icandle
Follow
Starred repositories
176
stars
written in Python
Clear filter
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Train transformer language models with reinforcement learning.
Lets make video diffusion practical!
The ultimate training toolkit for finetuning diffusion models
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also …
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
SwinIR: Image Restoration Using Swin Transformer (official repository)
Count the MACs / FLOPs of your PyTorch model.
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
[WIP] Layer Diffusion for WebUI (via Forge)
[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
Efficient vision foundation models for high-resolution generation and perception.
[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.
🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...
The state-of-the-art image restoration model without nonlinear activation functions.
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
📹 A more flexible framework that can generate videos at any resolution and creates videos from images.
[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos