BLIP
autodistill-metaclip
Our great sponsors
BLIP | autodistill-metaclip | |
---|---|---|
14 | 1 | |
4,242 | 16 | |
5.5% | - | |
0.0 | 6.4 | |
7 months ago | 5 months ago | |
Jupyter Notebook | Python | |
BSD 3-clause "New" or "Revised" License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
BLIP
-
MetaCLIP – Meta AI Research
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
-
Is there a website where you can upload a photo and get the description in a paragraph?
You can download the source and run it yourself from here: https://github.com/salesforce/BLIP
-
Stable Diffusion v2-1-unCLIP model released
Then there's also BLIP (Bootstrapping Language-Image Pre-training).
-
GPT-4 shows emergent Theory of Mind on par with an adult. It scored in the 85+ percentile for a lot of major college exams. It can also do taxes and create functional websites from a simple drawing
Or BLIP
-
meme
GitHub - salesforce/BLIP: PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
-
Object Recognition for Photo Metadata
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
-
I have a problem with the "interrogate" function of Automatic1111's fork. Can someone help me?
git clone https://github.com/salesforce/BLIP.git repositories/BLIP
-
Stable-diffusion in Nix
# 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
-
My easy-to-install Windows GUI for Stable Diffusion is ready for a beta release! It supports img2img as well, various samplers, can run multiple scales per image automatically, and more!
Also check img2text (basically to prompt): https://github.com/salesforce/BLIP
- [D] Author Interview - BLIP: Bootstrapping Language-Image Pre-training (Video)
autodistill-metaclip
-
MetaCLIP – Meta AI Research
I have been playing with MetaCLIP this afternoon and made https://github.com/autodistill/autodistill-metaclip as a pip installable version. The Facebook repository has some guidance but you have to pull the weights yourself, save them, etc.
My inference function (model.predict("image.png")) return an sv.Classifications object that you can load into supervision for processing (i.e. get top k) [1].
The paper [2] notes the following in terms of performance:
> In Table 4, we observe that MetaCLIP outperforms OpenAI CLIP on ImageNet and average accuracy across 26 tasks, for 3 model scales. With 400 million training data points on ViT-B/32, MetaCLIP outperforms CLIP by +2.1% on ImageNet and by +1.6% on average. On ViT-B/16, MetaCLIP outperforms CLIP by +2.5% on ImageNet and by +1.5% on average. On ViT-L/14, MetaCLIP outperforms CLIP by +0.7% on ImageNet and by +1.4% on average across the 26 tasks.
[1] https://github.com/autodistill/autodistill-metaclip
What are some alternatives?
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
clip-interrogator - Image to prompt with BLIP and CLIP
a-PyTorch-Tutorial-to-Image-Captioning - Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning
open_clip - An open source implementation of CLIP.
CodeFormer - [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
NumPyCLIP - Pure NumPy implementation of https://github.com/openai/CLIP
virtex - [CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations
sam-clip - Use Grounding DINO, Segment Anything, and CLIP to label objects in images.
nix-stable-diffusion - Nix-friendly fork of: Optimized Stable Diffusion modified to run on lower GPU VRAM
Text2LIVE - Official Pytorch Implementation for "Text2LIVE: Text-Driven Layered Image and Video Editing" (ECCV 2022 Oral)
taming-transformers - Taming Transformers for High-Resolution Image Synthesis
aphantasia - CLIP + FFT/DWT/RGB = text to image/video