BLIP VS stable-diffusion

I suggest trying BLIP for this. I've had really good results from that.

https://github.com/salesforce/BLIP

I built a tiny Python CLI wrapper for it to make it easier to try: https://github.com/simonw/blip-caption

You can download the source and run it yourself from here: https://github.com/salesforce/BLIP

Then there's also BLIP (Bootstrapping Language-Image Pre-training).

Or BLIP

GitHub - salesforce/BLIP: PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

From what I understand, what's most important to you is having a model that's already trained on something, rather than the architecture. Yolo is probably fine, as would be some of the older ones. You should be able to find a model that's been pretrained on COCO - you can look at see what classes are included. I don't know if there are other broadly trained models available that will serve your purpose. What I'd do is just run your picture through a COCO trained object detection model and see if the annotations do what you want.

Though backing up a bit, there are also image captioning models that may better do what you want to do for organizing your photos. I'm not really familiar with any - though I did come across BLIP the other day but I haven't used it: https://github.com/salesforce/BLIP

This may be a better way to get at what you want

git clone https://github.com/salesforce/BLIP.git repositories/BLIP

# Copy models as described in README cp ~/Downloads/model.ckpt . cp ~/Downloads/GFPGANv1.3.pth . # Clone other repos as mentioned in README mkdir repositories git clone https://github.com/CompVis/stable-diffusion.git repositories/stable-diffusion git clone https://github.com/CompVis/taming-transformers.git repositories/taming-transformers git clone https://github.com/sczhou/CodeFormer.git repositories/CodeFormer git clone https://github.com/salesforce/BLIP.git repositories/BLIP export NIXPKGS_ALLOW_UNFREE=1 nix-shell default.nix pip install torch --extra-index-url https://download.pytorch.org/whl/cu113 # Also from linux instructions. Can probably be added to default.nix python webui.py

Also check img2text (basically to prompt): https://github.com/salesforce/BLIP

Which is a 1-click install of Stable Diffusion with an alternative web interface. You can choose a different approach but this one is pretty simple and I am new to this stuff.

an invisible watermarking of the outputs, to help viewers identify the images as machine-generated.

It sounds like you just want to set up Stable Diffusion to run locally. I don't think your computer's specs will be able to do it. You need a graphics card with a decent amount of VRAM. Stable diffusion is in Python as is almost every AI open source project I've seen. If you can get your hands on a system with an Nvidia RTX card with as much VRAM as possible, you're in business. I have an RTX 3060 with 12 gigs of VRAM and I can run stable diffusion and a whole variety of open source LLMs as well as other projects like face swap, Roop, tortoise TTS, sadtalker, etc...

Use specific GPU on multi GPU systems · Issue #87 · CompVis/stable-diffusion · GitHub

I dealt with this in one of my posts. At least SD 1.1 till 1.5 are all trained on a batch size of 2048. The version pretty much everyone uses (1.5) is first pretrained at a resolution of 256x256 for 237K steps on laion2B-en, at the end of those training steps it will have seen roughly 500M images in laion2B-en. After that it is pre-trained for 194K steps on laion-high-resolution at a resolution of 512x512, which is a subset of 170M images from laion5B. Finally it is trained for 1.110K steps on LAION aesthetic v2 5+. This is easily verified by taking a glance at the model card of SD 1.5. Though that one doesn't specify for part of the training exactly which aesthetic set was used for part of the training, for that you have to look at the CompVis github repo. Thus at the end of it all both the most recent images and the majority of images will have come from LAION aesthetic v2 5+ (seeing every image approx 4 times). Realistically a lot of the weights obtained from pretraining on 2B will have been lost, and only provided a good starting point for the weights.

stable diffusion · CompVis/stable-diffusion@2ff270f · GitHub

Here for example --> https://github.com/CompVis/stable-diffusion