zhaowendao30
Follow
Stars
Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".
Diffusers pipeline for inpainting with any available finetune
Taming FLUX for Image Inversion & Editing; OpenSora for Video Inversion & Editing! (Official implementation for Taming Rectified Flow for Inversion and Editing.)
A powerful tool that translates ComfyUI workflows into executable Python code - now as a UI button.
A powerful tool that translates ComfyUI workflows into executable Python code.
AirLLM 70B inference with single 4GB GPU
A high-throughput and memory-efficient inference and serving engine for LLMs
Score identity Distillation with Long and Short Guidance for One-Step Text-to-Image Generation
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Official repository of In-Context LoRA for Diffusion Transformers
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
A connector to use ComfyUI in serverless deployments
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
SD.Next: All-in-one for AI generative image
Some awesome comfyui workflows in here, and they are built using the comfyui-easy-use node package.
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
Stable Diffusion and Flux in pure C/C++
Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.