Pinned Tweet
Had the honor to present diffusion transformers at CS25, Stanford. The place is truly magical.
Slides: bit.ly/dit-cs25
Recording: youtu.be/vXtapCFctTI?si=dlcE…
Thanks to @stevenyfeng for making it happen!
Sayak Paul retweeted
Everything we put into this model was designed to give creators the flexibility and speed to explore with precision.
In that spirit, we’re making Pika H3 Flex open source from day 1. You can find the code on GitHub, the weights on @huggingface, and start playing with it in @ComfyUI and diffusers right now.
Code: github.com/Pika-Labs/Pika-H3…
Weights: huggingface.co/Pika-Labs/Pik…
Diffusers:
huggingface.co/docs/diffuser…
ComfyUI: docs.comfy.org/tutorials/vid…
. @pika_labs just joined the crew and released a bunch of cool adapters post-trained on MiniMax H3: Pika H3 Flex!
Of course, it’s day-0 otherwise we are not balling!
Enjoy 😉
Everything we put into this model was designed to give creators the flexibility and speed to explore with precision.
In that spirit, we’re making Pika H3 Flex open source from day 1. You can find the code on GitHub, the weights on @huggingface, and start playing with it in @ComfyUI and diffusers right now.
Code: github.com/Pika-Labs/Pika-H3…
Weights: huggingface.co/Pika-Labs/Pik…
Diffusers:
huggingface.co/docs/diffuser…
ComfyUI: docs.comfy.org/tutorials/vid…
One difficulty users of Transformers & Diffusers faced was seamless operation on TPUs.
Over the past few months, Google has relentlessly worked on TorchTPU to bridge that gap. We ensured this was well supported by joining the efforts 🔥
huggingface.co/blog/hf-torch…
On the Kernels project, we shipped our own `kernels cache ls`.
It offers a better view of the variants stored per kernel version, going beyond what a standard `hf cache ls` offers.
Documentation:
huggingface.co/docs/kernels/…
What other CLI would you like in Kernels?
Completing 4 years today at @huggingface today! I am deeply grateful to call it my workplace 🤗
It has enabled a kind of growth that I wouldn't have thought for myself otherwise, even in my wildest dreams. But more importantly, it has made me kinder, more compassionate, and less complacent. I have nothing but gratitude.
I am writing this with a lot of emotions. They say "emotion clouds your judgement". But emotions only grow out of genuine places and this place is nothing but genuine! Genuine people, genuine work, and genuine impact (even the banters are genuine)!
I felt like it's a good time to remind myself of this portion from McConaughey's famous speech at the Oscars:
"So, to any of us, [...], whatever it is we look up to, whatever it is we look forward to, and whoever it is we're chasing, to that I say, 'Amen.' To that I say, 'Alright, alright, alright.'"
We secretly worked on bringing TorchTPU support to Diffusers with @Jhuaplin 🔥
It needed us to first ship TP support so that large models could fit in TPU chips. Then a bunch of small implementation-level changes.
Check out the post to know more:
huggingface.co/blog/hf-torch…
Sayak Paul retweeted
Meet Fibo 2.0 from @bria_ai_ 🔥
The #1 *open weights* model in image editing is supported in Diffusers (day-0, of course)!
1. JSON-native control
2. Pretty good text rendering
3. Comes in two variants: Turbo and Dev
Check out the model here:
huggingface.co/docs/diffuser…
We just merged the first protein sequence design model RFD4-Proteina in Diffusers 🔥
I hope this pushes the state of open BioML further.
Kudos to @NVIDIAAI and Baker Lab for shipping this!
Check out the docs to know more:
huggingface.co/docs/diffuser…
Cheers to @DidiKieran for leading the PR integration and bearing with our feedback. It's been a real treat!
Meet Fibo 2.0 from @bria_ai_ 🔥
The #1 *open weights* model in image editing is supported in Diffusers (day-0, of course)!
1. JSON-native control
2. Pretty good text rendering
3. Comes in two variants: Turbo and Dev
Check out the model here:
huggingface.co/docs/diffuser…
Some extended comments.
My main purpose for the trip was my talk on Kernels at the PyTorch Conference.
Reaching the US by a day's delay (which wouldn't anyway allow me to do the talk) only to leave after 4 days would have been too much.
So, I thought it's better I stay home and support the upcoming releases. Might as well enjoy the rest of the Durga Puja while it lasts.
Thanks to @qatarairways my US trip now stands canceled.
Somehow the Kolkata flight got delayed and that led them to choose an option for me which would land in SF at 1:15 PM 21st Oct (delayed by a day).
So, it forced me to ultimately cancel it.
Absolutely gutted for this. But maybe this is what Maa Durga wanted as I was leaving her amidst the festivities.
Thanks to @qatarairways my US trip now stands canceled.
Somehow the Kolkata flight got delayed and that led them to choose an option for me which would land in SF at 1:15 PM 21st Oct (delayed by a day).
So, it forced me to ultimately cancel it.
Absolutely gutted for this. But maybe this is what Maa Durga wanted as I was leaving her amidst the festivities.
Sayak Paul retweeted
It's time. It's fucking time!
Flux.3 Image Klein is out and we bring you full support for it in Diffusers.
Catch all the details in our post:
huggingface.co/blog/flux-3
It's time. It's fucking time!
Flux.3 Image Klein is out and we bring you full support for it in Diffusers.
Catch all the details in our post:
huggingface.co/blog/flux-3
Both the distilled and non-distilled pipelines are implemented as modular diffusers pipelines for maximum flexibility!
We have also worked hard to support loading the quantized checkpoints (FP8r and NVFP4) and performing inference with them.
We have even given them a backend of their own!
A release is incomplete without a LoRA training script.
We're providing Diffusers-native LoRA training scripts for both T2I and I2I. Thanks to @linoy_tsaban for tackling this!
We also support loading LoRAs trained with @ostrisai's ai-toolkit!
Enjoy :)
