rocm-build VS CLIP

Scripts to help with building rocm and hip. It will also help work out dependencies. You will need to modify the scripts for them to work and not all are required. https://github.com/xuhuisheng/rocm-build

Short answer no. Long answer "in theory" yes. I tried this [1] but gave up as building rocm + deps takes up to 6h :/ Official statement [2]

[1] https://github.com/xuhuisheng/rocm-build

I am in the same boat with a gfx03 card. What patch did you use? The ones here? https://github.com/xuhuisheng/rocm-build

I also tried to compile pytorch with its Vulkan backend, but ended throwing the towel as LDFLAGS are a mess to get right (I successfully compiled it, but that was only part of the build chain, and decided I had better things to spend time on). I wonder how that would perform; ncnn works pretty decently.

Unofficial black magic is available: https://github.com/xuhuisheng/rocm-build/tree/master/navi10 (pytorch 1.12.0 is outdated but can run SD)

also have an RX570, currently running latest Tensorflow and ROCm 4.1. had to recompile some parts of ROCm 4.1 libraries to get tensorflow to work. mostly followed this guide: https://github.com/xuhuisheng/rocm-build/tree/master/gfx803

We will also need two more libraries: OpenAI’s CLIP GitHub repo, enabling us to generate image features with the CLIP model, and the umap-learn library, which will let us apply a dimensionality reduction technique called Uniform Manifold Approximation and Projection (UMAP) to those features to visualize them in 2D:

Biggest missing feature for all these self hosted photo hosting is the lack of a real search. Being able to search for things like "beach at night" is a time saver instead of browsing through hundreds or thousands of photos. There are trained neural networks out there like https://github.com/openai/CLIP which are quite good.

In computer vision, this is known as zero-shot learning, or zero-shot prediction, because the goal is to generate predictions without explicitly being given any example predictions to learn from. With the advent of high quality multimodal models like CLIP and foundation models like Segment Anything, it is now possible to generate remarkably good zero-shot predictions for a variety of computer vision tasks, including:

(Github Repo | Most Popular Model | Paper | Project Page)

the first thing that comes to mind is CLIP: https://github.com/openai/CLIP

Whenever I’m working on semantic search applications that connect images and text, I start with a family of models known as contrastive language image pre-training (CLIP). These models are trained on image-text pairs to generate similar vector representations or embeddings for images and their captions, and dissimilar vectors when images are paired with other text strings. There are multiple CLIP-style models, including OpenCLIP and MetaCLIP, but for simplicity we’ll focus on the original CLIP model from OpenAI. No model is perfect, and at a fundamental level there is no right way to compare images and text, but CLIP certainly provides a good starting point.

in the modal card it says: pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).

Command: "C:\StabilityMatrix\Packages\stable-diffusion-webui\venv\Scripts\python.exe" -m pip install https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip --prefer-binary

CLIP might work for your needs.

pip install deepfloyd_if==1.0.2rc0 pip install xformers==0.0.16 pip install git+https://github.com/openai/CLIP.git --no-deps pip install huggingface_hub --upgrade