YRIKKA / ComfyUI-InferenceTimeScalingLinks
This extension provides inference-time optimization techniques to enhance diffusion-based image generation quality through random search and zero-order optimization algorithms, along with an ensemble verification system.
☆19Updated 3 months ago
Alternatives and similar repositories for ComfyUI-InferenceTimeScaling
Users that are interested in ComfyUI-InferenceTimeScaling are comparing it to the libraries listed below
Sorting:
- ComfyUI Custom Node for "Golden Noise for Diffusion Models: A Learning Framework". This node refines the initial latent noise in the diff…☆23Updated 2 months ago
- NNT Neural Network Toolkit Custom Nodes for ComfyUI☆67Updated 4 months ago
- it really is a skill issue☆33Updated 11 months ago
- Adaptive ODE Solvers for ComfyUI☆48Updated 10 months ago
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model☆53Updated 3 months ago
- flux distillation and stuff☆103Updated last week
- Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!☆42Updated this week
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUI☆17Updated 5 months ago
- ComfyUI extension for mixing model during sampling☆20Updated 3 weeks ago
- Wildly unsound and experimental sampling for ComfyUI☆26Updated last week
- ComfyUI powertools for SD1.5 and SDXL model merging☆87Updated 2 months ago
- Allows to sample without generating any uncond with Stable Diffusion!☆48Updated 10 months ago
- ComfyUI implementation of the paper https://arxiv.org/pdf/2410.02416 "APG".☆32Updated 6 months ago
- ☆44Updated 5 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.☆43Updated 10 months ago
- ☆25Updated last month
- Comfyui implementation of Regional Adaptive Sampling, for Flux and HunYuanVideo☆18Updated 2 months ago
- ☆39Updated 8 months ago
- ☆56Updated last month
- Just code snipet☆31Updated 8 months ago
- Token Downsampling optimization for stable-diffusion-webui☆26Updated last year
- Uses DARE to merge LoRA stacks as a ComfyUI node☆33Updated last year
- ☆91Updated 11 months ago
- Create Latents with Perlin Noise in any shape (dimensionality). Works with Flux, SD3 and other 16d latent models.☆34Updated 10 months ago
- Heuristic modification of the Heun sampler using normalized distances.☆33Updated 3 weeks ago
- A tool to help adjust or zero-out Flux Block Weights and SAVE. I'm not a dev, so this implementation might be wrong.☆25Updated 6 months ago
- ComfyUI nodes to run FLUX OminiControl using diffusers☆35Updated 5 months ago
- ComfyUI nodes to use APG scaling for CFG☆29Updated 8 months ago
- Gradio UI for training video models using finetrainers☆30Updated last month
- ☆76Updated this week