taming-transformers
sd-akashic
taming-transformers | sd-akashic | |
---|---|---|
35 | 37 | |
5,373 | 1,595 | |
1.6% | - | |
0.0 | 1.4 | |
9 days ago | about 1 year ago | |
Jupyter Notebook | ||
MIT License | The Unlicense |
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.
taming-transformers
-
Automatic1111 for Intel Arc (A380 Tested)
taming-transformers
-
[R] My simple Transformer audio encoder gives the same output for each timestep after the encoder
What’s your goal exactly? Are you trying to make a transformer based auto encoder of audio spectrograms? If so you should either start with either a proven ViT-based AE implementation (either a VAE or a VQ-GAN). But I don’t see why you necessarily need a ViT for this, if you’re working at a much smaller scale a convolutional architecture is plenty and much more amenable to beginners. See https://github.com/CompVis/taming-transformers for an example of a convolutional VQ GAN.
- Trying to make VqGAN+CLIP work again
-
im so lost
Command: "git" clone "https://github.com/CompVis/taming-transformers.git" "C:\AI\stable-diffusion-webui\repositories\taming-transformers"
-
Why is ChatGPT and other large language models not feasible to be used locally in consumer grade hardware while Stable Diffusion is?
See https://arxiv.org/abs/2012.09841 for prior work. SD authors swap out the Transformer and language modelling objective with a UNet diffusion objective. In general, the more inductive bias your model has, the more efficient it can be. ChatGPT runs purely on a Transformer architecture, which has far fewer priors than a CNN and requires far more parameters as a result. This may not be the case in the future.
-
1 or 2 Errors Installing Automatic1111 on Mac M1
There is definitely a cmd but I can't tell you. It's on GitHub https://github.com/CompVis/taming-transformers
-
Trying to Install InvokeAI and VectorQuantizer2 and taming modules but get error “zsh: parse error near `)’” How to fix? (MAC M1)
I wasn’t able to find a “taming” folder within the site-packages folder so I decided to look up how to get VectorQuantizer2 and taming.modules.vqvae.quantize and found this link: https://github.com/CompVis/taming-transformers/blob/master/taming/modules/vqvae/quantize.py I copied the raw contents and pasted that to the terminal and I got this error: “zsh: parse error near `)’” I’m not sure how to fix this so I can install VectorQuantizer2 so I can use InvokeAI. How do I fix this?
-
AI Is Coming For Commercial Art Jobs. Can It Be Stopped? (Greg Rutkowski quoted)
I say this to everyone... Even if SD and the model is legit and legal. Do not go around commercialising it's outputs or claiming ownership over them... and if you do the properly cite the source of the model and system along with it. In https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers and https://huggingface.co/CompVis/stable-diffusion-v1-4 there are citiations provided for you to use for a reason. I recommend you to use them.
-
Stable-diffusion in Nix
# Copy models as described in README cp ~/Downloads/model.ckpt . cp ~/Downloads/GFPGANv1.3.pth . # Clone other repos as mentioned in README mkdir repositories git clone https://github.com/CompVis/stable-diffusion.git repositories/stable-diffusion git clone https://github.com/CompVis/taming-transformers.git repositories/taming-transformers git clone https://github.com/sczhou/CodeFormer.git repositories/CodeFormer git clone https://github.com/salesforce/BLIP.git repositories/BLIP export NIXPKGS_ALLOW_UNFREE=1 nix-shell default.nix pip install torch --extra-index-url https://download.pytorch.org/whl/cu113 # Also from linux instructions. Can probably be added to default.nix python webui.py
-
[D] Where does VQ-GAN get its randomness from?
Code for https://arxiv.org/abs/2012.09841 found: https://compvis.github.io/taming-transformers/
sd-akashic
- [Stable Diffusion] La longueur maximale utilisable d'une invite de texte de diffusion stable est prétendument 77 jetons. Voici ce que cela signifie et comment tester le nombre de jetons dans votre invite de texte.
- [Stablediffusion] Que font exactement les guidance scale ?
-
Model Testing - Realistic portraits with a study of various artists (A's)
The very study you linked to also did this same thing, as have multiple others, and they have a visible, attributable, and even measurable effect exactly as I pointed out. Meanwhile yours doesn't, to the point of being attributable to noise on many. Therefor, "Don't be fooled."
- [Stablediffusion] Que fait exactement la Guidance Scale ?
- Is this tutorial legit?
-
Hi folks, thought I'd ask for help here because I'm quite a noob when it comes to stable diffusion. I have the problem that I want to generate landscapes and every time I get double mountains. I used negative (((Duplicate mountain))), double mountains,(((extra mountain))) but it doesn't help. Though
I remember referencing this image a lot - https://github.com/Maks-s/sd-akashic/blob/master/img/brbbbq-dimensions.png
-
Improving old 3D renders with AI and SD
I've found the keywords to improve the results in this repository along with a lot of usefull info.
-
What kind of limits would I have with an RTX 2070?
Picture Ratios
-
List of SD Tutorials & Resources
Stable Diffusion Akashic Records
-
Intro to Stable Diffusion: Resources and Tutorials
I think the current best list is at https://github.com/Maks-s/sd-akashic. There are now many such lists floating around. (I'm currently starting the hoarding of data and see if I can add to that list the many new links.)
What are some alternatives?
stable-diffusion - This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements. [Moved to: https://github.com/invoke-ai/InvokeAI]
stable-diffusion - Go to lstein/stable-diffusion for all the best stuff and a stable release. This repository is my testing ground and it's very likely that I've done something that will break it.
VQGAN-CLIP - Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
Dreambooth-Stable-Diffusion - Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles.
stable-diffusion - Optimized Stable Diffusion modified to run on lower GPU VRAM
rocm-build - build scripts for ROCm
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/sd-webui/stable-diffusion-webui]
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/Sygil-Dev/sygil-webui]
stable-diffusion - A latent text-to-image diffusion model