Artificial intelligence news.
Straight from the original announcements.

Hugging Face adds FLUX.3 Image Klein to its Diffusers library

October 15, 2026By the AI News Bites Editorial TeamSource: Hugging Face
Hugging Face adds FLUX.3 Image Klein to its Diffusers library
Image: Hugging Face

Hugging Face has published a blog post titled "Welcome FLUX.3 Image Klein in Diffusers", announcing support for the FLUX.3 Image Klein model family in its Diffusers library. The page lists two image-to-image models of 6B size alongside a dataset, two Spaces and a collection.

Key points
  • Hugging Face published "Welcome FLUX.3 Image Klein in Diffusers" on its blog.
  • Two models of 6B size, labelled image-to-image, are listed in the article.
  • The post references one dataset, two Spaces and a collection of 5 items.
  • Earlier Diffusers posts covered FLUX-2 (November 25, 2025) and FLUX.1-dev fine-tuning (June 19, 2025).

What the post covers

The post is titled "Welcome FLUX.3 Image Klein in Diffusers" and is published on the Hugging Face blog. Diffusers is Hugging Face's library for working with diffusion models, and the title indicates that FLUX.3 Image Klein can now be used through it.

The text available from the page is limited. It does not include the full technical description, so details such as architecture, licensing, benchmark results, hardware requirements and code examples cannot be reported here.

Models, datasets and Spaces

The page lists two models as mentioned in the article. Both are labelled as image-to-image models with a size of 6B. The listings show update times of "less than a minute ago" and "about 3 hours ago", which suggests the repositories were being actively updated around the time of publication.

  • Models: 2 mentioned in the article
  • Datasets: 1 mentioned in the article
  • Spaces: 2 mentioned in the article
  • Collections: 1 mentioned in the article, a group of 5 items

The Spaces are hosted demos on Hugging Face, and the collection bundles the related resources in one place. The page does not describe what each item does.

Part of a pattern of FLUX support in Diffusers

The post follows earlier Hugging Face articles on the FLUX family. The related reading section points to "Diffusers welcomes FLUX-2", dated November 25, 2025, which carries the tags diffusers, flux and quantization. It also links to "Fine-Tuning FLUX.1-dev on Consumer Hardware", dated June 19, 2025, tagged with guide, diffusers and quantization (LoRA).

Taken together, the posts show Hugging Face integrating successive FLUX releases into Diffusers, and the earlier articles dealt with practical topics such as quantization and fine-tuning on consumer hardware. Whether the FLUX.3 Image Klein post covers similar ground is not stated in the available text.

What it means for users

For developers who already use Diffusers, the announcement signals that FLUX.3 Image Klein is available in the library's ecosystem, with two 6B image-to-image models and demo Spaces to try. Anyone interested should read the full post on the Hugging Face blog for installation steps, usage instructions and licensing terms, none of which are included in the text reviewed here.

Related news

llama.cpp reaches v1.0.0 with a stable API and ABI policy
For developersNovember 13, 2026, 15:05

llama.cpp reaches v1.0.0 with a stable API and ABI policy

Hugging Face has released llama.cpp v1.0.0, marking the project’s first major version and setting clearer compatibility rules for developers building on its C and C++…

Hugging Face page lists LLMON in Granite 4.1 3B and 8B
ModelsNovember 12, 2026, 20:07

Hugging Face page lists LLMON in Granite 4.1 3B and 8B

Hugging Face has published a page titled “LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B.” The supplied page text identifies LLMON as an item…

Black Forest Labs releases FLUX 3 Image Klein, a 5.6B open weights modelTop story
ModelsOctober 15, 2026

Black Forest Labs releases FLUX 3 Image Klein, a 5.6B open weights model

Black Forest Labs has released FLUX 3 Image Klein, an open weights model with 5.6B parameters for text-to-image generation, image editing and multi-reference generation…