@ajyoung I’m sorry for that result. I started out dissatisfied with how generative stuff worked on the Mac after all of Apple’s boasts about how great the newer Macs were for Machine Learning and it slowly grew better over the last 3 - 4 months (after Apple Silicon had been out for two whole years mind you …) as PyTorch added more support and then finally CoreML support from Apple seemed to make things bearable.

But there’s still so much that’s worse on the Apple side of the fence. Plus, support for anything other than what Apple considers important seems to come at a very slow pace. So not sure if it’ll ever get any better unless Apple decides to enter the generative ML space using it for a business model somehow ….

@NoctisEqui I used to do this back in the day when books were scarce. Then I got so many books (because I travelled out of Sri Lanka where book choices were limited, especially for Science Fiction and Fantasy) that I always had a to-be read pile. So the thrill of reading something new and always being surprised took over.

I probably should go back to all the old DiscWorld books since I don’t think I’ve ever read any of them more than once. But then again, I remember most of them and all of them have some memory (outside the book) attached to them …

Is it too late for ‘Thick Trunk Thursday’?

I took a walk today, made .3 of a mile at a slow creep and found this wonderful tree by the dog park so of course I had to photograph it.

It is a truly magnificent tree!

This pastoral idyl was snapped with no filter by my rubbish cheap phone in the middle of Knightsbridge, London. To me that feels like a miracle. But then spring is always a miracle.

#spring #daffodils #cadoganSquare

Dusk over Lake Superior

I got a little carried away with the alt tag/image description. That's the meat of the post. There are like a million characters to use there. Mastodon should allow x4 the characters in toots. That'd be cool. Call it a Super Toot or a Massive Toot. Everyone gets one a day. Anyway, I digress.

#photography #LandscapePhotography #winter #LakeSuperior #Minnesota

Apologies for the non-art posting as I'm job hunting. Unsure if this will work since I mostly see tech-job postings, but shooting my shot. Boosts appreciated #getfedihired #fedijobs #jobsearch

Philippine-based person looking for work in landscape architecture, urban planning, transport planning, or anything where my skills are applicable in related jobs. Would consider work in climate change also.

Skills in technical writing, AutoCAD, Photoshop, InDesign, SketchUp, Lumion, GIS, illustration

@wadethemaker The costs will probablly depend (at least to some extent) on which flavour of Fedi-software you run. Apparently, Mastodon is a bit of a beast and will need a bit more RAM (and possibly CPU) power.

I ran several different Fedi-flavours (but not Mastodon) because of the above. Based on personal experience, what I can tell you is that GoToSocial will run fine on the lowest end DigitalOcean VPS which I think costs $5 or $10 a month?

However (at least at the time I tried) GotoSocial was missing a few features that I wanted and so I switched to Akkoma, which has all the features I wanted (and a few more besides). It probably needs about 2GB of RAM to be comfortable. I found a server with Hetzner (https://www.hetzner.com/) which gave me a 4GB RAM VPS for under/around $10 a month. I’ve been hosted there for a couple of months now and happy with things — both their server and Akkoma.

Today the flower of Orange Hawkweed.
As the name suggests it is actually a weed.
But it has beautiful flowers!

See it bigger here: https://jan-luit.pixels.com/featured/orange-hawkweed-close-up-jan-luit.html

#AYearForArt #ArtMatters #Art #Flower #Nature #PhotographyIsArt #Photography #Natuur #NaturePhotography #Naturelovers #NatureBeauty #Wildflowers #Wildflower #FediGiftShop #mastoart

Hello! I'm Jeff, a software architect near L.A.

From 1994-96 I ran a dialup #bbs with >1,000 users sharing 8 lines (oof). By the end it provided MINIX shell accounts + Internet email via FIDO. I've been online ever since.

I've been building Cerb.ai (formerly Cerberus Helpdesk) in #php + #mysql full-time for nearly 21 years. 1000s of teams use it for high-volume shared webmail + workflow automation.

