Jodh Singh (nvfp4)

ml @fal

[Jodh Singh (nvfp4) @jetjodh]

@zer0int1 thank you! i am gonna try scripts first, i am cli person.

[Jodh Singh (nvfp4) @jetjodh]

we test and ship ideas lightning fast too

[fal @fal]

Second part of our series on how we built one of the fastest image generation systems.
This time we dive into the diffusion pipeline and show how we hit 0.45s inference with kernel optimizations, quantization-aware distillation, and timestep distillation.
https://t.co/xID2Gv43be

[Jodh Singh (nvfp4) @jetjodh]

@zer0int1 code on your github yet?

[fal @fal]

First part of our series on how we built one of the fastest image generation systems, and we're kicking off with running LLMs (for prompt expansion) at >1000 tok/s by leveraging a DSpark adapter we trained from scratch!

https://t.co/qGFugOwCPo

[Jodh Singh (nvfp4) @jetjodh]

@tttraaacy @fal i will be in sf soon, so save one for me

[Jodh Singh (nvfp4) @jetjodh]

@sandylikesfrogs inday

[Jodh Singh (nvfp4) @jetjodh]

@Liv_Agar last 5 mins was more insane

[ilker @ailker]

🎨 I trained 999 Style LoRAs with the @fal Krea 2 Trainer.

Every single image in this video is a different LoRA.

That's 999 unique Style LoRAs, each trained for just 100 steps at 0.00035 LR, taking an average of ~30 seconds to train.

As I said before, @krea_ai 2 continues to prove that it's an incredible model for open-source Style LoRAs. Next week I'll be sharing even more LoRAs, along with a few surprises.

[Jodh Singh (nvfp4) @jetjodh]

@LazyKernel2025 @ailker @fal @krea_ai try our krea 2 trainer on fal then👀

[ilker @ailker]

Training LoRAs with Krea 2 on @fal has been the most fun I've had in a while.

Here are a few examples. In the next few days, I'll be releasing what is probably the largest public Style LoRA library built with Krea 2.

[Jodh Singh (nvfp4) @jetjodh]

@NagaSaiAbhinay 🤌

[fal @fal]

Krea 2 Open-Source is now available on fal

The most aesthetic open-source image model, released with open weights
Turbo delivers fast, polished text-to-image at low step counts
RAW serves as the malleable base checkpoint for LoRA training

[Jonathan Fischoff @jfischoff]

Houdini folks: we should talk

[Jodh Singh (nvfp4) @jetjodh]

@Sentdex unlimited mythos usage

[Joel ⚡ @gjoeldiaz]

Ya vi 36 partidos del mundial.. NECESITO MÁS LORD INFANTINO, QUE EL PRÓXIMO TENGA 80 SELECCIONES Y 18 HORAS DIARIAS DE PARTIDOS

[Ayomide 🧢 @Haryormdey4u]

i’m 27 years old in costco with my mom and she just ran into someone she knows

[Lovis Odin @OdinLovis]

Restyling mickey in realtime with @fal
source code : https://t.co/isxMfDuxE0

[Jodh Singh (nvfp4) @jetjodh]

@gorkem fal spa when?

[فُرات @jiminbas]

يمه 😭😭😭😭😭