peacasso 0.0.6a0

Create with AI models

Peacasso

Peacasso is a UI tool to help you generate art (and experiment) with multimodal (text, image) AI models (stable diffusion).

Requirements and Installation

• Step 1: HuggingFace Access Get access Acccess to the diffusion model weights needs a HuggingFace model account and access token. Please create an account at huggingface.co, get an access token and agree to the model terms here. Next, create a HF_API_TOKEN environment variable containing your token.
• Step 2: Verify Environment - Pythong 3.7+ and CUDA Setup and verify that your python environment is python 3.9 or higher (preferably, use Conda). Also verify that you have CUDA installed correctly (torch.cuda.is_available() is true) and your GPU has about 7GB of VRAM memory.

Once requirements are met, run the following command to install the library:

pip install peacasso

Usage - UI and Python API

You can use the library from the ui by running the following command:

peacasso ui   # or peacasso ui --port=8080

import os
from dotenv import load_dotenv
from peacasso.generator import PromptGenerator
from peacasso.datamodel import PromptConfig

# load token from .env file
load_dotenv()

token = os.environ.get("HF_API_TOKEN")
gen = PromptGenerator(token=token)
prompt = "A sea lion wandering the streets of post apocalyptic London"

prompt_config = PromptConfig(
    prompt=prompt,
    num_images=3,
    width=512,
    height=512,
    guidance_scale=7.5,
    num_inference_steps=50,
)

result = gen.generate(prompt_config)
for i, image in enumerate(result["images"]):
    image.save(f"image_{i}.png")

Features and Road Map

• Command line interface
• UI Features. Query models with multiple parametrs
  • Text prompting
  • Image based prompting
  • Image inpainting (masking)
  • Latent space exploration
• Curation/sharing experiment results

Acknowledgement

This work builds on the stable diffusion model and code is adapted from the HuggingFace implementation.

Please abide by the - CreativeML Open RAIL-M license associated with the stable diffusion model.