postmodern pygmalion // techno optimist // avid generalist

NYC
Joined February 2026
I spent two days pushing FLUX 3 Klein to its limits, trying to defeat its infamous wax faces. It ended up changing how I think about image models in general. Would you rather have one model that does everything decently, or a lean base you can shape?
7
1
6
2,057
getting crunk off that whistlepig maple syrup latte
20
ouuaagghh aahh ahhgg I'm getting poaached. labs! help! they're poaching meee
21
Lately there has been something ominous in the city I struggle to put into words, since I don't want to pick apart mundane things or exaggerate. Yet...
Replying to @geetz__romo
Everytime I visit nyc from La it’s like the stereotype of people of La infected nyc
1
106
Hey Apple, what if instead of one Mac Mini I had two Mac Minis
Apple should fund independent AI guys to improve inference on MLX. The hardware is there, just needs the software @johnternus
2
115
Felix Brener retweeted
Really getting tired of the "AI bad because NFTs" argument. From now until the end of time everything new will be NFTs all over again. If you don't understand the problem with making that parallel, your opinion is honestly just to biased to listen to
Replying to @TimSweeneyEpic
I understand, we're both trying to offer guidance to the next generation. The thing is, speaking as an artist, we've been force fed NFT's, metaverse, blockchain and now AI. Let these things naturally take its course, they'll find their place (or not).
14
17
1
493
8,601
best one yet. they put all of Pinterest in this thing
MOSS Image mix texture with picture, paper and glitters
1
71
These pics look noticeably better than GPT-Image 2.5 comeback time?
This is probably GPT Image 3 then aurora-red-alpha is a faster model but worse quality aurora-green-alpha is slower and better quality Haven't managed to test blue out yet
1
50
It's time to move to Metal on Apple Silicon @ComfyUI You are leaving so much performance on the ground by using MPS. I bet you can migrate easily leveraging AI 😉
10
3
82
7,437
MOSS-Image by @Open_MOSS now runs smoothly on a 16GB Mac. Go experiment with it! huggingface.co/VisualInferen…
MOSS-Image is the beautiful open image model that writes long English and Chinese text Introducing the best port to MLX. Mine vs mlx-vlm’s: – 4x lower peak memory (9.3 vs 38.7 GB) – half the download – zero text loss at 8-bit – same seed makes same pic as OpenMOSS samples 🧵
91
Round of applause for MOSS-Image everyone
MOSS-Image Base vs SFT both Seed 42, 50 steps had so much fun with this theme 🤣 this one prefer the base version prompts below
1
130
MOSS-Image is the beautiful open image model that writes long English and Chinese text Introducing the best port to MLX. Mine vs mlx-vlm’s: – 4x lower peak memory (9.3 vs 38.7 GB) – half the download – zero text loss at 8-bit – same seed makes same pic as OpenMOSS samples 🧵
1
1
3
251
Speed is the one drawback: a 1024² image at the official 50 steps takes ~12 min on an M4 Pro. That’s the model, not the port, though. It has to do 100 passes through a 5B DiT, and mlx-vlm takes the same ~12 min (mine is within 5%). But don't worry, a few-step turbo is already in the works next so we can get this thing down to 1–2 min, max
1
1
31
MOSS-Image itself is gorgeous. Go try it out and give @Open_MOSS a follow! Demo: huggingface.co/spaces/OpenMO… Site: openmoss.ai/MOSS-Image/ Code: github.com/OpenMOSS/MOSS-Ima… ImageWeights: huggingface.co/OpenMOSS-Team… On a Mac: pip install moss-image-mlx MLX weights: huggingface.co/collections/V… My code: github.com/felix-ab/moss-ima…
75
in 2026 you can't say "neurodivergent" anymore. the proper term is "transformer-based minds"
2
81
I’m proposing this bargain for my environmental econ class and would love your opinion. Would you pay $25 to help a farmer delay mowing so birds have time to nest? Read the deal and vote 'YES', 'NO', or 'YES IF'. This is just as a thought experiment :) buy-time-for-birds-felix.bre…
2
36
You need to see it to believe it
Moss Img 🙂 canon LoRA Canon shot styled image gen huggingface.co/Danrisi/canon…
1
50