Create compelling Disco Diffusion artworks in one line
DiscoArt is an elegant way of creating compelling Disco Diffusion[*] artworks for generative artists, AI enthusiasts and hard-core developers. DiscoArt has a modern & professional API with a beautiful codebase, ensuring high usability and maintainability. It introduces handy features such as result recovery and persistence, gRPC/HTTP serving w/o TLS, post-analysis, easing the integration to larger cross-modal or multi-modal applications.
[*] Disco Diffusion is a Google Colab Notebook that leverages CLIP-Guided Diffusion to allow one to create compelling and beautiful images from text prompts.
💯 Best-in-class: top-notch code quality, correctness-first; include bug fixes and feature improvements over original DD5.x.
👼 Available to all: fully optimized for Google Colab free tier! Perfect for those who don't own GPU by themselves.
🎨 Focus on create not code: one-liner create()
with a Pythonic interface, autocompletion in IDE, and powerful features. Fetch real-time results anywhere anytime, no more worry on session outrage on Google Colab. Set initial state easily for more efficient parameter exploration.
🏭 Ready for integration & production: built on top of DocArray data structure, enjoy smooth integration with Jina, CLIP-as-service and other cross-/multi-modal applications.
pip install discoart
- If you want to start a Jupyter Notebook on your own GPU machine, the easiest way is to use our prebuilt Docker image.
- If you are not using Google Colab/Jupyter Notebook, then other dependencies might be required as described in the Dockerfile.
Note, GPU is required.
from discoart import create
da = create()
That's it! It will create with the default text prompts and parameters.
Supported parameters are listed here. You can specify them in create()
:
from discoart import create
da = create(
text_prompts='A painting of sea cliffs in a tumultuous storm, Trending on ArtStation.',
init_image='https://d2vyhzeko0lke5.cloudfront.net/2f4f6dfa5a05e078469ebe57e77b72f0.png',
skip_steps=100,
)
This docs explains those parameters in very details. The minor difference on the parameters between DiscoArt and DD5.x is explained here.
create()
returns da
, a DocumentArray-type object. It contains the following information:
- All arguments passed to
create()
function, including seed, text prompts and model parameters. - 4 generated image and its intermediate steps' images, where
4
is determined byn_batches
and is the default value.
This allows you to further post-process, analyze, export the results with powerful DocArray API.
Images are stored as Data URI in .uri
, to save the first image as a local file:
da[0].save_uri_to_file('discoart-result.png')
To save all final images:
for idx, d in enumerate(da):
d.save_uri_to_file(f'discoart-result-{idx}.png')
You can also display all four final images in a grid:
da.plot_image_sprites(skip_empty=True, show_index=True, keep_aspect_ratio=True)
Or display them one by one:
for d in da:
d.display()
Or take one particular run:
da[0].display()
You can also zoom into a run (say the first run) and check out intermediate steps:
da[0].chunks.plot_image_sprites(
skip_empty=True, show_index=True, keep_aspect_ratio=True
)
You can .display()
the chunks one by one, or save one via .save_uri_to_file()
, or save all intermediate steps as a GIF:
da[0].chunks.save_gif(
'lighthouse.gif', show_index=True, inline_display=True, size_ratio=0.5
)
You can review its parameters from da[0].tags
or export it as an SVG image:
from discoart.config import save_config_svg
save_config_svg(da)
If you are a free-tier Google Colab user, one annoy thing is the lost of sessions from time to time. Or sometimes you just early stop the run as the first image is not good enough, and a keyboard interrupt will prevent .create()
to return any result. Either case, you can easily recover the results by pulling the last session ID.
-
Pull the result via that ID on any machine at any time, not necessarily on Google Colab:
from docarray import DocumentArray da = DocumentArray.pull('discoart-3205998582')
Consider a Document as a self-contained data with config and image, one can use it as the initial state for the future run. Its .tags
will be used as the initial parameters; .uri
if presented will be used as the initial image.
from discoart import create
from docarray import DocumentArray
da = DocumentArray.pull('discoart-3205998582')
create(
init_document=da[0],
cut_ic_pow=0.5,
tv_scale=600,
cut_overview='[12]*1000',
cut_innercut='[12]*1000',
use_secondary_model=False,
)
You can set environment variables to control the behavior of DiscoArt. The environment variables must be set before importing DiscoArt:
DISCOART_LOG_LEVEL='DEBUG' # more verbose logs
DISCOART_OPTOUT_CLOUD_BACKUP='1' # opt-out from cloud backup
We provide a prebuilt Docker image for running DiscoArt in the Jupyter Notebook.
# docker build . -t jinaai/discoart # if you want to build yourself
docker run -p 51000:8888 -v $(pwd):/home/jovyan/ -v $HOME/.cache:/root/.cache --gpus all jinaai/discoart
😎 If you are already a DD user: you are ready to go! There is no extra learning, DiscoArt respects the same parameter semantics as DD5.4. So just unleash your creativity!
There are some minor differences between DiscoArt and DD5.x:
- DiscoArt fixes multiple bugs e.g. weighted prompts, cut scheduling in original DD5.4, which improves the generation quality.
- DiscoArt does not support video generation and
image_prompt
(which was marked as ineffective in DD 5.4). - Due to no video support,
text_prompts
in DiscoArt accepts a string or a list of strings, not a dictionary; i.e. no frame index0:
or100:
. clip_models
accepts a list of values from all open-clip pretrained models and weights.cut_ic_pow
is changed to a scheduling parameter to control the power of inner cut, the syntax is the same ascut_overview
,cut_innercut
.
👶 If you are a DALL·E Flow or new user: you may want to take step by step, as Disco Diffusion works in a very different way than DALL·E. It is much more advanced and powerful: e.g. Disco Diffusion can take weighted & structured text prompts; it can initialize from a image with controlled noise; and there are way more parameters one can tweak. Impatient prompt like "armchair avocado"
will give you nothing but confusion and frustration. I highly recommend you to check out the following resources before trying your own prompt:
- Zippy's Disco Diffusion Cheatsheet v0.3
- EZ Charts - Diffusion Parameter Studies
- Disco Diffusion 70+ Artist Studies
- A Traveler’s Guide to the Latent Space
- Disco Diffusion Illustrated Settings
- Coar’s Disco Diffusion Guide
- Join our Slack community and chat with other community members about ideas.
- Join our Engineering All Hands meet-up to discuss your use case and learn Jina's new features.
- When? The second Tuesday of every month
- Where? Zoom (see our public events calendar/.ical) and live stream on YouTube
- Subscribe to the latest video tutorials on our YouTube channel
DiscoArt is backed by Jina AI and licensed under MIT License. We are actively hiring AI engineers, solution engineers to build the next neural search ecosystem in open-source.