DataCTE / SDXL-Training-ImprovementsLinks
π Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stability & comprehensive monitoring. β Performance-focused research framework.
β18Updated 4 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:
- Adaptive ODE Solvers for ComfyUIβ48Updated 10 months ago
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!β42Updated last week
- Wildly unsound and experimental sampling for ComfyUIβ26Updated last week
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUIβ17Updated 5 months ago
- Somewhat janky implementation of Sonar Sampling (momentum based sampling) for ComfyUI along with an assortment of advanced noise tools (sβ¦β42Updated this week
- Janky implementation of DiffuseHigh for ComfyUIβ32Updated last month
- β56Updated last month
- Auto-MBW for ComfyUI loosely based on sdweb-auto-MBWβ14Updated last year
- Tools needed for training B-LoRA method with sd-scripts.β45Updated 9 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 10 months ago
- Create Latents with Perlin Noise in any shape (dimensionality). Works with Flux, SD3 and other 16d latent models.β34Updated 9 months ago
- This custom node for ComfyUI is designed to optimize latent generation for use with FLUX, SDXL and SD3 modes. It provides flexible controβ¦β32Updated 2 weeks ago
- it really is a skill issueβ33Updated 11 months ago
- A comprehensive codebase for training and finetuning Image <> Latent models.β35Updated 3 months ago
- β23Updated last year
- β19Updated 9 months ago
- Uses DARE to merge LoRA stacks as a ComfyUI nodeβ33Updated last year
- β25Updated 3 weeks ago
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".β34Updated 5 months ago
- Heuristic modification of the Heun sampler using normalized distances.β33Updated 3 weeks ago
- ComfyUI nodes to use APG scaling for CFGβ29Updated 7 months ago
- ComfyUI node to apply the ResAdapter Unet patch for SD1.5 modelsβ31Updated 3 months ago
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation modelβ53Updated 3 months ago
- ComfyUI unofficial implementation of Thera - Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fieldsβ35Updated last month
- Explore how Flux Dev responds when you change the strengths of layers in the model.β20Updated 8 months ago
- Gradio UI for training video models using finetrainersβ30Updated last month
- MoD Control Tile Upscaler for SDXL Pipelineβ58Updated 2 months ago
- Data research, preparation, and manipulation nodes for model trainers and artists.β49Updated 3 months ago
- ComfyUI powertools for SD1.5 and SDXL model mergingβ86Updated 2 months ago
- Modifications to ComfyUI diffusers wrapper node X-Adapter to make it more ComfyUI-node-likeβ23Updated 11 months ago