Extraltodeus/DistanceSampler
Heuristic modification of the Heun sampler using normalized distances.
This tool helps AI artists and content creators generate higher-quality images using diffusion models with fewer steps. You input a text prompt into your image generation workflow, and it outputs a more coherent and aesthetically pleasing image, reducing common distortions like 'body horror' or 'merged people'. It's for anyone using Stable Diffusion or similar models to create visual content.
No commits in the last 6 months.
Use this if you are an AI artist seeking to generate visually superior images with fewer sampling steps and less 'body horror' using diffusion models.
Not ideal if you prioritize extremely fast image generation over subtle improvements in quality and coherence, as it can be slower per step.
Stars
42
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Extraltodeus/DistanceSampler"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scraed/LanPaint
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
julienkay/com.doji.diffusers
A Unity package to run pretrained diffusion models with Unity Sentis
apapiu/transformer_latent_diffusion
Text to Image Latent Diffusion using a Transformer core
Aatricks/LightDiffusion-Next
Fastest Diffusion backend, WebUI, server. Pushing implementation and discovery of optimizations...
FMXExpress/Stable-Diffusion-Desktop-Client
Stable Diffusion Desktop client for Windows, macOS, and Linux built in Embarcadero Delphi.