import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ishengfang/Camera-Settings-as-Tokens-SD2")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Camera Settings as Tokens
[project page][demo][dataset][code]
To use this model, please go to this github repository: aiiu-lab/Camera-Settings-as-Tokens
TL;DR: Camera Settings 📷 + Text 📝 ⮕ Image 🖼️
Notice
This code and model are for research only. For other purposes, please contact us.
- Downloads last month
- 3
Model tree for ishengfang/Camera-Settings-as-Tokens-SD2
Base model
stabilityai/stable-diffusion-2