DataCTE / SDXL-Training-Improvements
š Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stability & comprehensive monitoring. ā Performance-focused research framework.
ā19Updated 3 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
- Adaptive ODE Solvers for ComfyUIā49Updated 9 months ago
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUIā17Updated 4 months ago
- Gradio UI for training video models using finetrainersā27Updated 2 weeks ago
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideoā17Updated 3 weeks ago
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!ā41Updated last month
- Janky implementation of DiffuseHigh for ComfyUIā32Updated 3 months ago
- MoD Control Tile Upscaler for SDXL Pipelineā54Updated last month
- Heuristic modification of the Heun sampler using normalized distances.ā25Updated last week
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".ā33Updated 4 months ago
- Wildly unsound and experimental sampling for ComfyUIā26Updated 2 months ago
- Somewhat janky implementation of Sonar Sampling (momentum based sampling) for ComfyUI along with an assortment of advanced noise tools (sā¦ā40Updated 2 months ago
- ComfyUI nodes to use APG scaling for CFGā29Updated 7 months ago
- Provides the ability to set the temperature for both UNET and CLIP. For ComfyUI. Has for side effect to improve non-native resolutions.ā43Updated 9 months ago
- ā54Updated 2 months ago
- ComfyUI unofficial implementation of Thera - Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fieldsā34Updated this week
- Create Latents with Perlin Noise in any shape (dimensionality). Works with Flux, SD3 and other 16d latent models.ā34Updated 9 months ago
- Auto-MBW for ComfyUI loosely based on sdweb-auto-MBWā16Updated 11 months ago
- ā23Updated last year
- Allows to sample without generating any uncond with Stable Diffusion!ā47Updated 9 months ago
- ComfyUI node to apply the ResAdapter Unet patch for SD1.5 modelsā31Updated 2 months ago
- ā19Updated 8 months ago
- ComfyUI implementation of the paper https://arxiv.org/pdf/2410.02416 "APG".ā32Updated 5 months ago
- Uses DARE to merge LoRA stacks as a ComfyUI nodeā32Updated 11 months ago
- Experimental implementation of CADS for ComfyUIā41Updated this week
- H1111 --- GUI for Video Modelsā47Updated this week
- ā44Updated 4 months ago
- stochastic bfloat16 based optimizer libraryā13Updated 5 months ago
- A comfyui node that uses the loop function to process images and masksā32Updated last month
- ā46Updated last year
- Understand Human Behavior to Align True Needsā22Updated 9 months ago