LightDiffusion / LightDiffusion-Next
LightDiffusion SD and Flux refactored. Reassembled to support and be the fastest SD and Flux natively 🚀
☆43Updated last month
Alternatives and similar repositories for LightDiffusion-Next:
Users that are interested in LightDiffusion-Next are comparing it to the libraries listed below
- NNT Neural Network Toolkit Custom Nodes for ComfyUI☆65Updated 3 months ago
- ☆110Updated last month
- Text Encoders finally matter 🤖🎥 - scale CLIP & LLM influence! + a Nerdy Transformer Shuffle node☆65Updated 3 months ago
- Processes SafeTensors files for Stable Diffusion 1.5 (SD 1.5), Stable Diffusion XL (SDXL), and FLUX models. It extracts the UNet into a s…☆53Updated 5 months ago
- A set of nodes to edit videos using the Hunyuan Video model☆43Updated last month
- ComfyUI Qwen2.5VL and Qwen2.5 wrapper☆62Updated last month
- An image viewer and AI-assisted editing/captioning/masking tool that helps with curating datasets for generative AI models, finetunes and…☆107Updated this week
- [legacy repository]☆50Updated 2 months ago
- flux distillation and stuff☆64Updated last week
- ComfyUI Wrapper for HiDream - 4bit linux loading fix☆83Updated last week
- Nodes for ComfyUI to simply workflows☆60Updated this week
- Janky implementation of HiDiffusion for ComfyUI☆119Updated 4 months ago
- ComfyUI wrapper for Kokoro-onnx☆34Updated 3 months ago
- ComfyUI-FreeMemory is a custom node extension for ComfyUI that provides memory management capabilities within your image generation workf…☆94Updated last month
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model☆38Updated last month
- it really is a skill issue☆32Updated 10 months ago
- Makes creating new nodes for ComfyUI a breeze.☆107Updated 4 months ago
- Run Local and API LLMs, Features Gemini2 image generation, DEEPSEEK R1, QwenVL2.5, QWQ32B, Ollama, LlamaCPP LMstudio, Koboldcpp, TextGen,…☆112Updated 2 weeks ago
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideo☆17Updated 2 weeks ago
- Canvas to use with ComfyUI☆85Updated 4 months ago
- Fixed Attention Couple, NegPip(negative weights in prompts) for SDXL, FLUX and HunyuanVideo, more CFG++ and SMEA DY samplers, etc.☆168Updated last week
- Hot reloading for custom node developers☆78Updated 7 months ago
- ☆106Updated this week
- ☆44Updated 2 months ago
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model☆53Updated last month
- Superprompt a 77M Parameter T5 custom trained checkpoint to make dull prompts detailed.☆68Updated 11 months ago
- Executable Stable Diffusion merge recipes in comfyui☆73Updated 2 weeks ago
- A custom ComfyUI node designed to create seamless motion effects from single images by integrating with Hunyuan Video through latent spac…☆40Updated 3 months ago
- ☆91Updated 10 months ago
- Official Implementation of Attention Distillation for ComfyUI☆107Updated last month