Very few steps, high quality, and strong text rendering. The distilled FLUX variant, built for speed.
FLUX.1 [dev]
Released on Aug 1, 2024
The most advanced open image model: excellent prompt adherence, solid anatomy, full fine-tuning. The standard for serious work.
Features
- Top-class quality
- Full fine-tuning
- 12-24GB VRAM
- Prompt adherence
Version history
- FLUX.2 [klein] 4B/9BLatest
Modelli distillati di piccole dimensioni per inferenza rapida in ~4 step su hardware consumer.
- FLUX.2 [dev]
Modello open-weight da 32B parametri per generazione e editing unificati, il più capace open per numero di parametri al rilascio.
- FLUX.1 Kontext [dev]
Varianti dev di editing/contesto da 12B parametri eseguibile su GPU consumer da 24GB di VRAM.
- FLUX.1 [dev]
Modello open-weight da 12B parametri (uso non commerciale) al lancio di Black Forest Labs, il più grande T2I open disponibile al momento.
Tags
Useful links
Discover FLUX.1 [dev]
Visit the official site to download, learn more and start using FLUX.1 [dev].
Related resources — Models
An 11.4MB (single-file) System-1 decision model built on an e5-small-v2 text encoder. 128MB resident-memory peak, runs on CPU. Given a state and typed questions, it returns a calibrated probability per option in one pass, without generating tokens. English-only.
The newest open music model with excellent control over lyrics and styles: generates complete songs with lyrics in many languages, including Italian.

