k-diffusion VS CLIP

Traceback (most recent call last): File "C:\Program Files\Blender Foundation\Blender 3.3\3.3\scripts\modules\bpy_types.py", line 877, in draw_ls def draw_ls(self, context): KeyboardInterrupt pip 22.2.2 from C:\Program Files\Blender Foundation\Blender 3.3\3.3\python\lib\site-packages\pip (python 3.10) adding trusted host: 'https://download.pytorch.org' (from line 28 of C:\Users\User\AppData\Roaming\Blender Foundation\Blender\3.3\scripts\addons\dream-textures-main\requirements-win32.txt) Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cu113 Collecting clip Cloning https://github.com/openai/CLIP.git (to revision main) to c:\users\User\appdata\local\temp\pip-install-2ius2mgu\clip_37ce50499447435b9459dae25dc81033 Running command git clone --filter=blob:none --quiet https://github.com/openai/CLIP.git 'C:\Users\User\AppData\Local\Temp\pip-install-2ius2mgu\clip_37ce50499447435b9459dae25dc81033' Resolved https://github.com/openai/CLIP.git to commit d50d76daa670286dd6cacf3bcd80b5e4823fc8e1 Preparing metadata (setup.py) ... done Collecting k-diffusion Cloning https://github.com/lstein/k-diffusion.git (to revision master) to c:\users\User\appdata\local\temp\pip-install-2ius2mgu\k-diffusion_c1dbf384fd4443c3a23c90b01606a7a9 Running command git clone --filter=blob:none --quiet https://github.com/lstein/k-diffusion.git 'C:\Users\User\AppData\Local\Temp\pip-install-2ius2mgu\k-diffusion_c1dbf384fd4443c3a23c90b01606a7a9' Resolved https://github.com/lstein/k-diffusion.git to commit ef1bf07627c9a10ba9137e68a0206b844544a7d9 Installing build dependencies ... done Getting requirements to build wheel ... done Installing backend dependencies ... done Preparing metadata (pyproject.toml) ... done Obtaining file:///C:/Users/User/AppData/Roaming/Blender%20Foundation/Blender/3.3/scripts/addons/dream-textures-main/stable_diffusion (from -r C:\Users\User\AppData\Roaming\Blender Foundation\Blender\3.3\scripts\addons\dream-textures-main\requirements-win32.txt (line 32)) ERROR: file:///C:/Users/User/AppData/Roaming/Blender%20Foundation/Blender/3.3/scripts/addons/dream-textures-main/stable_diffusion (from -r C:\Users\User\AppData\Roaming\Blender Foundation\Blender\3.3\scripts\addons\dream-textures-main\requirements-win32.txt (line 32)) does not appear to be a Python project: neither 'setup.py' nor 'pyproject.toml' found.

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