Models⚡
FLUX.1 [dev]
Released Aug 1, 2024FLUX.2 [klein] 4B/9B
The most advanced open image model: excellent prompt adherence, solid anatomy, full fine-tuning. The standard for serious work.
ImmaginiDiffusionFLUX
Back to resources
FLUX.1 [schnell]
Released on Aug 1, 2024
Very few steps, high quality, and strong text rendering. The distilled FLUX variant, built for speed.
Features
- Few steps
- Strong text rendering
- 12-16GB VRAM
- Apache license
Version history
- FLUX.2 [klein] 4B/9BLatest
Famiglia compatta distillata in ~4 step per GPU consumer; la variante 4B è Apache 2.0, la 9B non commerciale.
- FLUX.2 [dev]
Seconda generazione da 32B parametri (VLM Mistral-3 + rectified flow transformer) con supporto multi-riferimento fino a 10 immagini e output 4MP.
- FLUX.1 Kontext [dev]
Modello di editing/contesto da 12B parametri che modifica immagini seguendo il prompt, con pesi disponibili su Hugging Face.
- FLUX.1 [schnell]
Variante veloce distillata (4 step) rilasciata sotto Apache 2.0 in occasione del debutto di Black Forest Labs.
Tags
Useful links
Discover FLUX.1 [schnell]
Visit the official site to download, learn more and start using FLUX.1 [schnell].
Related resources — Models
Models🧠
5ak3t/ej
Released Oct 8, 2026
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.
DecisioniOn-deviceClassificazioneOpen-weights
Models🎵
ACE-Step
Released Apr 28, 2025ACE-Step v1.5 XL
The newest open music model with excellent control over lyrics and styles: generates complete songs with lyrics in many languages, including Italian.
MusicaLyricsOpen Source