FLUX.1 [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. The FP8 version uses reduced precision numerics for 2x faster inference FLUX.1 [dev] FP8 is deployed as a Flumina app. See for more details: https://huggingface.co/fireworks-ai/FLUX.1-dev-fp8-flumina
ServerlessDocs | FLUX.1 [dev] FP8 is available via Fireworks' serverless API, where you pay per token. There are several ways to call the Fireworks API, including Fireworks' Python client, the REST API, or OpenAI's Python client. |
Run queries immediately, pay only for usage
FLUX.1 [dev] FP8 is a 12B parameter rectified flow transformer developed by Black Forest Labs. It is a diffusion-based image generation model deployed in FP8 precision (E4M3 format) for faster inference. This version is optimized for lightweight, high-speed deployment via Fireworks’ Flumina runtime.
The model is optimized for:
No, streaming and function calling are not supported.
The model has 12 billion parameters.
No, fine-tuning is not supported for this model.
The model is distributed under a custom FLUX.1 [dev] Non-Commercial License. Commercial use is not permitted without additional authorization.
