File size: 5,700 Bytes
03055f8
 
 
c8b1bf4
03055f8
 
 
 
 
694f32d
 
03055f8
33e0372
 
 
03055f8
 
694f32d
03055f8
 
33e0372
 
 
03055f8
 
 
 
 
 
 
 
 
 
 
 
33e0372
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
03055f8
 
33e0372
 
03055f8
33e0372
03055f8
 
 
 
 
33e0372
03055f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33e0372
 
03055f8
 
 
 
 
33e0372
 
03055f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
import torch
import numpy as np
from tqdm import tqdm
from sd.ddpm import DDPMSampler

def generate(
    prompt,
    uncond_prompt=None,
    input_image=None,
    strength=0.9,
    cfg_scale=8.0,
    n_inference_steps=50,
    width=512,
    height=512,
    generator=None,
    device=None,
    idle_device=None,
    models={},
    tokenizer=None,
):
    latents_width = width // 8
    latents_height = height // 8

    with torch.no_grad():
        if not 0 < strength <= 1:
            raise ValueError("strength must be between 0 and 1")

        if idle_device:
            to_idle = lambda x: x.to(idle_device)
        else:
            to_idle = lambda x: x

        clip = models["clip"]
        clip.to(device)
        
        # Convert into a list of length Seq_Len=77
        cond_tokens = tokenizer.batch_encode_plus(
            [prompt], padding="max_length", max_length=77
        ).input_ids
        # (Batch_Size, Seq_Len)
        cond_tokens = torch.tensor(cond_tokens, dtype=torch.long, device=device)
        # (Batch_Size, Seq_Len) -> (Batch_Size, Seq_Len, Dim)
        cond_context = clip(cond_tokens)
        # Convert into a list of length Seq_Len=77
        uncond_tokens = tokenizer.batch_encode_plus(
            [uncond_prompt], padding="max_length", max_length=77
        ).input_ids
        # (Batch_Size, Seq_Len)
        uncond_tokens = torch.tensor(uncond_tokens, dtype=torch.long, device=device)
        # (Batch_Size, Seq_Len) -> (Batch_Size, Seq_Len, Dim)
        uncond_context = clip(uncond_tokens)
        # (Batch_Size, Seq_Len, Dim) + (Batch_Size, Seq_Len, Dim) -> (2 * Batch_Size, Seq_Len, Dim)
        context = torch.cat([cond_context, uncond_context])
        to_idle(clip)

        sampler = DDPMSampler(generator)
        sampler.set_inference_timesteps(n_inference_steps)

        latents_shape = (1, 4, latents_height, latents_width)

        if input_image:
            encoder = models["encoder"]
            encoder.to(device)

            input_image_tensor = input_image.resize((width, height))
            # (Height, Width, Channel)
            input_image_tensor = np.array(input_image_tensor)
            # (Height, Width, Channel) -> (Height, Width, Channel)
            input_image_tensor = torch.tensor(input_image_tensor, dtype=torch.float32, device=device)
            # (Height, Width, Channel) -> (Height, Width, Channel)
            input_image_tensor = rescale(input_image_tensor, (0, 255), (-1, 1))
            # (Height, Width, Channel) -> (Batch_Size, Height, Width, Channel)
            input_image_tensor = input_image_tensor.unsqueeze(0)
            # (Batch_Size, Height, Width, Channel) -> (Batch_Size, Channel, Height, Width)
            input_image_tensor = input_image_tensor.permute(0, 3, 1, 2)

            # (Batch_Size, 4, Latents_Height, Latents_Width)
            encoder_noise = torch.randn(latents_shape, generator=generator, device=device)
            # (Batch_Size, 4, Latents_Height, Latents_Width)
            latents = encoder(input_image_tensor, encoder_noise)

            # Add noise to the latents (the encoded input image)
            # (Batch_Size, 4, Latents_Height, Latents_Width)
            sampler.set_strength(strength=strength)
            latents = sampler.add_noise(latents, sampler.timesteps[0])

            to_idle(encoder)
        else:
            # (Batch_Size, 4, Latents_Height, Latents_Width)
            latents = torch.randn(latents_shape, generator=generator, device=device)

        diffusion = models["diffusion"]
        diffusion.to(device)

        timesteps = tqdm(sampler.timesteps)
        for i, timestep in enumerate(timesteps):
            # (1, 320)
            time_embedding = get_time_embedding(timestep).to(device)

            # (Batch_Size, 4, Latents_Height, Latents_Width)
            model_input = latents

            # (Batch_Size, 4, Latents_Height, Latents_Width) -> (2 * Batch_Size, 4, Latents_Height, Latents_Width)
            model_input = model_input.repeat(2, 1, 1, 1)

            # model_output is the predicted noise
            # (Batch_Size, 4, Latents_Height, Latents_Width) -> (Batch_Size, 4, Latents_Height, Latents_Width)
            model_output = diffusion(model_input, context, time_embedding)

            output_cond, output_uncond = model_output.chunk(2)
            model_output = cfg_scale * (output_cond - output_uncond) + output_uncond

            # (Batch_Size, 4, Latents_Height, Latents_Width) -> (Batch_Size, 4, Latents_Height, Latents_Width)
            latents = sampler.step(timestep, latents, model_output)

        to_idle(diffusion)

        decoder = models["decoder"]
        decoder.to(device)
        # (Batch_Size, 4, Latents_Height, Latents_Width) -> (Batch_Size, 3, Height, Width)
        images = decoder(latents)
        to_idle(decoder)

        images = rescale(images, (-1, 1), (0, 255), clamp=True)
        # (Batch_Size, Channel, Height, Width) -> (Batch_Size, Height, Width, Channel)
        images = images.permute(0, 2, 3, 1)
        images = images.to("cpu", torch.uint8).numpy()
        return images[0]
    
def rescale(x, old_range, new_range, clamp=False):
    old_min, old_max = old_range
    new_min, new_max = new_range
    x -= old_min
    x *= (new_max - new_min) / (old_max - old_min)
    x += new_min
    if clamp:
        x = x.clamp(new_min, new_max)
    return x

def get_time_embedding(timestep):
    # Shape: (160,)
    freqs = torch.pow(10000, -torch.arange(start=0, end=160, dtype=torch.float32) / 160) 
    # Shape: (1, 160)
    x = torch.tensor([timestep], dtype=torch.float32)[:, None] * freqs[None]
    # Shape: (1, 160 * 2)
    return torch.cat([torch.cos(x), torch.sin(x)], dim=-1)