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 | Immediately run model on pre-configured GPUs and pay-per-token |
On-demand DeploymentDocs | On-demand deployments give you dedicated GPUs for FLUX.1 [dev] FP8 using Fireworks' reliable, high-performance system with no rate limits. |
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.
