zishen-ucap / PromptTeaLinks
This repository contains the official implementation of our paper: PromptTea: Let Prompts Tell TeaCache the Optimal Threshold
☆33Updated last month
Alternatives and similar repositories for PromptTea
Users that are interested in PromptTea are comparing it to the libraries listed below
Sorting:
- ☆71Updated 11 months ago
- ☆49Updated last week
- A ComfyUI wrapper for Diffusion Self Distillation (DSD) - Zero-Shot Customized Image Generation☆41Updated 6 months ago
- Official Implementation of Attention Distillation for ComfyUI☆110Updated 6 months ago
- Python GUI tool for preparing video datasets (LORA, Wan, Hunyuan training). Features range clipping, cropping, FPS conversion & optional …☆87Updated 4 months ago
- A wrapper of Craftsman for Comfyui☆17Updated 5 months ago
- ☆66Updated 4 months ago
- ☆71Updated this week
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model☆54Updated 7 months ago
- A repo to quantize diffusion models directly in ComfyUI☆76Updated 3 months ago
- High-Quality Text-to-Video Generation with Alpha Channel☆110Updated this week
- ☆53Updated 7 months ago
- ☆76Updated 5 months ago
- A set of nodes to edit videos using the Hunyuan Video model☆49Updated 7 months ago
- Interactive levels adjustment node for ComfyUI that provides a real-time levels adjustment tool directly within the user interface. It al…☆37Updated last month
- Mel-Band RoFormer for Music Source Separation☆58Updated last month
- ComfyUI custom node for lightx2v☆41Updated this week
- Some Comfyui custom nodes for wan2.1 VACE, attempt to implement VACE video generation/editing in a better way.☆118Updated last month
- Hot reloading for custom node developers☆114Updated last year
- ☆30Updated last month
- ComfyUI nodes to edit videos using Genmo Mochi☆23Updated 11 months ago
- This node preserves image quality by selectively merging only the changed regions from AI-generated edits back into the original image.☆85Updated last month
- A custom ComfyUI node designed to create seamless motion effects from single images by integrating with Hunyuan Video through latent spac…☆42Updated 9 months ago
- Official implementation of "Normalized Attention Guidance"☆166Updated 3 months ago
- ☆32Updated last month
- A ComfyUI extention for BAGEL(Unified Model for Multimodal Understanding and Generation)☆184Updated last week
- Text Encoders finally matter 🤖🎥 - scale CLIP & LLM influence! + a Nerdy Transformer Shuffle node☆67Updated 8 months ago
- Image to text with CLIP ViT-L/14 in ComfyUI☆58Updated 9 months ago
- ☆117Updated 4 months ago
- ☆70Updated 3 months ago