Image-to-Image
Diffusers
Safetensors
Diffusion Single File
English
Flux2Pipeline
image-generation
image-editing
flux
Instructions to use CaaretAI/FLUX.2-dev-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
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] - Diffusion Single File
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
- Notebooks
- Google Colab
- Kaggle
Download caaret_fp8_meta.json from CaaretAI/FLUX.2-dev-FP8: direct link, hf CLI and curl.
- Browser
- Download file 292 Bytes
-
https://huggingface.co/CaaretAI/FLUX.2-dev-FP8/resolve/main/caaret_fp8_meta.json
- Command line
-
hf download hf://CaaretAI/FLUX.2-dev-FP8/caaret_fp8_meta.json
-
curl -L -o caaret_fp8_meta.json https://huggingface.co/CaaretAI/FLUX.2-dev-FP8/resolve/main/caaret_fp8_meta.json
292 Bytes
| { | |
| "source": "/workspace/flux2-bf16", | |
| "components_fp8": [ | |
| "transformer" | |
| ], | |
| "format": "float8_e4m3fn + <name>_fp8_scale", | |
| "mining": "runtime image_mine.py hooks \u2014 not this conversion", | |
| "note": "Loaders that do not understand float8 may need a cast back using _fp8_scale" | |
| } | |