KohakuBlueleaf / MinDiff
Some minimal implementation of some Diffusion Models. Try to use as less code and as simple arch as possible
☆20Updated 4 months ago
Alternatives and similar repositories for MinDiff
Users that are interested in MinDiff are comparing it to the libraries listed below
Sorting:
- This package introduces a perceptual loss implementation based on the modern ConvNeXt architecture.☆13Updated 6 months ago
- A comprehensive codebase for training and finetuning Image <> Latent models.☆33Updated 2 months ago
- Prodigy and Schedule-Free, together at last.☆55Updated this week
- Understand Human Behavior to Align True Needs☆22Updated 10 months ago
- Crawler and cleaner of data for novelai embedding's training☆20Updated last month
- Swiftly get tons of images from indexed tars on Huggingface☆56Updated 5 months ago
- A system for Prompt generation to improve Text-to-Image performance.☆78Updated 2 months ago
- Model code for inferencing T5☆64Updated 2 months ago
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUI☆17Updated 5 months ago
- text-image dataset maker for anime-style images☆98Updated 2 months ago
- ☆19Updated 9 months ago
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".☆34Updated 5 months ago
- Multimodal captioner☆118Updated this week
- A tool to easily modify a Stable Diffusion VAE☆84Updated 2 years ago
- ComfyUI implementation of the paper https://arxiv.org/pdf/2410.02416 "APG".☆32Updated 5 months ago
- Executable State Dict Recipes☆65Updated this week
- ComfyUI node of DTG☆64Updated 9 months ago
- Uses DARE to merge LoRA stacks as a ComfyUI node☆31Updated 11 months ago
- Diffusers Implementation of Controlling Text-to-Image Diffusion by Orthogonal Finetuning☆35Updated last year
- Tools needed for training B-LoRA method with sd-scripts.☆44Updated 9 months ago
- Evaluation for stable diffusion model training☆25Updated 8 months ago
- ☆50Updated last year
- Greatly increase the diversity of your generated images in Automatic1111 WebUI through Condition-Annealed Sampling.☆105Updated last year
- ☆44Updated 4 months ago
- ☆73Updated last year
- ComfyUI nodes to use APG scaling for CFG☆29Updated 7 months ago
- Tiny AutoEncoder for Hunyuan Video & Wan 2.1☆45Updated last month
- ComfyUI powertools for SD1.5 and SDXL model merging☆85Updated last month
- ☆13Updated 3 months ago
- ☆55Updated 2 weeks ago