Hey, folks. Big layoffs at DigitalOcean today, and my team and I were hit. In fact, so was my adjacent team, and a good chunk of my department. I don't have much reach here on Mastodon yet, but if anybody wants to discuss opportunities for a technical editor / writer / manager of same, I'm up for it.

Anybody doing any #Generative #MachineLearning stuff and posting about it as you work on it? Not papers? But just the daily trials and tribulations (and successes) of working on stuff. Have too many #DeepLearning and #MachineLearning accounts talking about their courses and videos and stuff and not enough of the daily stuff …

I miss that … Seeing what other people are working on, the small triumphs, and learning about new ways to do/try things …

If you are out there, hit me up and I’d like to follow you 🙂

I'm excited to be presenting a tutorial for new programmers at @pycon this year. 😊

Have a colleague attending #PyCon2022 who doesn't (yet) write code? 🧑‍💻

Ask them to keep an eye out for "Intro to Python for Brand New Programmers" when tutorial registration opens up! 💖

Yesterday's Pratchett novel title prompt was: "Snuff"

I didn't really expect much from that one since there isn't a lot to work with there. But I still got some interesting images 🙂

These are from multiple models and so the styles are a little different across images. But still, I thought the end results were interesting ...

#AIArt #StableDiffusion #DeepLearning #MachineLearning #CV #AI #DiscWorld
Prompt: “Snuff”. Colourful pict…
Prompt: “Snuff”. A huge creatur…
Prompt: “Snuff”. A colourful im…
Prompt: “Snuff”. A colourful bu…

This photo was taken in Kenai, #Alaska yesterday next to the Senior Center and Senior Apartments overlooking Cook Inlet with the mountain range in the background. And of course, there is a kneeling moose eating some grub. This is the area of the state I live in. 💗
📸 by Carol Reinhardt King
#AlaskaMoose #Moosetodon

And with 11 papers boosted out of 82 in the cs.CV category on arXiv, we are done with papers for the day 🙂

#AI #CV #NewPapers #DeepLearning #MachineLearning

"DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model. (arXiv:2302.06908v1 [cs.CV])" — Today seems to be the day for papers on turning sketches into realistic colour images using diffusion models 😛 This is another approach ...

Paper: http://arxiv.org/abs/2302.06908

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A Sketch-Guided Lantent Diffusi…

"Text-Guided Scene Sketch-to-Photo Synthesis. (arXiv:2302.06883v1 [cs.CV])" — Creating a whole scene color image based on a sketch using generative models such as Stable Diffusion.

Paper: http://arxiv.org/abs/2302.06883

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Overview of training and sampli…

"Make Your Brief Stroke Real and Stereoscopic: 3D-Aware Simplified Sketch to Portrait Generation. (arXiv:2302.06857v1 [cs.CV])" — Creating photorealistic images of people based on sketches using 3D generative models.

Paper: http://arxiv.org/abs/2302.06857

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The visualization of our Stereo…

"DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Models. (arXiv:2302.06826v1 [cs.CV])" — Transfer the input image appearance onto images of items of clothing while not altering the structure of the clothing item.

Paper: http://arxiv.org/abs/2302.06826
Code: https://github.com/Rem105-210/DiffFashion

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Two examples of a reference-bas…

"Multiple Appropriate Facial Reaction Generation in Dyadic Interaction Settings: What, Why and How?. (arXiv:2302.06514v2 [cs.CV] UPDATED)" — An attempt to generate appropriate behavioral responses to received stimulus and to evaluate the appropriateness of the generated responses.

Paper: http://arxiv.org/abs/2302.06514

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Multiple appropriate reaction g…

"NYCU-TWO at Memotion 3: Good Foundation, Good Teacher, then you have Good Meme Analysis. (arXiv:2302.06078v2 [cs.CL] UPDATED)" — Classifying the emotions and intensity expressed in memes using machine learning.

