Flux2

FLUX.2 is a production-grade image generation model from Black Forest Labs that pairs a 9 billion parameter flow transformer with a vision-language model for deep contextual prompt understanding and high-fidelity image synthesis. Using rectified flow matching for efficient inference with fewer steps than standard diffusion, it delivers exceptional photorealism and compositional accuracy — and is supported by a large LoRA ecosystem and fine-tuning community.

Features

Serverless API

Flux.2 [klein] 4B is available via sciforium' serverless API. Use the REST API or OpenAI-compatible client libraries to generate images.

Docs

High-Speed Generation

Optimized rectified flow transformer architecture delivers fast image generation, ideal for interactive and real-time creative workflows.

Docs
MiniMax  M2.5
Kimi K2.5
GLM 5
DeepSeek V3.2
gpt-oss-120b
gpt-oss-20b
Qwen3 Instruct
Qwen3 Thinking
Qwen3 Coder
Qwen3.5
Qwen3 VL Instruct
Qwen3 ASR
Qwen-Image
Qwen-Image-Edit
Flux2
Stable Diffusion 3.5
Hunyuan Image
Z-Image
Wan2.2-I2V
Wan2.2-T2V
Hunyuan Image
Z-Image