I'm also interested in #aws #docker #machinelearning #german #boardgames

#introduction

Yesterday's Pratchett novel title was: "The Shepherd's Crown"

And that's the last of the #DiscWorld titles 😞 Sure there are a few others left like "Nation", "Dodger", and the "Bromeliad" stuff (not to mention "Johnny") but those don't really count as much here. I was reluctant to do this one since it feels (almost) like reading the last DiscWorld novel (and I haven't read anything much since then ...)

But time moves on and I guess we must too?

#AIArt #StableDiffusion #DeepLearning #MachineLearning #CV #AI
Prompt: “The Shepherd's Crown”.…
Prompt: “The Shepherd's Crown”.…
Prompt: “The Shepherd's Crown”.…
Prompt: “The Shepherd's Crown”.…

That’s it for papers today — 9 papers boosted from the cs.CV category on arXiv.org out of a total of 93 papers.

#AI #CV #NewPapers #DeepLearning #MachineLearning

"Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation. (arXiv:2206.07771v2 [cs.CV] UPDATED)" — Synthesis of multiple types of content such as dance-to-music or text-to-image using a new diffusion mechanism, at fewer steps.

Paper: http://arxiv.org/abs/2206.07771
Code: https://github.com/l-yezhu/cdcd

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Examples of the input (left col…

"Write and Paint: Generative Vision-Language Models are Unified Modal Learners. (arXiv:2206.07699v2 [cs.CV] UPDATED)" — A unified model based on training a model to write and paint concurrently.

Paper: http://arxiv.org/abs/2206.07699

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Illustration of the overall arc…

"Towards Reliable Image Outpainting: Learning Structure-Aware Multimodal Fusion with Depth Guidance. (arXiv:2204.05543v2 [cs.CV] UPDATED)" — Reliable outpainting using depth-guidance.

Paper: http://arxiv.org/abs/2204.05543

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A comparison of image outpainti…

"Text-driven Visual Synthesis with Latent Diffusion Prior. (arXiv:2302.08510v1 [cs.CV])" — Using diffusion models as the generic driver for diverse image generation tasks such as text-to3D, image editing, and StyleGAN adaptation.

Paper: http://arxiv.org/abs/2302.08510

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Applications of the proposed la…

i boosted this site earlier but i think it deserves more explanation. this is a search engine for images that shows you the copyright status for the image right there front and center and you can filter for them. for instance i grabbed this copyright 0 image of an echidna from there. and it even generated a citation for me: "Echidna on the move" by CazzJj is marked with CC0 1.0. i think this is a really easy way for getting a reference image while ensuring the person who took the image consents to its use! https://openverse.org/

"3D-aware Conditional Image Synthesis. (arXiv:2302.08509v1 [cs.CV])" — Using a 2 input such as a segmentation or edge map to generate photo-realistic images from different perspectives/viewpoints.

Paper: http://arxiv.org/abs/2302.08509
Code: https://github.com/dunbar12138/pix2pix3D

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Given a 2D label map as input, …

"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models. (arXiv:2302.08453v1 [cs.CV])" — Controlling text-to-image diffusion models in a more granular fashion by using special adapters to provide extra guidance.

Paper: http://arxiv.org/abs/2302.08453
Code: https://github.com/TencentARC/T2I-Adapter

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
We propose T2I-Adapter, a simpl…

"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation. (arXiv:2302.08113v1 [cs.CV])" — Controlling diffusion-based image generation so that you can specify image components, component placement etc. without any further fine-tuning.

Paper: http://arxiv.org/abs/2302.08113
Code: https://github.com/omerbt/MultiDiffusion

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
MultiDiffusion enables flexible…

"\`A-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting. (arXiv:2302.07994v1 [cs.LG])" — Having multiple subsets of data trained on specific prompts and being able to compose the final model based on the prompts you select.

Paper: http://arxiv.org/abs/2302.07994

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A-la-carte Learning and APT. Gi…