LightDiffusion / LightDiffusion-Next
LightDiffusion SD and Flux refactored. Reassembled to support and be the fastest SD and Flux natively π
β43Updated 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 ComfyUIβ65Updated 3 months ago
- β110Updated last month
- Text Encoders finally matter π€π₯ - scale CLIP & LLM influence! + a Nerdy Transformer Shuffle nodeβ65Updated 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 sβ¦β53Updated 5 months ago
- A set of nodes to edit videos using the Hunyuan Video modelβ43Updated last month
- ComfyUI Qwen2.5VL and Qwen2.5 wrapperβ62Updated last month
- An image viewer and AI-assisted editing/captioning/masking tool that helps with curating datasets for generative AI models, finetunes andβ¦β107Updated this week
- [legacy repository]β50Updated 2 months ago
- flux distillation and stuffβ64Updated last week
- ComfyUI Wrapper for HiDream - 4bit linux loading fixβ83Updated last week
- Nodes for ComfyUI to simply workflowsβ60Updated this week
- Janky implementation of HiDiffusion for ComfyUIβ119Updated 4 months ago
- ComfyUI wrapper for Kokoro-onnxβ34Updated 3 months ago
- ComfyUI-FreeMemory is a custom node extension for ComfyUI that provides memory management capabilities within your image generation workfβ¦β94Updated last month
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation modelβ38Updated last month
- it really is a skill issueβ32Updated 10 months ago
- Makes creating new nodes for ComfyUI a breeze.β107Updated 4 months ago
- Run Local and API LLMs, Features Gemini2 image generation, DEEPSEEK R1, QwenVL2.5, QWQ32B, Ollama, LlamaCPP LMstudio, Koboldcpp, TextGen,β¦β112Updated 2 weeks ago
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideoβ17Updated 2 weeks ago
- Canvas to use with ComfyUIβ85Updated 4 months ago
- Fixed Attention Couple, NegPip(negative weights in prompts) for SDXL, FLUX and HunyuanVideo, more CFG++ and SMEA DY samplers, etc.β168Updated last week
- Hot reloading for custom node developersβ78Updated 7 months ago
- β106Updated this week
- β44Updated 2 months ago
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation modelβ53Updated last month
- Superprompt a 77M Parameter T5 custom trained checkpoint to make dull prompts detailed.β68Updated 11 months ago
- Executable Stable Diffusion merge recipes in comfyuiβ73Updated 2 weeks ago
- A custom ComfyUI node designed to create seamless motion effects from single images by integrating with Hunyuan Video through latent spacβ¦β40Updated 3 months ago
- β91Updated 10 months ago
- Official Implementation of Attention Distillation for ComfyUIβ107Updated last month