Alex

Good afternoon, @PapayasTehSkeletor :) We would like to publish ruDALL-E Kandinsky (XXL) in near future, but I am not sure about exact time. We have some points: 1. Only colab...

@neverix, thank you a lot for all your provided features :) yttm tokenizer was trained using lowercase text only, so it doesn't expect uppercase text. For correct encoding/decoding should use...

@HetagKoroev you can try to use examples with inference on GPU 3.5Gb vRAM https://github.com/sberbank-ai/ru-dalle/pull/51 [](https://colab.research.google.com/drive/1AoolDYePUpPkRCKIu0cP9zV7lX5QGD3Z?usp=sharing) or [Jupyter version](https://github.com/sberbank-ai/ru-dalle/blob/master/jupyters/Malevich-3.5GB-vRAM-usage.ipynb): let me known if it helps for you @HetagKoroev

@muhammadyusuf-kurbonov Could you try to reinstall torch with version 1.7.1 cuda 10.2? ``` # CUDA 10.2 pip install torch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 ```

@blue-fish can't reproduce on my device and colab, could you give more information for reproducing: https://colab.research.google.com/drive/13VtQ_04XPvO4KTrsxukva_cpLWYfY1dk?usp=sharing

hello! welcome to make tutorials and guides 🙏 @FurkanGozukara 1: no ideas; 2: gradio script here: https://huggingface.co/spaces/DeepFloyd/IF/blob/main/app.py ; I suppose it can be run locally; 3: watermark is not forced!...

weights are available, problem is not actual

https://github.com/crowsonkb/k-diffusion/pull/78

thank you for this issue! @ProGamerGov could you give feedback here after release of weights, please how many false positive and how much complicated making of arts with these kind...