Sayak Paul
@RisingSayak
Oct 15
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
8
12
89
10,286
Sayak Paul
@RisingSayak
Oct 15
Replying to @RisingSayak
The model is capable of regular T2I and I2I workflows. But it can also do layout control!

This means we can specify bounding box coordinates in the prompt and take precise control of how we want things in the outputs.
2
0
2
556
Sayak Paul
@RisingSayak
Oct 15
Replying to @RisingSayak
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!

Oct 15, 2026 · 3:50 PM UTC

1
0
2
394
Sayak Paul
@RisingSayak
Oct 15
Replying to @RisingSayak
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 :)
0
1
3
300
RepliesRelevant