Perturbed-Attention Guidance (PAG), Smoothed Energy Guidance (SEG), Sliding Window Guidance (SWG), PLADIS, Normalized Attention Guidance (NAG), Token Perturbation Guidance (TPG), Frequency-Decoupled Guidance (FDG), Momentum Guidance (MG), Sliding Mode Control CFG (SMC-CFG), mostly for ComfyUI.
☆298Mar 9, 2026Updated 4 months ago
Alternatives and similar repositories for sd-perturbed-attention
Users that are interested in sd-perturbed-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Enhance Stable Diffusion image quality, prompt following, and more through multiple implementations of novel algorithms for Automatic1111…☆153Apr 24, 2025Updated last year
- If your image was a pizza and the CFG the temperature of your oven: this is a thermostat that ensures it is always cooked like you want. …☆425Sep 10, 2024Updated last year
- ☆67May 3, 2025Updated last year
- Janky implementation of HiDiffusion for ComfyUI☆126May 6, 2025Updated last year
- Greatly increase the diversity of your generated images in Automatic1111 WebUI through Condition-Annealed Sampling.☆108Apr 22, 2024Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Gather similar vectors within the CLIP weights and use them to redirect the original weights☆127Aug 28, 2024Updated last year
- Allows to sample without generating any uncond with Stable Diffusion!☆50Jul 10, 2024Updated 2 years ago
- A set of nodes to prepare the noise predictions before the CFG function☆66May 24, 2025Updated last year
- Nodes that implement iterative mixing of samples to help with upscaling quality☆120Mar 10, 2025Updated last year
- A small neural network to provide interoperability between the latents generated by the different Stable Diffusion models.☆327Aug 6, 2024Updated last year
- ComfyUI nodes for prompt editing and LoRA control☆421Jul 4, 2026Updated 3 weeks ago
- An Extension for Forge Webui that implements Attention Couple☆459Jun 2, 2026Updated last month
- ☆99Aug 18, 2025Updated 11 months ago
- Tiled Diffusion, MultiDiffusion, Mixture of Diffusers, and optimized VAE☆539Mar 18, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ComfyUI TCD implementation☆141Jan 6, 2026Updated 6 months ago
- ComfyUI nodes for restart sampling based on the paper "Restart Sampling for Improving Generative Processes"☆89Dec 6, 2025Updated 7 months ago
- ComfyUI nodes collection: better TAESD previews (including batch previews), improved HyperTile and Deep Shrink nodes☆141Jun 2, 2026Updated last month
- ComfyUI implementation of Long-CLIP☆165Mar 8, 2025Updated last year
- Attention Couple for SDXL and Anima; NegPiP (negative weights in prompts) for SDXL and Anima; etc.☆264Updated this week
- ☆270Dec 1, 2024Updated last year
- ComfyUI custom nodes kit☆315May 7, 2025Updated last year
- Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.☆537Dec 17, 2024Updated last year
- Node to use Smoothed Energy Guidance for Diffusion in ComfyUI☆42Sep 11, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Provides the ability to set the temperature for both UNET and CLIP. For ComfyUI. Has for side effect to improve non-native resolutions.☆43Jul 10, 2024Updated 2 years ago
- Nodes for better inpainting with ComfyUI: Fooocus inpaint model for SDXL, LaMa, MAT, and various other tools for pre-filling inpaint & ou…☆1,216May 31, 2026Updated last month
- A powerful anti-burn allowing much higher CFG scales for latent diffusion models (for ComfyUI)☆232Jan 5, 2026Updated 6 months ago
- ☆196Jul 31, 2024Updated last year
- 6 nodes for ComfyUI that allows for more control and flexibility over noise to do e.g. variations or "un-sampling"☆321Jun 10, 2024Updated 2 years ago
- ELLA nodes for ComfyUI☆382Aug 16, 2024Updated last year
- An Automatic1111 extension for dynamically controlling the weights of LoRAs during image generation☆266Sep 20, 2023Updated 2 years ago
- ComfyUI Implementaion of ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment☆160Apr 27, 2024Updated 2 years ago
- Janky implementation of DiffuseHigh for ComfyUI☆37May 6, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Custom nodes for ComfyUI such as CLIP Text Encode++☆327Jun 4, 2025Updated last year
- A sampler base on Euler, aim at generating better picture/一种基于Euler的采样方法，旨在生成更好的图片☆227Sep 1, 2024Updated last year
- Experimental implementation of CADS for ComfyUI☆42Jun 23, 2025Updated last year
- A CustomNet node for ComfyUI☆10Aug 11, 2024Updated last year
- A few nodes to mix sigmas and a custom scheduler that uses phi☆96Aug 21, 2025Updated 11 months ago
- Heuristic modification of the Heun sampler using normalized distances.☆44Jun 19, 2025Updated last year
- a1111 implementation of https://github.com/ChenyangSi/FreeU☆310Dec 3, 2024Updated last year