ai-art-generator

ai-art-generator copied to clipboard

I am attempting to run this on Anaconda Powershell, so maybe this is my first mistake, but everything was installing and running smoothly up until putting in the curl prompts...

SpeciesXBeer

RuntimeError: CUDA out of memory. Tried to allocate 72.00 MiB (GPU 0; 4.00 GiB total capacity; 3.35 GiB already allocated; 0 bytes free; 3.41 GiB reserved in total by PyTorch)...

vrotmelk

Can't figure out how to run multiple instances pointing at multiple graphics cards

2

LyfeOnEdge

Working with z of shape (1, 256, 16, 16) = 65536 dimensions. loaded pretrained LPIPS loss from taming/modules/autoencoder/lpips\vgg.pth VQLPIPSWithDiscriminator running with hinge loss. Restored from checkpoints/vqgan_imagenet_f16_16384.ckpt Using device: cuda:0 Optimising...

vrotmelk

Training the AI?

1

how does training work? I know it uses checkpoints as trained data but is there a way I can train it manually for my art and specific images?

Error404-RedRose

Up-Scaling and Diffusion Not Working?

2

Is there any way to upscale a generated image? Would that be done by diffusion? but if so the problem then is my Diffusion is missing cv2 Module. Everything was...

Error404-RedRose

Add multi-gpu support

2

GPU defaults to cuda zero Some more work will need to be done Adds #!CUDA_DEVICE to prompt file to set gpu

LyfeOnEdge

Hi there, after messing around with the code on this repo I noticed that some of my images were getting deformed corners/borders, mostly the top-right and bottom-left corners but in...

ZeroCool940711

i followed all the steps up to the test, and when i try 'python vqgan.py -s 128 128 -i 200 -p "a red apple" -o output/output.png' it says that there...

prais14

Or forked Version. [DALL-E 2](https://github.com/lucidrains/DALLE2-pytorch)

LokiInside