stable-diffusion
stable-diffusion copied to clipboard
CompVis
A latent text-to-image diffusion model
I am getting this error ImportError: cannot import name 'VectorQuantizer2' from 'taming.modules.vqvae.quantize' Any ideas on how to solve it?
Error thrown when clicking on "Send to img2img" in the web-ui: Browser console log: POST http://127.0.0.1:7860/api/predict/500 (Internal Server Error) Lc @ index.9828d028.js:56 (anonymous) @ index.9828d028.js:56 await in (anonymous) (async) (anonymous)...
Would be great to add images as style reference or even as key reference frames to build the video generatuon
Hi all, congratulations for your work. I have been playing with diffusion models for images only generation and results are great. But what if I would use the same model...
Been looking since yesterday and haven't found the answer lol. How in the heck do we accomplish executing multiple prompts from a txt file? Is there an example somewhere that...
Problem: ``` ubuntu@instance-09:~/stable-diffusion-cpuonly$ conda env create -f environment-cpuonly.yaml Collecting package metadata (repodata.json): done Solving environment: failed ResolvePackageNotFound: - python=3.8.5 - pip=20.3 ubuntu@instance-09:~/stable-diffusion-cpuonly$ ``` specs: Specs: OS: Ubuntu 22.04.1 LTS aarch64...
I have success run it on my computer, but I find every time when I run it, will log this: Fetching 16 files: 100%|██████████| 16/16 [00:31
I'm receiving the following error but unsure how to proceed. This is the output of setting `--n_samples 1`! ``` RuntimeError: CUDA out of memory. Tried to allocate 1024.00 MiB (GPU...
Would it be possible to implement distillation such as one in this repo: https://github.com/Hramchenko/diffusion_distiller
