DataCTE / SDXL-Training-ImprovementsLinks
📊 Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stability & comprehensive monitoring. ⭐ Performance-focused research framework.
☆20Updated 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 ComfyUI☆36Updated 4 months ago
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!☆47Updated 3 months ago
- MoD Control Tile Upscaler for SDXL Pipeline☆61Updated 6 months ago
- Somewhat janky implementation of Sonar Sampling (momentum based sampling) for ComfyUI along with an assortment of advanced noise tools (s…☆47Updated last month
- Adaptive ODE Solvers for ComfyUI☆52Updated last year
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".☆34Updated 9 months ago
- RadialAttention in ComfyUI native workflow☆68Updated 2 weeks ago
- ☆61Updated 4 months ago
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUI☆17Updated 9 months ago
- Allows to sample without generating any uncond with Stable Diffusion!☆50Updated last year
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideo☆21Updated 5 months ago
- Modifications to ComfyUI diffusers wrapper node X-Adapter to make it more ComfyUI-node-like☆23Updated last year
- A collection of niche / personally useful PyTorch optimizers with modified code.☆25Updated 2 months ago
- Batched Runge-Kutta Samplers for ComfyUI☆62Updated last year
- Explore how Flux Dev responds when you change the strengths of layers in the model.☆21Updated last year
- Gradio UI for training video models using finetrainers☆31Updated 5 months ago
- ComfyUI for XLA devices for TPUs/GPUs☆20Updated 9 months ago
- ComfyUI unofficial implementation of Thera - Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields☆35Updated 4 months ago
- ComfyUI powertools for SD1.5 and SDXL model merging☆93Updated 5 months ago
- Model code for inferencing T5☆66Updated 6 months ago
- Wildly unsound and experimental sampling for ComfyUI☆28Updated 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.☆43Updated last year
- Create Latents with Perlin Noise in any shape (dimensionality). Works with Flux, SD3 and other 16d latent models.☆34Updated 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 flex…☆44Updated 2 weeks ago
- custom plugins for comfyUI☆59Updated last month
- Auto-MBW for ComfyUI loosely based on sdweb-auto-MBW☆16Updated last year
- Heuristic modification of the Heun sampler using normalized distances.☆39Updated 3 months ago
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆62Updated 6 months ago
- ☆38Updated last year
- A custom node for ComfyUI that adds cinematic and movie scene styles to video generation prompts. This node helps create more dynamic and…☆45Updated 8 months ago