# rohitgandikota/sliders

Concept Sliders for Precise Control of Diffusion Models

Repository: https://github.com/rohitgandikota/sliders
Canonical: https://ross.abutalabs.com/products/sliders
Homepage: https://sliders.baulab.info
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-04-13T22:22:14+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 77, release rhythm 8, longevity 75
- inputs: {"age_days": 1052, "days_push": 142, "days_rel": 575, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1139, forks 89 (observed 2026-08-28T04:03:44.205730+00:00)

## What it is
Official implementation of Concept Sliders, LoRA adaptors that enable precise, plug-and-play control of attributes in diffusion models like Stable Diffusion and FLUX. It provides training scripts and demos for creating sliders from text prompts, image pairs, or StyleGAN stylespace neurons.

## Use cases
- train a slider to make generated people look older or younger
- control attribute strength like lighting or eye size in stable diffusion images
- create LoRA adaptors from text prompts or image pairs
- train concept sliders for FLUX-1 models
- use GPT to generate prompts for training a text slider
- edit images without disrupting overall structure

## When to choose
- you need fine-grained, strength-adjustable control over concepts in diffusion model outputs
- you want to train custom LoRA sliders from text descriptions or small image sets
- you are doing research on controllable image generation

## When to avoid
- you just want simple prompt-based image generation without attribute control
- you need a no-training solution (use the related SliderSpace repo instead)
- you work outside diffusion-based image generation

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, llm-training
- domain: machine-learning, deep-learning, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: diffusion-models, lora, stable-diffusion, flux, concept-sliders, text-to-image, eccv-2024, research, gpu

## Member repositories
- rohitgandikota/sliders (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:44.205730+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:36:06.486436+00:00, confidence not recorded.
  - readme: https://github.com/rohitgandikota/sliders (fetched 2026-08-28T04:03:44.205730+00:00, sha 336b95785772)
  - homepage: https://sliders.baulab.info (fetched 2026-08-29T12:41:13.719307+00:00, sha 93310a767140)
  - site_page: https://baulab.info/ (fetched 2026-08-29T12:41:13.722979+00:00, sha c7fc6fcfaa05)
- Data as of 2026-08-30T08:39:29.467469+00:00.