FLUX.1 [schnell] 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 [schnell] FP8 is deployed as a Flumina app. See for more details: https://huggingface.co/fireworks-ai/FLUX.1-schnell-fp8-flumina
ServerlessDocs | FLUX.1 [schnell] 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 [schnell] FP8 is a 12-billion parameter image generation model developed by Black Forest Labs. It is a rectified flow transformer trained to generate images from text prompts. The FP8 variant uses reduced-precision floating point (FP8) numerics to deliver approximately 2× faster inference.
FLUX.1 [schnell] FP8 is optimized for:
FLUX.1 [schnell] FP8 has 12 billion parameters.
No, fine-tuning is not supported for this model.
The model is licensed under the Apache License 2.0, permitting commercial use.