import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("WarmBloodAban/Krea2_Anything2RealCharacters-V1")
prompt = "transform the image to realistic photograph"
image = pipe(prompt).images[0]Krea2_Anything2RealCharacters-V1
- Prompt
- transform the image to realistic photograph
Model description
Trained on Krea2, this LoRA is designed to transform various artistic styles into high-quality realistic portraits.
Current Release: V1 Tech Preview (core style-transformation verification).
What’s Next: We are actively working on V2! Future updates will bring richer facial expressions and enhanced portrait editing capabilities. Stay tuned!
💡 Usage Guide Trigger Word: transform the image to realistic photograph
Recommended Base Model: Krea2 Turbo
Recommended Settings:
Steps: 10
CFG Scale: 1
Online Demo Link:https://www.runninghub.ai/zh-cn/ai-detail/2081336761087012866?inviteCode=rh-v1559
Trigger words
You should use transform the image to realistic photograph to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 470