File size: 3,208 Bytes
6efc195 9d64062 6efc195 |
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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 |
from PIL import Image
from IPython.display import display
import torch as th
from glide_text2im.download import load_checkpoint
from glide_text2im.model_creation import (
create_model_and_diffusion,
model_and_diffusion_defaults,
model_and_diffusion_defaults_upsampler
)
# Create base model.
options = model_and_diffusion_defaults()
options['use_fp16'] = has_cuda
options['timestep_respacing'] = '100' # use 100 diffusion steps for fast sampling
model, diffusion = create_model_and_diffusion(**options)
model.eval()
if has_cuda:
model.convert_to_fp16()
model.to(device)
model.load_state_dict(load_checkpoint('base', device))
print('total base parameters', sum(x.numel() for x in model.parameters()))
def show_images(batch: th.Tensor):
""" Display a batch of images inline. """
scaled = ((batch + 1)*127.5).round().clamp(0,255).to(th.uint8).cpu()
reshaped = scaled.permute(2, 0, 3, 1).reshape([batch.shape[2], -1, 3])
display(Image.fromarray(reshaped.numpy()))
# Sampling parameters
prompt = ""
batch_size = 1
guidance_scale = 3.0
# Tune this parameter to control the sharpness of 256x256 images.
# A value of 1.0 is sharper, but sometimes results in grainy artifacts.
upsample_temp = 0.997
import gradio as gr
def generate_image_from_text(prompt):
# Set the prompt text
prompt = prompt
##############################
# Sample from the base model #
##############################
# Create the text tokens to feed to the model.
tokens = model.tokenizer.encode(prompt)
tokens, mask = model.tokenizer.padded_tokens_and_mask(
tokens, options['text_ctx']
)
# Create the classifier-free guidance tokens (empty)
full_batch_size = batch_size * 2
uncond_tokens, uncond_mask = model.tokenizer.padded_tokens_and_mask(
[], options['text_ctx']
)
# Pack the tokens together into model kwargs.
model_kwargs = dict(
tokens=th.tensor(
[tokens] * batch_size + [uncond_tokens] * batch_size, device=device
),
mask=th.tensor(
[mask] * batch_size + [uncond_mask] * batch_size,
dtype=th.bool,
device=device,
),
)
# Create a classifier-free guidance sampling function
def model_fn(x_t, ts, **kwargs):
half = x_t[: len(x_t) // 2]
combined = th.cat([half, half], dim=0)
model_out = model(combined, ts, **kwargs)
eps, rest = model_out[:, :3], model_out[:, 3:]
cond_eps, uncond_eps = th.split(eps, len(eps) // 2, dim=0)
half_eps = uncond_eps + guidance_scale * (cond_eps - uncond_eps)
eps = th.cat([half_eps, half_eps], dim=0)
return th.cat([eps, rest], dim=1)
# Sample from the base model.
model.del_cache()
samples = diffusion.p_sample_loop(
model_fn,
(full_batch_size, 3, options["image_size"], options["image_size"]),
device=device,
clip_denoised=True,
progress=True,
model_kwargs=model_kwargs,
cond_fn=None,
)[:batch_size]
model.del_cache()
# Show the output
show_images(samples)
demo = gr.Interface(fn =generate_image_from_text,inputs ="text",outputs ="image")
demo.launch()
|