DataCTE / SDXL-Training-ImprovementsLinks
š Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stability & comprehensive monitoring. ā Performance-focused research framework.
ā20Updated 6 months ago
Alternatives and similar repositories for SDXL-Training-Improvements
Users that are interested in SDXL-Training-Improvements are comparing it to the libraries listed below
Sorting:
- Janky implementation of DiffuseHigh for ComfyUIā36Updated 7 months ago
- Adaptive ODE Solvers for ComfyUIā53Updated last year
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!ā48Updated 6 months ago
- MoD Control Tile Upscaler for SDXL Pipelineā61Updated 9 months ago
- ā53Updated 9 months ago
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".ā34Updated last year
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUIā17Updated last year
- Somewhat janky implementation of Sonar Sampling (momentum based sampling) for ComfyUI along with an assortment of advanced noise tools (sā¦ā47Updated 4 months ago
- Loop your image from output to input in your ComfyUI workflowā12Updated last month
- Allows to sample without generating any uncond with Stable Diffusion!ā51Updated last year
- Gradio UI for training video models using finetrainersā33Updated 7 months ago
- ā63Updated 7 months ago
- Heuristic modification of the Heun sampler using normalized distances.ā41Updated 5 months ago
- ComfyUI powertools for SD1.5 and SDXL model mergingā94Updated 8 months ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIPā63Updated 9 months ago
- ComfyUI unofficial implementation of Thera - Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fieldsā35Updated 7 months ago
- Wildly unsound and experimental sampling for ComfyUIā28Updated 4 months ago
- Batched Runge-Kutta Samplers for ComfyUIā63Updated last year
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideo