| # CLIP Interrogator 2.2 by [@pharmapsychotic](https://twitter.com/pharmapsychotic) | |
| # | |
| # Want to figure out what a good prompt might be to create new images like an existing one? The CLIP Interrogator is here to get you answers! | |
| # | |
| # <br> | |
| # | |
| # For Stable Diffusion 1.X choose the **ViT-L** model and for Stable Diffusion 2.0+ choose the **ViT-H** CLIP Model. | |
| # | |
| # This version is specialized for producing nice prompts for use with Stable Diffusion and achieves higher alignment between generated text prompt and source image. You can try out the old [version 1](https://colab.research.google.com/github/pharmapsychotic/clip-interrogator/blob/v1/clip_interrogator.ipynb) to see how different CLIP models ranks terms. | |
| # |
This is Felix Kuehling, long time KFD driver architect. I started looking into the TinyGrad source code yesterday, focusing on ops_kfd.py, ops_hsa.py and driver/hsa.py, to understand how TinyGrad talks to our HW and help with the ongoing debugging effort from the top down. This analysis is based on this commit: https://github.com/tinygrad/tinygrad/tree/3de855ea50d72238deac14fc05cda2a611497778
I'm intrigued by the use of Python for low-level programming. I think I can learn something from your use of ctypes and clang2py for fast prototyping and test development. I want to share some observations based on my initial review.
ops_kfd looks pretty new, and I see many problems with it based on my long experience working on KFD. I think it's interesting, but probably not relevant for the most pressing problems at hand, so I'll cover that last.
ops_hsa uses ROCr APIs to manage GPU memory, create a user mode AQL queue for GPU kernel dispatch, async SDMA copies, and signal-based synchronization with barrier packets
