---
title: WeavePrompt
emoji: 🎨
colorFrom: blue
colorTo: purple
sdk: docker
sdk_version: 5.44.1
pinned: false
license: mit
app_file: app.py
app_port: 7860
---

# WeavePrompt

Iterative prompt refinement for text-to-image models.
Given a target image, WeavePrompt automatically generates and refines text prompts to make a model's output resemble the target image, using vision-language models and perceptual metrics.

## Features
- Upload a target image
- Step-by-step prompt optimization
- View prompt and generated image at each iteration
- Full optimization history

## Installation

1. Clone the repository:
	```bash
	git clone <repo-url>
	cd WeavePrompt
	```
2. Install dependencies:
	```bash
	uv venv
	uv sync
    source .venv/bin/activate
	```
3. Setup `.env`
Put the following inside `.env`:
- API keys `WANDB_API_KEY` and `FAL_KEY`
- Weave project name `WEAVE_PROJECT`

## Usage

Run the demo app:
```bash
streamlit run app.py
```

Follow the instructions in the browser to upload an image and step through the optimization process.


## Architecture Diagram

![diagram](./diagram.png)