ru-dalle
ru-dalle copied to clipboard
ai-forever
Generate images from texts. In Russian
currently show assumes square size. when you have more rows than columns this will change the main axis determining the size from width to height.
Make it possible to fine-tune on both a CPU and GPU (3/4 on GPU and 1/4 on CPU for example). If this is already possible, how?
I'm getting this error recently: ```python import transformers import more_itertools from tqdm.auto import tqdm from rudalle.pipelines import show, cherry_pick_by_clip from rudalle import get_rudalle_model, get_tokenizer, get_vae, get_ruclip from rudalle.utils import seed_everything,...
My Jupyeter notebook kernel dies (`The kernel appears to have died. It will restart automatically`.)when trying to load the main model after downloading it: ``` device = 'cuda' dalle =...
@shonenkov Great work everyone! As far as I can tell, there is only VAE decoder with DWT and no corresponding encoder. Encoding with get_vae(dwt=True) produces the same number of tokens...
Input image: https://static8.depositphotos.com/1370441/848/i/600/depositphotos_8486144-stock-photo-beach-and-tropical-sea.jpg Input text: 'elon musk' Result: [image](https://scontent-frt3-2.xx.fbcdn.net/v/t39.30808-6/266850659_10215735351777199_4719489214825321057_n.jpg?_nc_cat=101&_nc_rgb565=1&ccb=1-5&_nc_sid=730e14&_nc_ohc=F-dcUV66HngAX-_WQwX&_nc_ht=scontent-frt3-2.xx&oh=00_AT-_oZpQ7XN81wUUtEnn6moUUwvneOtsQ9XHKySKuz3WhA&oe=61C00A55) and [image](https://user-images.githubusercontent.com/40601736/146972487-84ba7258-06c1-4845-8f02-e781ecc7fdb3.png) Colab that runs out of memory: https://colab.research.google.com/drive/1ancv6fQMrzaz67Ikvfv3wnjlwpWsoebO?usp=sharing My method is to optimize the text embedding of the transformer, in...
should we now use use_cache=True for image prompts? I was using the latest code but with use_cache=False. after changing results look the same but it is 10x faster... is there...
hi, like others, i prepared a colab with more accessible GUI and presets here: https://gist.github.com/eyaler/0cee9a71f5dd3fdfa9c0c03656ebdd4c this is oriented for easily doing batch experiments and you can see some results here:...
It seems like the tokenizer ignores the first letter when it's uppercase, chaining `encode_text` + `decode_text` shows that. What could be the source of this bug? Is this the intended...
