transcribe-anything VS Hentai-Diffusion

transcribe-anything

OpenAI whisper. Here is a tool that has it, a video downloader, and some other things bundled in with it: https://github.com/zackees/transcribe-anything

People interested in this might also be interested in transcribe-anything [1].

It automates video fetching and uses whisper to generate .srt, .vtt and .txt files.

[1] https://github.com/zackees/transcribe-anything

Nice looks great, link broken but it just needed a hyphen https://github.com/zackees/transcribe-anything

Right now the cuda accelerated whls are hosted outside of pypi which can only be accessed by using `--extra-index-url`, when installing from a requirements file (pip install -r requirements.txt). However pip install doesn't allow --extra-index-url for security reasons, which means deploying cuda accelerated ML apps on python is a complicated affair, see this [script](https://github.com/zackees/transcribe-anything/blob/main/install_cuda.py) as an example of what needs to be done to uninstall conflicting cpu only version of pytorch and replace it with cuda acceleration.

Transcribe Anything

Code Repo: https://github.com/zackees/transcribe-anything (please give my repo a like)

I came across a nice picture that I want to emulate. No model name is given. It took me a while to track down the model. It is an older version of Hentai Diffusion (HD-17). However, after I entered the same parameters to generate the picture, I could not get the same picture. Then I realized the picture was generated using img2img. So unless I have the original picture, I am not going to generate the same picture. The results are still good nonetheless, so I am going to keep it in my model directory.

Hentai Diffusion (SFW link except for one panty shot) is a finetune of Stable Diffusion, presumably trained on AI (although they claim that the model does some SFW stuff better too). The github readme contains some examples showcasing what the AI could do. However, at least two images (in partiuclar, the ones under "Better Obscure Camera Angles") were generated by the NovelAI model, not by Hentai Diffusion.