Paper: http://arxiv.org/abs/2302.06078

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Overview of the Meme Encoder

"Vector Quantized Diffusion Model with CodeUnet for Text-to-Sign Pose Sequences Generation. (arXiv:2208.09141v2 [cs.CV] UPDATED)" — Using diffusion models to generate sign language pose sequences based on spoken language.

Paper: http://arxiv.org/abs/2208.09141

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The forward diffusion process a…

"ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models. (arXiv:2302.07257v1 [cs.CV])" — Using Large Language Models (LLM) with Computer-Aided Diagnosis (CAD) networks to enhance the output of CAD networks by summarizing and presenting the information in a more understandable format.

Paper: http://arxiv.org/abs/2302.07257

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Overview of our proposed strate…

"Painting 3D Nature in 2D: View Synthesis of Natural Scenes from a Single Semantic Mask. (arXiv:2302.07224v1 [cs.CV])" — Using a semantic mask as input to generate photorealistic color images of natural scenes.

Paper: http://arxiv.org/abs/2302.07224

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Given only a single semantic ma…

"Netizens, Academicians, and Information Professionals' Opinions About AI With Special Reference To ChatGPT. (arXiv:2302.07136v1 [cs.CY])" — It's interesting to see what people think about ChatGPT (and AI in general) given all the current rush to embrace ChatGPT as the saviour of many businesses/corporations ... 😛 But a little light on specifics — mostly general statistics/impressions.

Paper: http://arxiv.org/abs/2302.07136

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>

"Universal Guidance for Diffusion Models. (arXiv:2302.07121v1 [cs.CV])" — a universal guidance algorithm that enables diffusion models to be controlled by arbitrary guidance methods such as segmentation, face recognition, object detection, and classifier signals, without the need to retrain for that specific method.

Paper: http://arxiv.org/abs/2302.07121
Code: https://github.com/arpitbansal297/Universal-Guided-Diffusion

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Examples of diffusion being gui…

A total of 82 papers in the cs.CV category on arXiv.org today — 47 new, 35 updated.

Have CoreML models I want to play with, but I guess I’ll have to read papers instead 😛

#AI #CV #NewPapers #DeepLearning #MachineLearning

Since yesterday evening, when I finally perfected the process for converting existing #StableDiffusion models (in either CKPT or SAFETENSOR format) to CoreML format, I’ve converted six models. Of them, all except for one work fine 🙂

So, in case this helps anybody else, here are the important things to remember:

1. You *must* use Python 3.8. If you any other Python version, you will end up with errors. (Not that I’ve tested all Python versions, but I did have errors with Python 3.9 and have read reports of others …)

2. You should be on Ventura 13.1 or higher.

3. You need the models to be in Diffusers format to run the conversion, but the easiest way that has worked for me is to download a CKPT file, convert it to Diffusers and point the script at the local folder with the Diffusers format model.

4. HuggingFace folks have a bunch of conversion scripts here: https://github.com/huggingface/diffusers/tree/main/scripts

5. The above scripts don’t mention SAFETENSOR format in the file names but SAFETENSOR is just CKPT with some changes. The CKPT conversion file has an extra argument named “--from_safetensors” so you can use the same script for CKPT to convert SAFETENSOR files with that extra argument.

6. You can use the Apple conversion script to convert one element at at a time using the different arguments such as “--convert-unet”, “--convert-text-encoder” etc. You don’t have to run all of them together. In fact, it turned out when I ran them all together, sometimes a component might be left out — generally the text encoder.

7. Once you’ve converted all the components and have them in one folder, you have to run the Apple conversion script once more with the “--bundle-resources-for-swift-cli” argument (pointing at your output folder) to create the final compiled CoreML model files (.mlmodelc) from your .mlpackage files.

That’s it 🙂 If you do all of the above, it should be fairly straightforward to create new CoreML models from existing StableDiffusion models.

Feel free to hit me up should you run into issues. Since I’ve gone through all this, I’d be happy to help anybody else facing the same issues ….

#CoreML #StableDiffusion #MachineLearning #DeepLearning #ModelConversion

A tiny jumping spider pauses to take in the view.

#spiders #arachnids #spider #arthropods #nature #photography #macrophotography