EraseAnything/prompt_process.py at main · tomguluson92/EraseAnything · GitHub

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
import torch

def tokenize_prompt(tokenizer, prompt, max_sequence_length, add_special_tokens=False):
    text_inputs = tokenizer(
        prompt,
        padding="max_length",
        max_length=max_sequence_length,
        truncation=True,
        return_length=False,
        return_overflowing_tokens=False,
        add_special_tokens=add_special_tokens,
        return_tensors="pt",
    )
    text_input_ids = text_inputs.input_ids
    return text_input_ids


def _get_t5_prompt_embeds(
    text_encoder,
    tokenizer,
    max_sequence_length=512,
    prompt=None,
    num_images_per_prompt=1,
    device=None,
    text_input_ids=None,
):
    prompt = [prompt] if isinstance(prompt, str) else prompt
    batch_size = len(prompt)

    if tokenizer is not None:
        text_inputs = tokenizer(
            prompt,
            padding="max_length",
            max_length=max_sequence_length,
            truncation=True,
            return_length=False,
            return_overflowing_tokens=False,
            return_tensors="pt",
        )
        text_input_ids = text_inputs.input_ids
    else:
        if text_input_ids is None:
            raise ValueError("text_input_ids must be provided when the tokenizer is not specified")

    prompt_embeds = text_encoder(text_input_ids.to(device))[0]

    dtype = text_encoder.dtype
    prompt_embeds = prompt_embeds.to(dtype=dtype, device=device)

    _, seq_len, _ = prompt_embeds.shape

    # duplicate text embeddings and attention mask for each generation per prompt, using mps friendly method
    prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
    prompt_embeds = prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

    return prompt_embeds


def _get_clip_prompt_embeds(
    text_encoder,
    tokenizer,
    prompt: str,
    device=None,
    text_input_ids=None,
    num_images_per_prompt: int = 1,
):
    prompt = [prompt] if isinstance(prompt, str) else prompt
    batch_size = len(prompt)

    if tokenizer is not None:
        text_inputs = tokenizer(
            prompt,
            padding="max_length",
            max_length=77,
            truncation=True,
            return_overflowing_tokens=False,
            return_length=False,
            return_tensors="pt",
        )

        text_input_ids = text_inputs.input_ids
    else:
        if text_input_ids is None:
            raise ValueError("text_input_ids must be provided when the tokenizer is not specified")

    prompt_embeds = text_encoder(text_input_ids.to(device), output_hidden_states=False)

    # Use pooled output of CLIPTextModel
    prompt_embeds = prompt_embeds.pooler_output
    prompt_embeds = prompt_embeds.to(dtype=text_encoder.dtype, device=device)

    # duplicate text embeddings for each generation per prompt, using mps friendly method
    prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
    prompt_embeds = prompt_embeds.view(batch_size * num_images_per_prompt, -1)

    return prompt_embeds


def encode_prompt(
    text_encoders,
    tokenizers,
    prompt: str,
    max_sequence_length,
    device=None,
    num_images_per_prompt: int = 1,
    text_input_ids_list=None,
):
    prompt = [prompt] if isinstance(prompt, str) else prompt
    batch_size = len(prompt)
    dtype = text_encoders[0].dtype

    pooled_prompt_embeds = _get_clip_prompt_embeds(
        text_encoder=text_encoders[0],
        tokenizer=tokenizers[0],
        prompt=prompt,
        device=device if device is not None else text_encoders[0].device,
        num_images_per_prompt=num_images_per_prompt,
        text_input_ids=text_input_ids_list[0] if text_input_ids_list is not None else None,
    )

    prompt_embeds = _get_t5_prompt_embeds(
        text_encoder=text_encoders[1],
        tokenizer=tokenizers[1],
        max_sequence_length=max_sequence_length,
        prompt=prompt,
        num_images_per_prompt=num_images_per_prompt,
        device=device if device is not None else text_encoders[1].device,
        text_input_ids=text_input_ids_list[1] if text_input_ids_list is not None else None,
    )

    text_ids = torch.zeros(batch_size, prompt_embeds.shape[1], 3).to(device=device, dtype=dtype)
    text_ids = text_ids.repeat(num_images_per_prompt, 1, 1)

    return prompt_embeds, pooled_prompt_embeds, text_ids