import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ValerianFourel/RealisticEmotionStableDiffusion", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This is a finetune of SG161222/Realistic_Vision_V6.0_B1_noVAE.
This project's aim is to leverage (text,image) pairs with descriptions of the picture alongside the emotions on a dataset of 35k images. We will release the metrics soons to verify the accuracy of the images compared to test values.
- Downloads last month
- 17