Instructions to use krea/Krea-2-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use krea/Krea-2-Turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda") prompt = "A small, dark-colored cat is captured mid-stride, walking down the center of a narrow, abandoned street. The street is paved and appears cracked and worn. On either side of the street are tall, dilapidated buildings with visible brickwork and windows. A street lamp stands on the right side. The entire image is rendered in a monochromatic blue, with a distinct halftone dot pattern overlaying the scene, giving it a retro or printed appearance. The focus is soft, and the lighting is diffused, creating a hazy, atmospheric effect. The perspective is from ground level, looking down the length of the street, which narrows into the distance., halftone texture" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
The pictures generated by Krea2 have no expressions.
#16
by wange1002 - opened
After testing several sets of generated images, I found that Krea2 has poor control over the expressions of characters. It couldn't generate even some cute, playful, or sticking-out-the-tongue expressions. I also used the same prompt words in Zimage Turbo, and Zimage generated very well and could understand what is playful and cute. However, Krea2 completely failed to understand. Every time it generated an image, it was always one with a blank expression!
could you please share those prompts?

