imagen-pytorch
cupscale
imagen-pytorch | cupscale | |
---|---|---|
47 | 81 | |
7,787 | 2,067 | |
- | - | |
6.8 | 0.0 | |
about 1 month ago | over 1 year ago | |
Python | C# | |
MIT License | 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.
imagen-pytorch
-
Google's StyleDrop can transfer style from a single image
If google doesnt, someone like lucidrains probably would implement it, just like he did for imagen and muse.
- Create a Stable diffusion neural network from scratch.
-
Google just announced an Even better diffusion process.
lucidrains/imagen-pytorch: Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch (github.com)
- Karlo, the first large scale open source DALL-E 2 replication is here
-
training imagen
Hi Can someone guide me a little, as to how i can use LAION dataset to train my imagen model? like how i can download the data, and in which format it should be fed to https://github.com/lucidrains/imagen-pytorch code?
-
If everyone in this sub make a donation of $10 then we can train truly open stable diffusion.
If we were to put money into training something, I'd hope we use a better model, like Imagen.
- AI Content Generation, Part 1: Machine Learning Basics
-
DALL-E 2 is switching to a credits system (50 generations for free at first, 15 free per month)
I've been messing around with this open-source implementation. You can get a pretty good idea of the model size by just copying the parameters from the paper.
-
Protests erupt outside of DALL-E offices after pricing implementation, press photograph
I'm waiting on this implementation/training of imagen: https://github.com/lucidrains/imagen-pytorch
-
Show HN: Food Does Not Exist
I'm honestly surprised that they trained a StyleGAN. Recently, the Imagen architecture has been show to be both easier in structure, easier to train, and even faster to produce good results. Combined with the "Elucidating" paper by NVIDIA's Tero Karras you can train a 256px Imagen to tolerable quality within an hour on a RTX 3090.
Here's a PyTorch implementation by the LAION people:
https://github.com/lucidrains/imagen-pytorch
And here's 2 images I sampled after training it for some hours, like 2 hours base model + 4 hours upscaler:
https://imgur.com/a/46EZsJo
cupscale
- Print Four Souls Cards at Home (Fixed Audio)
-
What about game assets that target 1080p and you want 4K fidelity?
If you want to do more, there's chaiNNer and CupScale. You need to download an AI model to use those. There are a lot of anime/cartoon models out, so pick one that you like from here. (Note: Upscaly doesn't support these custom models.)
- Help selecting software
-
Do you have Topaz AI?
I'm not 100% sure how it holds up against topaz, but I've used cupscale (a gui for ESRGAN) to upscale most of my stuff. Its free (https://github.com/n00mkrad/cupscale) and you can find a million different ESRGAN models which are focused on different kinds of images (https://upscale.wiki/wiki/Model_Database).
- Unfall mit Fahrerflucht, AI-Upscaling?
-
(For FE Awakening in Citra) How can I change robin hair portrait?
Now upscaling isn't hard to do by itself, but the setup can be difficult. As I said earlier, ERSGAN is the preferable way to do it. (https://github.com/n00mkrad/cupscale) Cupscale is my preferred tool for doing it this way. (https://www.topazlabs.com/gigapixel-ai) Gigapixel is another option that's easier for newcomers, but may not produce as good of results. They even have a free trial if you want to demo the tool.
- What workflow is best for upscaling portraits taken by phone camera or DSLR?
-
Now that they started banning stable diffusion on google colab, what's the cheapest and the best way to deploy stable diffusion?
I use cupscale for upscaling things. Allows chaining models and handles video.
-
Are there any google collab scripts or other tools to upscale a bunch of images..?
For local there's cupscale and chainner
- A rustic cottage by the field [1920x1080]
What are some alternatives?
dalle-mini - DALLĀ·E Mini - Generate images from a text prompt
Waifu2x-Extension-GUI - Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, Real-CUGAN, RTX Video Super Resolution VSR, SRMD, RealSR, Anime4K, RIFE, IFRNet, CAIN, DAIN, and ACNet.
DALLE2-pytorch - Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
chaiNNer - A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and powerful programmatic image processing application.
DALLE-pytorch - Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Real-ESRGAN-ncnn-vulkan - NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
Real-ESRGAN - Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
DeepCreamPy - deeppomf's DeepCreamPy + some updates
waifu2x - Image Super-Resolution for Anime-Style Art
CogVideo - Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"
chaiNNer - A flowchart/node-based image processing GUI aimed at making chaining image processing tasks (especially upscaling done by neural networks) easy, intuitive, and customizable. [Moved to: https://github.com/chaiNNer-org/chaiNNer]