discoart
pyttv
| discoart | pyttv | |
|---|---|---|
| 11 | 5 | |
| 3,839 | 38 | |
| 0.1% | - | |
| 2.8 | 2.4 | |
| 12 months ago | about 1 year ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
discoart
-
Has anyone gotten disco diffusion to run locally
Just look at basic Python syntax and read through the discoart readme and it should all make sense :). If you still get lost, me and other people are always here to help more
- Which AI (Art) Generator is your Favourite?
-
What hardware does Disco Diffusion need to run at speeds like MidJourney, Stable Diffusion or DALL-E?
just install latest Python from official page, then PyTorch from here (make sure it's some of the CUDA versions) and then follow the steps here and you should be good to go
-
Stable Diffusion Interactive Google Colab Notebook for Image Generation
discoart is a python library that significantly simplifies interacting with disco diffusion. Install the library with pip, a single import statement, and call the create() function and you're running. I've used it with a Google Colab sheet set to use a GPU runtime and had a good time generating until I hit Big G's limits.
- Discoart - Create disco diffusion artworks in one line
-
AI painting with the keywords: Universe, Goku, Dragon Ball, Supernova, Mist. Instantly became my favorite wallpaper
try out discoart! Takes a bit of practice though
- Isometric Pinball Island
- First nice portrait on 5.6 running locally on 2070 (comparison untouched / GFPGAN)
- Would DDArt created in one line really work?
- I made DiscoArt package to ease the integration of DD in production system
pyttv
-
Working on an audio-reactive tool for video generation, similar to deforum but more versatile. Here's an example of prompt audio-reactivity (the audio modulates the prompt attention)
This is the tool in question: https://github.com/sbaier1/pyttv
-
Extension Installation
is it this file init.sh ?
- I made a modified version of the Schism music video where a generative model tries to turn every single frame into an alex grey painting
-
made a music video/animation using stable diffusion
i used this tool i wrote for this: https://github.com/sbaier1/pyttv it integrates with auto's web UI to generate the frames and supports audio reactivity of different types to guide the animation.
What are some alternatives?
disco-diffusion
AI-Image-PromptGenerator - A flexible UI script to help create and expand on prompts for generative AI art models, such as Stable Diffusion and MidJourney. Get inspired, and create.
Simple_Prompt_Generator - Simple prompt generator for Midjourney, DALLe, Stable and Disco Diffusion, and etc.
onnx-web - web UI for GPU-accelerated ONNX pipelines like Stable Diffusion, even on Windows and AMD
stylegan2-projecting-images - Projecting images to latent space with StyleGAN2.
stable-diffusion-docker - Run the official Stable Diffusion releases in a Docker container with txt2img, img2img, depth2img, pix2pix, upscale4x, and inpaint.
docarray - Represent, send, store and search multimodal data
ai-art-generator - For automating the creation of large batches of AI-generated artwork locally.
Disco_Diffusion_Local - Getting the latest versions of Disco Diffusion to work locally, instead of colab. Including how I run this on Windows, despite some Linux only dependencies ;)
automatic - SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
clip-guided-diffusion - A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.
sd-webui-inpaint-anything - Inpaint Anything extension performs stable diffusion inpainting on a browser UI using masks from Segment Anything.