latent-diffusion
latent-diffusion copied to clipboard
CompVis
High-Resolution Image Synthesis with Latent Diffusion Models
Trying the sample on a barebones fresh Ubuntu Server install. ```bash python scripts/knn2img.py --prompt "a happy bear reading a newspaper, oil on canvas" ``` results in `Segmentation fault (core dumped)`...
The artbench zipfile has a typo in. (data/rdm/retrieval_databases/). An example fix without changing the archive file is: ``` mv artbench-impressionsim artbench-impressionism ```
Congratulations on the new awesome fantastic rdm research, but ... For anyone with insufficient RAM to build index with scann script, I propose using autofaiss to create index I have...
Can you provide inference scripts for semantic image synthesis and layout-to-image synthesis? I tried to use data loaders from the ``taming-transformers`` repo but got random noise outputs. The evaluation results...
I'm attempting to run the demo on a machine that doesn't have a CUDA compatible GPU. I got as far as the sample command: `python scripts/txt2img.py --prompt "a virus monster...
# Intro I added support for Docker, and made sure cache and build files do not hit the repository, making it easier to work for others on this. The Docker...
In #6 a license was added, which is associated to the source code. Because they are downloaded separately, it would be great to have a license for the pretrained models...
If I want to guide latent diffusion, do I need to retrain model
I am not sure why the implementation only use the tokenizer from hugging face but did not use the pre-trained encoder. I mean why need to retrain the BERT-like transformer?...
Thanks for the excellent work! I wonder about the training device on text2image. The paper says it is trained on a single A100, but it seems the settings in table...
