Instructions to use ProCreations/Image-2.1-Turbo-Calibrated-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ProCreations/Image-2.1-Turbo-Calibrated-FP8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ProCreations/Image-2.1-Turbo-Calibrated-FP8", 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
Release calibrated Image 2.1 Turbo FP8 transformer, accelerated SM120 runtime, quality evidence and real-time demo
ffc54ec verified Download reports/quantization_summary.json from ProCreations/Image-2.1-Turbo-Calibrated-FP8: direct link, hf CLI and curl.
- Browser
- Download file 311 Bytes
-
https://huggingface.co/ProCreations/Image-2.1-Turbo-Calibrated-FP8/resolve/main/reports/quantization_summary.json
- Command line
-
hf download hf://ProCreations/Image-2.1-Turbo-Calibrated-FP8/reports/quantization_summary.json
-
curl -L -o quantization_summary.json https://huggingface.co/ProCreations/Image-2.1-Turbo-Calibrated-FP8/resolve/main/reports/quantization_summary.json
311 Bytes
| { | |
| "quantized_modules": 224, | |
| "bf16_outliers": [], | |
| "transformer_bytes": 7261413376, | |
| "mean_diagnostic_nrmse": 0.017676136601961365, | |
| "max_diagnostic_nrmse": 0.033623486972181066, | |
| "gptq_selected": 224, | |
| "mean_fit_nrmse": 0.01752518390451643, | |
| "mean_nearest_fit_nrmse_same_alpha": 0.021777420390643766 | |
| } |