Instructions to use uifkus/Piranesi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use uifkus/Piranesi with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("uifkus/Piranesi") prompt = "\"portrait\", \"a colossal automated warehouse, towering shelving racks full of boxes, conveyor belt bridges crossing in the air, robotic lifts and chains, tiny workers far below\"" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Piranesi

- Prompt
- "portrait", "a colossal automated warehouse, towering shelving racks full of boxes, conveyor belt bridges crossing in the air, robotic lifts and chains, tiny workers far below"
- Negative Prompt
- NEG = ('color, colorful, painting, photo, photograph, 3d render, cgi, blurry, low quality, ' 'text, letters, watermark, signature, frame, border') SIZES = {'landscape': (1216, 832), 'portrait': (832, 1216), 'square': (1024, 1024)}

- Prompt
- "landscape", "a deep underground metro interchange, criss-crossing escalators and stairways, massive concrete pillars and vaults, hanging lamps, crowds of tiny commuters"
- Negative Prompt
- NEG = ('color, colorful, painting, photo, photograph, 3d render, cgi, blurry, low quality, ' 'text, letters, watermark, signature, frame, border') SIZES = {'landscape': (1216, 832), 'portrait': (832, 1216), 'square': (1024, 1024)}

- Prompt
- "landscape", "a container port at the edge of the sea, colossal gantry cranes, stacks of shipping containers, a giant container ship, chains and ropes, broad stairs to the water, tiny dock workers"
- Negative Prompt
- NEG = ('color, colorful, painting, photo, photograph, 3d render, cgi, blurry, low quality, ' 'text, letters, watermark, signature, frame, border') SIZES = {'landscape': (1216, 832), 'portrait': (832, 1216), 'square': (1024, 1024)}
Model description
grvr style
Trigger words
You should use grvr style to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 13
Model tree for uifkus/Piranesi
Base model
stabilityai/stable-diffusion-xl-base-1.0