Instructions to use AX1Y2JP/Krea-2-Turbo-INT8-ConvRot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AX1Y2JP/Krea-2-Turbo-INT8-ConvRot with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AX1Y2JP/Krea-2-Turbo-INT8-ConvRot", 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
⚠️ComfyUI's native int8 support only supports tensorwise, so this model won't work. Please continue to use int8-fast.
A Krea 2 model quantized to INT8 with ConvRot using a conservative quantization policy.
Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit https://krea.ai/krea-2-licensing.
- Downloads last month
- 863