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.
β20Updated 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
Sorting:
- Janky implementation of DiffuseHigh for ComfyUIβ36Updated 4 months ago
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!β47Updated 3 months ago
- MoD Control Tile Upscaler for SDXL Pipelineβ61Updated 6 months ago
- Somewhat janky implementation of Sonar Sampling (momentum based sampling) for ComfyUI along with an assortment of advanced noise tools (sβ¦β47Updated last month
- Adaptive ODE Solvers for ComfyUIβ52Updated last year
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".β34Updated 9 months ago
- RadialAttention in ComfyUI native workflowβ68Updated 2 weeks ago
- β61Updated 4 months ago
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUIβ17Updated 9 months ago
- Allows to sample without generating any uncond with Stable Diffusion!β50Updated last year
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideoβ21Updated 5 months ago
- Modifications to ComfyUI diffusers wrapper node X-Adapter to make it more ComfyUI-node-likeβ23Updated last year
- A collection of niche / personally useful PyTorch optimizers with modified code.β25Updated 2 months ago
- Batched Runge-Kutta Samplers for ComfyUIβ62Updated last year
- Explore how Flux Dev responds when you change the strengths of layers in the model.β21Updated last year
- Gradio UI for training video models using finetrainersβ31Updated 5 months ago
- ComfyUI for XLA devices for TPUs/GPUsβ20Updated 9 months ago
- ComfyUI unofficial implementation of Thera - Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fieldsβ35Updated 4 months ago
- ComfyUI powertools for SD1.5 and SDXL model mergingβ93Updated 5 months ago
- Model code for inferencing T5β66Updated 6 months ago
- Wildly unsound and experimental sampling for ComfyUIβ28Updated last month
- Provides the ability to set the temperature for both UNET and CLIP. For ComfyUI. Has for side effect to improve non-native resolutions.β43Updated last year
- Create Latents with Perlin Noise in any shape (dimensionality). Works with Flux, SD3 and other 16d latent models.β34Updated last year
- This custom node for ComfyUI is designed to optimize latent generation for use with FLUX, Qwen, SDXL, SD3 and WAN modes. It provides flexβ¦β44Updated 2 weeks ago
- custom plugins for comfyUIβ59Updated last month
- Auto-MBW for ComfyUI loosely based on sdweb-auto-MBWβ16Updated last year
- Heuristic modification of the Heun sampler using normalized distances.β39Updated 3 months ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIPβ62Updated 6 months ago
- β38Updated last year
- A custom node for ComfyUI that adds cinematic and movie scene styles to video generation prompts. This node helps create more dynamic andβ¦β45Updated 8 months ago