lodestone-rock / torchasticLinks
stochastic bfloat16 based optimizer library
☆21Updated last year
Alternatives and similar repositories for torchastic
Users that are interested in torchastic are comparing it to the libraries listed below
Sorting:
- Model code for inferencing T5☆66Updated 9 months ago
- A comprehensive codebase for training and finetuning Image <> Latent models.☆48Updated 9 months ago
- ☆19Updated last year
- A collection of niche / personally useful PyTorch optimizers with modified code.☆27Updated last month
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆111Updated 2 weeks ago
- ☆33Updated last year
- MoD Control Tile Upscaler for SDXL Pipeline☆61Updated 9 months ago
- ☆112Updated 7 months ago
- ☆165Updated 2 weeks ago
- 📊 Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stabi…☆20Updated 6 months ago
- ComfyUI powertools for SD1.5 and SDXL model merging☆94Updated 8 months ago
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".☆34Updated last year
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUI☆17Updated last year
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!☆48Updated 6 months ago
- This is a ComfyUI node that integrates pruna☆65Updated 3 months ago
- ☆20Updated last year
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆63Updated 9 months ago
- ☆46Updated 3 weeks ago
- A system for Prompt generation to improve Text-to-Image performance.☆86Updated 2 weeks ago
- Official implementation of "Normalized Attention Guidance"☆173Updated 5 months ago
- ComfyUI implementation of the paper https://arxiv.org/pdf/2410.02416 "APG".☆35Updated last year
- Adaptive ODE Solvers for ComfyUI☆53Updated last year
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideo☆22Updated 2 months ago
- ☆43Updated last year
- Scale-wise Distillation of Diffusion Models☆112Updated 2 months ago
- Janky implementation of DiffuseHigh for ComfyUI☆36Updated 7 months ago
- Create Latents with Perlin Noise in any shape (dimensionality). Works with Flux, SD3 and other 16d latent models.☆34Updated last year
- ☆14Updated last year
- Wildly unsound and experimental sampling for ComfyUI☆28Updated 4 months ago
- it really is a skill issue☆34Updated last year