Instructions to use changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-AutoRound with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-AutoRound", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
File size: 392 Bytes
54daaf9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | {
"auto_round_commit": "8869842f9741538ea729849d5c23592bdb605e61",
"scheme": "MXFP8",
"iters": 0,
"disable_opt_rtn": true,
"encoder_coverage": [
"language_model.model.layers",
"vision_tower.transformer.layers",
"multi_modal_projector"
],
"transformer": "/home/changwa1/FLUX.2-dev-MXFP8-RTN-blocks-only/transformer",
"visual_task_validation": "not yet performed"
}
|