How to use CaaretAI/FLUX.2-dev-FP8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CaaretAI/FLUX.2-dev-FP8", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0]
How to use CaaretAI/FLUX.2-dev-FP8 with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
https://huggingface.co/CaaretAI/FLUX.2-dev-FP8/resolve/main/CAARET_MINING.md
hf download hf://CaaretAI/FLUX.2-dev-FP8/CAARET_MINING.md
curl -L -o CAARET_MINING.md https://huggingface.co/CaaretAI/FLUX.2-dev-FP8/resolve/main/CAARET_MINING.md
Transformer weights stored as float8_e4m3fn with per-tensor *_fp8_scale companions.
float8_e4m3fn
*_fp8_scale
PoUW mining is applied at runtime by worker/agent/image_mine.py on eligible linears (K>=2048), independent of this storage format.
worker/agent/image_mine.py
