opendiffusionai/cc12m-4mp-realistic
Viewer • Updated • 20.9k • 86 • 21
How to use suayptalha/Z-Image-Turbo-Realism-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("suayptalha/Z-Image-Turbo-Realism-LoRA")
prompt = "Realism, gritty portrait of a mechanic covered in grease and oil, wiping sweat from forehead, inside a dim garage, metallic textures in background, intense gaze, smoke in the air, volumetric lighting, raw and unfiltered."
image = pipe(prompt).images[0]





This is a LoRA fine-tuned adapter for the Z-Image-Turbo model, trained on the hand-selected subset of the well known C12M dataset. It specializes in generating high-quality ultra-realistic images.
diffusers pipelines.You should use Realism to trigger the image generation.
Download them in the Files & versions tab.
Base model
Tongyi-MAI/Z-Image-Turbo