Instructions to use pinecoresystems/Krea-2-Raw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use pinecoresystems/Krea-2-Raw with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("pinecoresystems/Krea-2-Raw", 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
Krea 2 Raw (ungated mirror)
Ungated mirror of krea/Krea-2-Raw, republished by TinyPine so it can be downloaded without a Hub gate. The weights are unmodified, byte for byte those of the source repository; verify by comparing each file's sha256 against the source's LFS oid.
Contents: the transformer/ folder only. RAW shares its text encoder, tokenizer, scheduler and VAE with Krea 2 Turbo (identical files), so load those from the Turbo mirror.
Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit https://krea.ai/krea-2-licensing.
By downloading or using these files you agree to be bound by the Krea 2 Community License
Agreement (LICENSE.pdf in this repository), including its Acceptable Use Policy and the
requirement that entities with $1,000,000 or more in trailing-twelve-month revenue obtain an
enterprise license from Krea before any commercial use.
Not an official Krea product and not endorsed by Krea.
- Downloads last month
- -