime_biggan_toy. Generate Amazing Anime Pictures With BigGAN. Just Have Fun !!!

control-lora-v2. ControlLoRA Version 2: A Lightweight Neural Network To Control Stable Diffusion Spatial Information Version 2

control-lora-v3. ControlLoRA Version 3: LoRA Is All You Need to Control the Spatial Information of Stable Diffusion.

waifu2x-tfjs. Image super-resolution using Tensorflow.js .

pixel-guide-diffusion-for-anime-colorization. Use denoising diffusion probabilistic model to do the anime colorization task.

EasyOCR. Java OCR 识别组件（历史找回版本，基于Tesseract OCR 引擎）。能自动完成图片清理、识别 CAPTCHA 验证码图片内容的一体化工作。Java Image cleanup, OCR recognition component (based Tesseract OCR engine, automatically cleanup image and identification CAPTCHA verification code picture content).

stylegan2-faceapp. Try to use stylegan2 to achieve some facial special effects, still under construction

flux-4bit. Jupyter Notebook

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

keras-bert-tpu. Implementation of BERT that could load official pre-trained models for feature extraction and prediction on TPU

starganv2vc-paddle. Python

stylegan2-pytorch2paddle. Convert StyleGAN2 PyTorch to PaddlePaddle

face_morpher_plus. Face morpher plus based on facemorpher

rwkv-paddle. Python

denoising-diffusion-paddle. Implementation of Denoising Diffusion Probabilistic Models in PaddlePaddle

Condition-StyleGAN-PyTorch. A fork

DECA-Paddle-Inference. Python

SelfGAN. My pytorch implementation of 'SelfGAN--Not A GAN But Punch Itself'.

DiffSinger-ONNX-Infer. DiffSinger ONNX Inference

ddim. Denoising Diffusion Implicit Models

stylegan2-paddle. Simplest working implementation of Stylegan2 in PaddlePaddle. Enabling everyone to experience disentanglement

beat-interpolator. Interpolate the latents of your DL model to follow the beat of the music

PaddleSpeech. Easy-to-use Speech Toolkit including SOTA/Streaming ASR with punctuation, influential TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

gan. some demo of GANs

embformer. Embformer: An Embedding-Weight-Only Transformer Architecture

PaddleGAN. PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

taming-transformers. Jupyter Notebook

DECA. DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

godot. Godot Engine – Multi-platform 2D and 3D game engine

onnxruntime. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

import_daz. Forked from https://bitbucket.org/Diffeomorphic/import_daz