VQGAN-CLIP
sminterpolate
VQGAN-CLIP | sminterpolate | |
---|---|---|
67 | 6 | |
2,563 | 1,373 | |
- | - | |
0.0 | 0.0 | |
over 1 year ago | almost 4 years 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.
VQGAN-CLIP
-
📚 Tutorials & 🎨 AI Art Generation Tool List Mega Thread
VQGAN-CLIP
-
Which is your favorite text to image model overall?
I've screwed with many text-to-image models over the past couple of years, and I found that while I currently enjoy Stable Diffusion's coherency, I have a soft spot for the ImageNet model used by default for VQGAN+CLIP. It easily approaches the uncanny valley when generating people or animals, but makes for great abstract backgrounds and wallpapers. I already have nostalgia for generating images with it on my CPU overnight.
-
Stable Diffusion Announcement
For someone only tangentially familiar with this space, how is this different than e.g. https://github.com/nerdyrodent/VQGAN-CLIP which you can also run at home? Is it the quality of the generated images?
-
Medieval Noir - VQGAN-CLIP - COCO Checkpoint
Used https://github.com/nerdyrodent/VQGAN-CLIP
- Once have access, do you run it on your computer or over the internet on Open-AI's computers?
- How to get AI imaging effect in Premiere pro
-
A Guide to Asking Robots to Design Stained Glass Windows
I don't have any of the DALL-Es but I do have a couple from github [1], [2] which gave these outputs[3]
[1] https://github.com/nerdyrodent/VQGAN-CLIP
-
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.
- Ask HN: Is there a publicly available (not private beta) text-to-image API?
-
Got a Machine Learning Algorithm to depict Aphex
For those that are interested, I used VQGAN-CLIP, specifically this GitHub repository
sminterpolate
-
How to upscale and remove watermark
For increasing fps, I recommend butterflow, but it's rather old. One of the forks has it working on a more recent version of fedora, not sure if that translates to windows easily.
- AMD Fluid Motion, how to get it to work?
-
Dancing Thunder Clouds. Vqgan/Clip
For motion interpolation I used a program called butterflow: https://github.com/dthpham/butterflow. It can be hit or miss, but it's a cool tool to have your belt. In this case it added a bit of rhythmic jerkiness that made me think of adding music :-)
- One concussion please
- Open-firmware GoPro alternative?
-
Frame rate booster from 24fps to 60fps for free
Butterflow is good: https://github.com/dthpham/butterflow
What are some alternatives?
CLIP-Guided-Diffusion - Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.
Super-SloMo - PyTorch implementation of Super SloMo by Jiang et al.
DALLE-mtf - Open-AI's DALL-E for large scale training in mesh-tensorflow.
butterflow-ui - A graphical user interface for butterflow.
image-super-resolution - 🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
deep-daze - Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
waifu2x - Image Super-Resolution for Anime-Style Art
stable-diffusion - A latent text-to-image diffusion model
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
Real-ESRGAN - Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
3d-photo-inpainting - [CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
fast-style-transfer - TensorFlow CNN for fast style transfer ⚡🖥🎨🖼