File size: 1,798 Bytes
161e2ab |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
import model_loader
import pipeline
from PIL import Image
from pathlib import Path
from transformers import CLIPTokenizer
import torch
DEVICE = "cpu"
ALLOW_CUDA = True
ALLOW_MPS = False
if torch.cuda.is_available() and ALLOW_CUDA:
DEVICE = "cuda"
print(f"Using device: {DEVICE}")
tokenizer = CLIPTokenizer("../data/tokenizer_vocab.json", merges_file="../data/tokenizer_merges.txt")
model_file = "../data/v1-5-pruned-emaonly.ckpt"
models = model_loader.preload_models_from_standard_weights(model_file, device=DEVICE)
## TEXT TO IMAGE
# prompt = "A dog with sunglasses, wearing comfy hat, looking at camera, highly detailed, ultra sharp, cinematic, 100mm lens, 8k resolution."
prompt = "A cat stretching on the floor, highly detailed, ultra sharp, cinematic, 100mm lens, 8k resolution."
uncond_prompt = "" # Also known as negative prom pt
do_cfg = True
cfg_scale = 8 # min: 1, max: 14
## IMAGE TO IMAGE
input_image = None
# Comment to disable image to image
image_path = "../images/dog.jpg"
# input_image = Image.open(image_path)
# Higher values means more noise will be added to the input image, so the result will further from the input image.
# Lower values means less noise is added to the input image, so output will be closer to the input image.
strength = 0.9
## SAMPLER
sampler = "ddpm"
num_inference_steps = 2
seed = 42
output_image = pipeline.generate(
prompt=prompt,
uncond_prompt=uncond_prompt,
input_image=input_image,
strength=strength,
do_cfg=do_cfg,
cfg_scale=cfg_scale,
sampler_name=sampler,
n_inference_steps=num_inference_steps,
seed=seed,
models=models,
device=DEVICE,
idle_device="cpu",
tokenizer=tokenizer,
)
# Combine the input image and the output image into a single image.
Image.fromarray(output_image) |