import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("CCMat/fruins-ruins", dtype=torch.bfloat16, device_map="cuda")
prompt = "a photo of fruins ruins in Paris in front of the Arc de triomphe, mdjrny-v4 style"
image = pipe(prompt).images[0]DreamBooth model for the fruins concept trained on the CCMat/db-forest-ruins dataset.
This is a Stable Diffusion model fine-tuned on the fruins concept with DreamBooth. It can be used by modifying the instance_prompt: a photo of fruins ruins
This model was created as part of the DreamBooth Hackathon 🔥. Visit the organisation page for instructions on how to take part!
Description
This is a Stable Diffusion model fine-tuned on ruins images for the landscape theme.
Concept: fruins : forest ruins, greenery ruins
Pretrained Model: prompthero/openjourney
Learning rate: 1e-6
Usage
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained('CCMat/fruins-ruins')
image = pipeline().images[0]
image
Samples
Prompt: "a photo fruins ruins in Paris in front of the Arc de triomphe, in the 1970s, vivid colors"
Prompt: "high quality photo of Rome in fruins ruins with the Colosseum in the background"
Prompt: "fruins ruins in London near the Tower Bridge, professional photograph"
Prompt: "A futiristic post-apocalyptic town in fruins ruins trending on artstation, nostalgic lightning, unreal engine 5"
Prompt: "fruins ruins in Saint Petersburg, Sovietwave"
- Downloads last month
- 4