Black Forest Labs Releases FLUX.3 Image Klein, Now Available on Hugging Face Diffusers
Current overview (not historical)
Black Forest Labs has launched FLUX.3 Image Klein, an open‑weights image generation model that is now hosted on Hugging Face’s Diffusers library. The model supports text‑to‑image, multi‑reference image generation, and layout control via bounding‑box prompts, allowing users to dictate the placement of image elements. FLUX.3 Image Klein offers two checkpoints: a default Time‑Step distilled checkpoint that enables 16‑step fast inference without a classifier‑free guidance (CFG) parameter, and a base model checkpoint that requires 50 steps and uses CFG. The model is capable of native 4K output and pixel‑level editing, and it can run on consumer‑grade GPUs with only 8 GB of VRAM, making it accessible to a wide range of users.
Written with AI from the reporting · updated 10/15/2026
EventGraph Explorer
One time cutoff for reports, relations and evidence.
New at this step ·Black Forest Labs' FLUX 3 Image Klein Now Runs on Consumer GPUs
- Reports in replay
- 2
- First-party
- 1
- Sources
- 2
Reports first seen at this step · 1
- The Decoder · Third-partyBlack Forest Labs' FLUX 3 Image Klein Now Runs on Consumer GPUsOriginal source ↗
Discovery-time replay; the linked graph and evidence share this cutoff. The full overview and activity remain current.
Event developments
2 developments10/15/2026, 11:30:10 PM
FLUX.3 Image Klein Debuts in Hugging Face's DiffusersHugging Face Blog
10/16/2026, 1:51:12 AM
Black Forest Labs' FLUX 3 Image Klein Now Runs on Consumer GPUsThe Decoder
Filtered by first discovery; only representative reports already discovered by this cutoff are shown. Story grouping may have changed later, so this is not a complete historical snapshot.
Relations at this time
Loading time-scoped relations…
Bounded reconstruction, not an exact snapshot: entity names, relationship text and story grouping may include later revisions. Overview and full source archive below remain current.
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Oct 15, 00:00recorded Oct 15, 23:30single sourcerevised
Hugging Face 发布 FLUX.3 Image Klein 支持 Diffusers
Read original source ↗ Hugging Face BlogReplay this moment in the explorer - 2Oct 15, 00:00recorded Oct 16, 01:51single sourcerevised
Black Forest Labs 发布 FLUX 3 Image Klein 开源模型
Read original source ↗ The DecoderReplay this moment in the explorer
Uncertainty marks flag where to check the sources; they are not proven causation.
Full source archive (current)
Current public reports; outside the historical replay.
First-party sources · 1 reports
- Hugging Face Blog · Oct 15, 08:00FLUX.3 Image Klein Debuts in Hugging Face's Diffusers
Hugging Face introduces FLUX.3 Image Klein, a model capable of text-to-image, multi-reference image-to-image, and layout control, now available in Diffusers. The model supports bounding-box layout manipulation and offers a 1024x1024 image generation in approximately 2 seconds on an H100 GPU.
Read original source ↗
Independent coverage · 1 reports
- The Decoder · Oct 16, 00:57Black Forest Labs' FLUX 3 Image Klein Now Runs on Consumer GPUs
Black Forest Labs introduces FLUX 3 Image Klein, a 5.6-billion-parameter open model for text-to-image generation and editing, which runs on consumer GPUs with 8 GB VRAM, outperforming competitors in internal tests.
Read original source ↗
Different reports do not necessarily disagree. Check original sources and publication dates.
Report timeline
Explore every side through dated source reports.
- The DecoderSelectedBlack Forest Labs' FLUX 3 Image Klein Now Runs on Consumer GPUs
Black Forest Labs introduces FLUX 3 Image Klein, a 5.6-billion-parameter open model for text-to-image generation and editing, which runs on consumer GPUs with 8 GB VRAM, outperforming competitors in internal tests.
- Hugging Face BlogSelectedFLUX.3 Image Klein Debuts in Hugging Face's Diffusers
Hugging Face introduces FLUX.3 Image Klein, a model capable of text-to-image, multi-reference image-to-image, and layout control, now available in Diffusers. The model supports bounding-box layout manipulation and offers a 1024x1024 image generation in approximately 2 seconds on an H100 GPU.