Amazing. I think this is an understudied areas. The big labs if anything are disincentivized to make efficient models as currently access to compute is one of their moats. That's not the same for Chinese labs, which is why you see groundbreaking efficiency work mostly coming from China.
Really happy to see a small shop like yours doing this sort of work!
It looks really good! Except almost every hand is wrong. I'm guessing that's a training data thing? Can you tell us more about the 660M training images and prompts? Where did they come from and what do they cover? (I've seen the README say text was excluded.)
Wow this is really impressive. Throwing away the VAE feels counterintuitive - I'm shocked it works so well! Appreciate that you shared your training insights on the blog post!
Reminds me of this great paper where they trained a LLM that beats LLaMA2-13B from scratch with < $0.1M: https://arxiv.org/abs/2404.07413
What was the most difficult challenge for you guys with this project?
Also I'm a little intrigued on looking into efficiency techniques for video gen. What are current research directions in that field and promising directions you are particularly interested in? Any pointers for beginners?
I think there's a whole plethora of research on efficient attention implementations (similar to how DeepSeek & Kimi has made strides with theirs in LLMs) [1], [2]. And various techniques to reduce the flow-matching / diffusion iterations ("reflow") [3].
CVPR 2026 paper list (after filtering on video generation) might be a good start - asking LLMs to take a look and filter relevant papers sound even better.
Interesting. It does however seem to struggle with a lot of the typical t2i models struggle with.
Over smoothing, lots of uncanney shine, mangled limbs and such.
Impressive. Even the average number of fingers seems to be correct ;-)
Looking at the failures, I wonder how much cherry picking went into the showcase.
Congrats guys, this is super cool. I think if you built an arena where you can drive the cost even lower ($1K), it'd really get developers stoked.
Have you thought about setting up auto-research on this for smaller experiments? What's the minimum-viable budget for these types of workloads?
Amazing. I think this is an understudied areas. The big labs if anything are disincentivized to make efficient models as currently access to compute is one of their moats. That's not the same for Chinese labs, which is why you see groundbreaking efficiency work mostly coming from China.
Really happy to see a small shop like yours doing this sort of work!
HF link: https://huggingface.co/Linum-AI/pjit-21k
It looks really good! Except almost every hand is wrong. I'm guessing that's a training data thing? Can you tell us more about the 660M training images and prompts? Where did they come from and what do they cover? (I've seen the README say text was excluded.)
Wow this is really impressive. Throwing away the VAE feels counterintuitive - I'm shocked it works so well! Appreciate that you shared your training insights on the blog post!
Reminds me of this great paper where they trained a LLM that beats LLaMA2-13B from scratch with < $0.1M: https://arxiv.org/abs/2404.07413
What was the most difficult challenge for you guys with this project?
Also I'm a little intrigued on looking into efficiency techniques for video gen. What are current research directions in that field and promising directions you are particularly interested in? Any pointers for beginners?
I think there's a whole plethora of research on efficient attention implementations (similar to how DeepSeek & Kimi has made strides with theirs in LLMs) [1], [2]. And various techniques to reduce the flow-matching / diffusion iterations ("reflow") [3].
CVPR 2026 paper list (after filtering on video generation) might be a good start - asking LLMs to take a look and filter relevant papers sound even better.
[1] https://arxiv.org/abs/2609.15810 [2] https://arxiv.org/abs/2602.13515 [3] https://arxiv.org/abs/2605.23381
Interesting. It does however seem to struggle with a lot of the typical t2i models struggle with. Over smoothing, lots of uncanney shine, mangled limbs and such.
What are you using as your training data out of interest? Very impressive generation.
Impressive. Even the average number of fingers seems to be correct ;-) Looking at the failures, I wonder how much cherry picking went into the showcase.
This is awesome. Thanks for sharing weights on HF :-)
How many ladybugs are in training dataset?
What open source datasets did you use? Or did you pirate like the big labs ?
I wonder how this behaves when quantized, and how far are we from being able to run something like this purely in the browser with WebGPU.
If you swap the text encoder for something like T5-small or CLIP, this could be <2.5Gb at INT4; doable on a lot of machines.