autodistill-metaclip
clip-interrogator
autodistill-metaclip | clip-interrogator | |
---|---|---|
1 | 27 | |
16 | 2,491 | |
- | - | |
6.4 | 4.8 | |
5 months ago | 3 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
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.
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
clip-interrogator
-
AI Horde’s AGPL3 hordelib receives DMCA take-down from hlky
It's image -> words, the inverse of stable diffusion.
see: https://github.com/pharmapsychotic/clip-interrogator
-
What are the "fastest" image classifiers I can use?
I have been using this on a CPU https://github.com/pharmapsychotic/clip-interrogator, I tried a lot of pre-trained models combinations, all are slow.
- -New Monthly Event!-
-
I keep trying to recreate this scene as a painting. But the AI doesn't get it. How do I describe that the man is reaching behind to stab a lion in the head, as the lion has pounced and is biting the rear of the horse. The AI always redraws this without the lion or not how it is shown here.
I'm addition to controlnet, try the clip interrogator to see how clip would describe the image and then use that language in your prompt. You can try the whole image or cropped portions. There is a colab available if you don't want to run it locally.
-
For Lora training, isn’t there a good AI that discribes the pictures you want to use for training?
In my current process, I use CLIP Interrogator to produce a high level caption and wd14 tagger for more granular booru tags. Typically in that order, because you can append the results from the latter to the former. Both tools perform with greater accuracy than the standard interrogators in img2img and give you more flexibility and features as well. You still have to do some manual adjustments, but I generally prefer this process over starting from scratch.
- Midjourney Image2text
-
Tech pioneers call for six-month pause of "out-of-control" AI development
If you are interested in this, definitely see if you can get some of the OSS models running and get a feel for how to interrogate them. Maybe see if you can get some mileage out of the CLIP-Interrogator
-
ChatGPT 3.5 vs 4 & Stable Diffusion
Next, I used the lists of artists, flavors, mediums, movements, and negatives that are used for the clip-interrogator and pasted these in the chat and told the bot to categorize them accordingly. As you can only paste up to certain characters in single message (4-5K in 3.5 and 6-8K in 4).
-
Any idea of what type of prompt has been used to make this?
Here’s the specific one I’m using (runs in browser)
-
CLIP Interrogator 2 locally
I really enjoy using the CLIP Interrogator on huggingspaces, but it is often super slow and sometimes straight up breaks. Now it is possible to locally install it, https://github.com/pharmapsychotic/clip-interrogator but I don't know if its viable to run on a laptop with 6gb videocard anyway.
What are some alternatives?
open_clip - An open source implementation of CLIP.
stable-diffusion-webui-wd14-tagger - Labeling extension for Automatic1111's Web UI
BLIP - PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
laion-datasets - Description and pointers of laion datasets
NumPyCLIP - Pure NumPy implementation of https://github.com/openai/CLIP
dalle-2-preview
sam-clip - Use Grounding DINO, Segment Anything, and CLIP to label objects in images.
stable-diffusion-artists - Curated list of artists for Stable Diffusion prompts
Text2LIVE - Official Pytorch Implementation for "Text2LIVE: Text-Driven Layered Image and Video Editing" (ECCV 2022 Oral)
hordelib - A wrapper around ComfyUI to allow use by the AI Horde. [UnavailableForLegalReasons - Repository access blocked]
aphantasia - CLIP + FFT/DWT/RGB = text to image/video
semantic-kernel - Integrate cutting-edge LLM technology quickly and easily into your apps