lodestone-rock / torchasticLinks
stochastic bfloat16 based optimizer library
☆20Updated last year
Alternatives and similar repositories for torchastic
Users that are interested in torchastic are comparing it to the libraries listed below
Sorting:
- A comprehensive codebase for training and finetuning Image <> Latent models.☆49Updated 11 months ago
- Model code for inferencing T5☆66Updated 11 months ago
- ☆19Updated last year
- A collection of niche / personally useful PyTorch optimizers with modified code.☆27Updated 3 months ago
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUI☆17Updated last year
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆114Updated 2 months ago
- MoD Control Tile Upscaler for SDXL Pipeline☆61Updated 11 months ago
- ☆33Updated last year
- ComfyUI powertools for SD1.5 and SDXL model merging☆94Updated 10 months ago
- ComfyUI implementation of the paper https://arxiv.org/pdf/2410.02416 "APG".☆34Updated last year
- ☆167Updated this week
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".☆34Updated last year
- Janky implementation of DiffuseHigh for ComfyUI☆36Updated 9 months ago
- Home Made Diffusion Models☆187Updated 2 months ago
- ☆44Updated last year
- A system for Prompt generation to improve Text-to-Image performance.☆90Updated last week
- Adaptive ODE Solvers for ComfyUI☆54Updated last year
- Gradio UI for training video models using finetrainers☆33Updated 9 months ago
- Prodigy and Schedule-Free, together at last.☆85Updated 4 months ago
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideo☆22Updated 4 months ago
- ☆32Updated last year
- Token Downsampling optimization for stable-diffusion-webui☆26Updated last year
- ComfyUI for XLA devices for TPUs/GPUs☆22Updated last year
- 📊 Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stabi…☆21Updated 8 months ago
- This is a ComfyUI node that integrates pruna☆65Updated 5 months ago
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!☆47Updated 8 months ago
- This extension provides inference-time optimization techniques to enhance diffusion-based image generation quality through random search …☆23Updated 11 months ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆63Updated 11 months ago
- Executable State Dict Recipes☆79Updated 2 weeks ago
- ☆43Updated last year