# google/prompt-to-prompt

Repository: https://github.com/google/prompt-to-prompt
Canonical: https://ross.abutalabs.com/products/prompt-to-prompt
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-05-14T08:06:32+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1430, "days_push": 841, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3456, forks 318 (observed 2026-08-28T04:08:05.515750+00:00)

## What it is
Google's official implementation of the Prompt-to-Prompt paper, which enables text-driven image editing in Latent Diffusion and Stable Diffusion models by controlling cross-attention weights during generation. It provides an AttentionControl API supporting prompt replacement, refinement, and token re-weighting edits.

## Use cases
- edit images by swapping words in the prompt while keeping composition
- add style or detail tokens to a prompt and regenerate the same image
- strengthen or weaken the influence of a specific word on the generated image
- research attention control in diffusion models
- build text-to-image editing pipelines on top of Stable Diffusion

## When to choose
- you want research-grade, paper-faithful prompt-to-prompt image editing with Stable Diffusion or Latent Diffusion
- you need a simple AttentionControl abstraction to experiment with cross-attention manipulation
- you want runnable notebooks demonstrating replacement, refinement, and re-weighting edits

## When to avoid
- you need a production image-editing service or polished UI rather than research code
- you want the latest diffusion models or editors like InstructPix2Pix or ControlNet
- you have less than 12GB of GPU VRAM or no GPU available

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning, prompt-engineering
- domain: artificial-intelligence, image-processing, deep-learning, machine-learning
- platform: python
- tags: stable-diffusion, latent-diffusion, diffusion-models, attention-control, text-to-image, image-editing, research-code, jupyter-notebooks, gpu

## Member repositories
- google/prompt-to-prompt (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:05.515750+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 2026-08-29T18:37:30.113483+00:00, confidence not recorded.
  - readme: https://github.com/google/prompt-to-prompt (fetched 2026-08-28T04:08:05.515750+00:00, sha 06fa790bcfe0)
- Data as of 2026-08-30T08:39:29.467469+00:00.