vqgan-clip-app
CLIP-Guided-Diffusion
| vqgan-clip-app | CLIP-Guided-Diffusion | |
|---|---|---|
| 3 | 4 | |
| 101 | 377 | |
| - | - | |
| 0.0 | 0.0 | |
| over 1 year ago | over 1 year ago | |
| Python | Python | |
| MIT License | GNU General Public License v3.0 or later |
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.
vqgan-clip-app
-
How not to waste $1600?
If you want to try your hand at buggering your whole system - try playing with AI image generation as it uses all possible computer assets :D . There is a lot of forms and installations for those but I VQGANs from github the easiest. Problem is that some require familarity with shell, python and in some cases - you need to enable the Linux subsystem in Windows (is it called a subsystem? it is not exactly a VM). This one is the easiest to install out of all I tried. But I liked the results of Pixray most but I wrecked it. I use this one nowadays.
-
[P] Nvidia releases web app for GauGAN2, which generates landscape images via text description, inpainting, sketch, object type segmentation map, and style image
My attempt at centralizing models to be run locally looks like this: https://github.com/tnwei/vqgan-clip-app/, currently supports VQGAN-CLIP models and CLIP guided diffusion models.
- App for running VQGAN-CLIP and CLIP guided diffusion locally
CLIP-Guided-Diffusion
-
Which is your favorite text to image model overall?
Runner-ups are Craiyon (for being more "creative" than SD), Disco Diffusion, minDALL-E, and CLIP Guided Diffusion.
-
Once have access, do you run it on your computer or over the internet on Open-AI's computers?
-clip guided diffusion https://github.com/nerdyrodent/CLIP-Guided-Diffusion
-
how would i go about running disco diffusion locally?
Nerdy Rodent has a Github repo for this; it should work fine from the Anaconda command line: https://github.com/nerdyrodent/CLIP-Guided-Diffusion
-
PLAYING AGAIN (CLIP GUIDED DIFFUSION) (VQGAN + CLIP) (Beksinski)
As far as I understand, VQGAN is not a guided diffusion model. I've been using a slightly tweaked version of https://github.com/nerdyrodent/CLIP-Guided-Diffusion for diffusion. Once you get it set up the interface is pretty much what you might expect:
What are some alternatives?
VQGAN-CLIP-Video - Traditional deepdream with VQGAN+CLIP and optical flow. Ready to use in Google Colab.
VQGAN-CLIP - Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
streamlit - Streamlit — A faster way to build and share data apps.
DALLE-mtf - Open-AI's DALL-E for large scale training in mesh-tensorflow.
jina-app-store-example - App store search example, using Jina as backend and Streamlit as frontend [Moved to: https://github.com/jina-ai/example-app-store]
disco-diffusion
ai-art-generator - For automating the creation of large batches of AI-generated artwork locally.
big-sleep - A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun
feed_forward_vqgan_clip - Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt
mindall-e - PyTorch implementation of a 1.3B text-to-image generation model trained on 14 million image-text pairs
zero-shot-object-tracking - Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.
artroom-stable-diffusion