DataCTE / SDXL-Training-Improvements
π Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stability & comprehensive monitoring. β Performance-focused research framework.
β19Updated 2 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 ComfyUIβ48Updated 7 months ago
- Create Latents with Perlin Noise in any shape (dimensionality). Works with Flux, SD3 and other 16d latent models.β34Updated 7 months ago
- Gradio UI for training video models using finetrainersβ26Updated this week
- β53Updated 3 weeks ago
- custom plugins for comfyUIβ52Updated 3 months ago
- Allows to sample without generating any uncond with Stable Diffusion!β45Updated 8 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.β43Updated 8 months ago
- ComfyUI nodes to use APG scaling for CFGβ29Updated 5 months ago
- Somewhat janky implementation of Sonar Sampling (momentum based sampling) for ComfyUI along with an assortment of advanced noise tools (sβ¦β40Updated 2 weeks ago
- Janky implementation of DiffuseHigh for ComfyUIβ23Updated 2 months ago
- flux distillation and stuffβ56Updated last week
- Modifications to ComfyUI diffusers wrapper node X-Adapter to make it more ComfyUI-node-likeβ22Updated 8 months ago
- Executable Stable Diffusion merge recipes in comfyuiβ67Updated 3 weeks ago
- Tools needed for training B-LoRA method with sd-scripts.β42Updated 7 months ago
- β23Updated last year
- β39Updated 10 months ago
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUIβ17Updated 3 months ago
- Auto-MBW for ComfyUI loosely based on sdweb-auto-MBWβ16Updated 10 months ago
- β46Updated 11 months ago
- A custom node for ComfyUI that adds cinematic and movie scene styles to video generation prompts. This node helps create more dynamic andβ¦β40Updated 2 months ago
- Allows native usage of ModelScope based Text To Video Models in ComfyUIβ26Updated 10 months ago
- it really is a skill issueβ32Updated 9 months ago
- β42Updated last year
- Wildly unsound and experimental sampling for ComfyUIβ26Updated last month