Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

krea
/
Krea-2-Turbo

Text-to-Image
Diffusers
Safetensors
English
Krea2Pipeline
Model card Files Files and versions
xet
Community
25

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
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Running Krea 2 Turbo natively on Mac (Swift/Metal, no Python

#25 opened 10 days ago by
gwenn-ha-dev

Anime+ cartoon

#23 opened about 1 month ago by
zak01010101

Badaramoni Realism Fusion β€” mixed LoRA + LoKR merge for Krea 2 Turbo

#22 opened about 2 months ago by
badaramoni

Run on <4gb Vram.

πŸ‘πŸ”₯ 2
1
#21 opened about 2 months ago by
Jit2024

Krea 2 is really bad with anime

1
#20 opened 2 months ago by
zak01010101

Update README.md

#19 opened 3 months ago by
Anon252008

Windows Nvidia 1 Click Install

#18 opened 3 months ago by
Redtash1

The pictures generated by Krea2 have no expressions.

πŸ˜” 6
2
#16 opened 4 months ago by
wange1002

New

1
#11 opened 4 months ago by
Spdzio

Training LoRA for Krea 2 Turbo w/Training Adapter with AI-Toolkit

❀️ 5
5
#10 opened 4 months ago by
natural-light

No Controlnet Available

#9 opened 4 months ago by
abline11

Edit variant

πŸ‘ 2
2
#8 opened 4 months ago by
Osony1

bad image when rendering Chinese text

1
#7 opened 4 months ago by
ydayda

give me a photo of the sea

#5 opened 4 months ago by
yazidALA

System Prompt

πŸ”₯πŸ‘ 17
1
#4 opened 4 months ago by
rzgar

Prompts skills

4
#3 opened 4 months ago by
Ian0707

VRAM

11
#2 opened 4 months ago by
AminTz
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs