huggingface / huggingface/diffusers

Dynamic thresholding (full)

Open
#4,497 10 comments 0 reactions 0 assignees View on GitHub
contributions-welcome stale
Dominant language
Python
Stars
34.5k
Forks
7.3k
Avg merge
3d 3h
Merged PRs (30d)
91

Description

**Is your feature request related to a problem? Please describe.**
I am trying to increase the variety and quality of my results

**Describe the solution you'd like**
I would like dynamic thresholding implemented

**Describe alternatives you've considered**
Doing it myself, paying someone better than to do it or giving up

**Additional context**
here's the repo: https://github.com/mcmonkeyprojects/sd-dynamic-thresholding/tree/master
here's the relevant code: https://github.com/mcmonkeyprojects/sd-dynamic-thresholding/blob/master/dynthres_core.py
code is short too. less than 200 lines.

Contributor guide

Open the contributing guide

Research direction

Start with the linked dynthres_core.py and compare its behavior with the Diffusers implementation to identify the relevant pipeline entry point. Done means full dynamic thresholding is integrated into Diffusers and its image-generation behavior is validated.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.