simongao's repositories
ControlNet_TensorRT
天池 NVIDIA TensorRT Hackathon 2023 —— 生成式AI模型优化赛 初赛第三名方案
Diff2X
Memory efficient sliding-window upscaling based on iterative refinement
Dilated-Convolution-with-Learnable-Spacings-PyTorch
[ICLR 2023] "Dilated convolution with learnable spacings" Ismail Khalfaoui Hassani, Thomas Pellegrini and Timothée Masquelier
distill-sd
Segmind Distilled diffusion
distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
DynamiCrafter
DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
FastSDXL
An efficient implementation of Stable-Diffusion-XL
FreeDoM
[ICCV 2023] Official PyTorch implementation for the paper "FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model"
img2img-turbo
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
keras-io
Keras documentation, hosted live at keras.io
Metodos-Numericos
Librería de métodos numéricos en C++
minSDXL
Huggingface-compatible SDXL Unet implementation that is readily hackable
ODConv
The official project website of "Omni-Dimensional Dynamic Convolution" (ODConv for short, spotlight in ICLR 2022).
OnnxStream
Running Stable Diffusion on a RPI Zero 2 (or in 260MB of RAM)
patch_conv
Patch convolution to avoid large GPU memory usage of Conv2D
qf-map-generator
An Overhead-Free Region-Based JPEG Framework for Task-Driven Image Compression
S2D2
S2D2: Simple Stable Diffusion based on Diffusers (Hires.fix on jupyter notebook, ipython or python interactive shell)
sam-hq
Segment Anything in High Quality
sd-webui-fastblend
Make videos smooth!
SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
stable-diffusion-webui
Stable Diffusion web UI
StableSR
Exploiting Diffusion Prior for Real-World Image Super-Resolution
SyncTalk
[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"
tokenizers-cpp
Universal tokenizer binding to HF and sentencepiece
Tri-RMSNorm
Efficient kernel for RMS normalization with fused operations, includes both forward and backward passes, compatibility with PyTorch.
VideoFlow
Official implementation of ICCV2023 VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
visual-concept-translator
Code of ICCV 2023 paper titled General Image-to-Image Translation with One-Shot Image Guidance
zest_code
This is the official implementation of ZeST