NovelAI / novelai-aspect-ratio-bucketingLinks
Implementation of aspect ratio bucketing for training generative image models as described in: https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac
☆390Updated 10 months ago
Alternatives and similar repositories for novelai-aspect-ratio-bucketing
Users that are interested in novelai-aspect-ratio-bucketing are comparing it to the libraries listed below
Sorting:
- Low-rank adaptation for Erasing COncepts from diffusion models.☆324Updated last year
- Train generative models with pytorch lightning☆331Updated 8 months ago
- Repo for my Tensorflow/Keras CV experiments. Mostly revolving around the Danbooru20xx dataset☆121Updated last year
- Merges two latent diffusion models at a user-defined ratio☆264Updated 2 years ago
- ☆244Updated 2 years ago
- Mixture of Diffusers for scene composition and high resolution image generation☆444Updated 2 years ago
- ☆115Updated last year
- ☆326Updated 2 years ago
- Implementation of "SVDiff: Compact Parameter Space for Diffusion Fine-Tuning"☆381Updated last year
- ControlLoRA: A Lightweight Neural Network To Control Stable Diffusion Spatial Information☆605Updated last year
- ☆118Updated 2 years ago
- Implementation of Paint-with-words with Stable Diffusion : method from eDiff-I that let you generate image from text-labeled segmentation…☆645Updated 2 years ago
- stable diffusion webui with contrastive prompt tuning☆870Updated 2 years ago
- DreamArtist for Stable-Diffusion-webui extension☆692Updated last year
- DAAM for Stable Diffusion Web UI☆174Updated last year
- Advanced fine tuning tools for vision models☆227Updated 2 years ago
- Adaptation of the merging method described in the paper - Git Re-Basin: Merging Models modulo Permutation Symmetries (https://arxiv.org/a…☆145Updated last year
- ☆321Updated 11 months ago
- A 99% automatized pipeline to construct training set from anime and more for text-to-image model training☆218Updated last year
- Personalization for Stable Diffusion via Aesthetic Gradients 🎨☆732Updated 2 years ago
- Pure pytorch implementation of DeepDanbooru☆129Updated last year
- Merge models with separate rate for each 25 U-Net block (input, middle, output). Extension for Stable Diffusion UI by AUTOMATIC1111☆321Updated last year
- ☆153Updated 2 years ago
- a CLI utility/library for AnimateDiff stable diffusion generation☆263Updated last week
- ☆231Updated 2 years ago
- ☆134Updated 2 years ago
- SigLIP-based Aesthetic Score Predictor☆304Updated 8 months ago
- Neural Rendering with Attention: An Incremental Improvement for Anime Character Animation☆418Updated 2 years ago
- Erasing Concepts from Diffusion Models☆630Updated last week
- ☆144Updated 2 years ago