[arXiv 2026] This is the official PyTorch implementation of "MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators".
[arXiv 2026] This is the official PyTorch implementation of "RTDMD: Reinforcing Few-step Generators via Reward-Tilted Distribution Matching".
[arXiv 2026] FlowBP: Exploring the Design Space of Reward Backpropagation for Flow Matching
WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.
Optimized LTXV workflows for ComfyUI
InvokeAI-Colab provides a simple setup to run the InvokeAI (Stable Diffusion) model on Google Colab.
A powerful and flexible custom node pack for ComfyUI, designed to eliminate boilerplate and keep your workflows clean and focused. From model loading to post-production — everything you need in one place.
To associate your repository with the sd35 topic, visit your repo's landing page and select "manage topics."