lovisdotio / VidTrainPrepLinks
Python GUI tool for preparing video datasets (LORA, Wan, Hunyuan training). Features range clipping, cropping, FPS conversion & optional Gemini descriptions. (Enhanced refactor of HunyClip).
☆93Updated 6 months ago
Alternatives and similar repositories for VidTrainPrep
Users that are interested in VidTrainPrep are comparing it to the libraries listed below
Sorting:
- ☆71Updated last year
- Some Comfyui custom nodes for wan2.1 VACE, attempt to implement VACE video generation/editing in a better way.☆129Updated last month
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model☆54Updated 10 months ago
- A video clipper for Hunyuan video training.☆86Updated 5 months ago
- ☆52Updated 10 months ago
- Node and workflow profiling. Find bottlenecks in your workflows. See trends over time.☆69Updated 7 months ago
- ☆159Updated 9 months ago
- ☆53Updated 9 months ago
- ☆119Updated 7 months ago
- Hot reloading for custom node developers☆117Updated last year
- GUI for the new musubi-tuner☆51Updated 11 months ago
- ComfyUI implementation of FLATTEN☆110Updated last year
- ☆67Updated this week
- This node preserves image quality by selectively merging only the changed regions from AI-generated edits back into the original image.☆91Updated 4 months ago
- Divide and Conquer Node Suite☆114Updated last month
- ☆97Updated 4 months ago
- ComfyUI wrapper for StableX normal/delight models☆63Updated 10 months ago
- A Pinokio application to manage ComfyUI environments with Docker.☆89Updated last month
- A collection of custom nodes for ComfyUI.☆28Updated 6 months ago
- Simple GUI for training LoRA on Wan 2.1 models using musubi-tuner.☆39Updated 8 months ago
- ComfyUI wrapper for LVCD☆62Updated last year
- A custom ComfyUI node for interactive 360° panorama image previews.☆80Updated 7 months ago
- Kytra's MatAnyone implementation for use in ComfyUI☆145Updated 9 months ago
- A custom ComfyUI node designed to create seamless motion effects from single images by integrating with Hunyuan Video through latent spac…☆42Updated last year
- A repo to quantize diffusion models directly in ComfyUI☆97Updated 6 months ago
- Works similar to the Ultimate Upscaler except that uses Vision-Language Models to generate prompts for each tile. Plus a collection of o…☆56Updated 7 months ago
- A ComfyUI node implementation for ByteDance's Sa2VA☆92Updated last week
- ComfyUI nodes for Lotus depth/normal prediction☆158Updated last month
- ☆80Updated this week
- ☆66Updated 7 months ago