File size: 6,685 Bytes
cd458ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
# Copyright 2026 Krea AI and The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


from ...utils import logging
from ..modular_pipeline import SequentialPipelineBlocks
from ..modular_pipeline_utils import InsertableDict, OutputParam
from .before_denoise import (
    Krea2PrepareLatentsStep,
    Krea2PreparePositionIdsStep,
    Krea2SetTimestepsStep,
    Krea2TextInputsStep,
)
from .decoders import Krea2DecodeStep
from .denoise import Krea2DenoiseStep
from .encoders import Krea2TextEncoderStep


logger = logging.get_logger(__name__)  # pylint: disable=invalid-name


CORE_DENOISE_BLOCKS = InsertableDict(
    [
        ("input", Krea2TextInputsStep()),
        ("prepare_latents", Krea2PrepareLatentsStep()),
        ("set_timesteps", Krea2SetTimestepsStep()),
        ("prepare_position_ids", Krea2PreparePositionIdsStep()),
        ("denoise", Krea2DenoiseStep()),
    ]
)


# auto_docstring
class Krea2CoreDenoiseStep(SequentialPipelineBlocks):
    """
    Core denoising workflow for Krea 2 text-to-image: prepares the batch/latents/timesteps and the shared position ids,
    then runs the symmetric-CFG denoising loop, producing the denoised packed latents for the decoder.

      Components:
          transformer (`Krea2Transformer2DModel`) scheduler (`FlowMatchEulerDiscreteScheduler`) guider
          (`ClassifierFreeGuidance`)

      Inputs:
          num_images_per_prompt (`int`, *optional*, defaults to 1):
              The number of images to generate per prompt.
          prompt_embeds (`Tensor`):
              Per-prompt stacked text features (B, text_seq_len, num_text_layers, text_hidden_dim).
          prompt_embeds_mask (`Tensor`):
              Per-prompt boolean text mask (B, text_seq_len).
          negative_prompt_embeds (`Tensor`, *optional*):
              Per-prompt negative text features.
          negative_prompt_embeds_mask (`Tensor`, *optional*):
              Per-prompt negative text mask.
          latents (`Tensor`, *optional*):
              Pre-generated noisy latents for image generation.
          height (`int`, *optional*, defaults to 1024):
              The height in pixels of the generated image.
          width (`int`, *optional*, defaults to 1024):
              The width in pixels of the generated image.
          generator (`Generator`, *optional*):
              Torch generator for deterministic generation.
          num_inference_steps (`int`, *optional*, defaults to 28):
              The number of denoising steps.
          sigmas (`list`, *optional*):
              Custom sigma schedule (defaults to a linear ramp).
          attention_kwargs (`dict`, *optional*):
              Additional kwargs for attention processors.

      Outputs:
          latents (`Tensor`):
              The denoised packed latents (B, image_seq_len, in_channels).
    """

    model_name = "krea2"
    block_classes = list(CORE_DENOISE_BLOCKS.values())
    block_names = list(CORE_DENOISE_BLOCKS.keys())

    @property
    def description(self) -> str:
        return (
            "Core denoising workflow for Krea 2 text-to-image: prepares the batch/latents/timesteps and the shared "
            "position ids, then runs the symmetric-CFG denoising loop, producing the denoised packed latents for the "
            "decoder."
        )

    @property
    def outputs(self) -> list[OutputParam]:
        return [
            OutputParam.template("latents", description="The denoised packed latents (B, image_seq_len, in_channels).")
        ]


# auto_docstring
class Krea2AutoBlocks(SequentialPipelineBlocks):
    """
    Auto Modular pipeline for text-to-image generation using Krea 2: encode text -> core denoise (symmetric CFG) ->
    decode.

      Supported workflows:
        - `text2image`: requires `prompt`

      Components:
          text_encoder (`Qwen3VLModel`): The Qwen3-VL text encoder. tokenizer (`AutoTokenizer`): The tokenizer paired
          with the text encoder. guider (`ClassifierFreeGuidance`) transformer (`Krea2Transformer2DModel`) scheduler
          (`FlowMatchEulerDiscreteScheduler`) vae (`AutoencoderKLQwenImage`) image_processor (`VaeImageProcessor`)

      Inputs:
          prompt (`str`):
              The prompt or prompts to guide image generation.
          negative_prompt (`str`, *optional*):
              The negative prompt(s) for CFG.
          max_sequence_length (`int`, *optional*, defaults to 512):
              Maximum sequence length for prompt encoding.
          num_images_per_prompt (`int`, *optional*, defaults to 1):
              The number of images to generate per prompt.
          latents (`Tensor`, *optional*):
              Pre-generated noisy latents for image generation.
          height (`int`, *optional*, defaults to 1024):
              The height in pixels of the generated image.
          width (`int`, *optional*, defaults to 1024):
              The width in pixels of the generated image.
          generator (`Generator`, *optional*):
              Torch generator for deterministic generation.
          num_inference_steps (`int`, *optional*, defaults to 28):
              The number of denoising steps.
          sigmas (`list`, *optional*):
              Custom sigma schedule (defaults to a linear ramp).
          attention_kwargs (`dict`, *optional*):
              Additional kwargs for attention processors.
          output_type (`str`, *optional*, defaults to pil):
              Output format: 'pil', 'np', 'pt'.

      Outputs:
          images (`list`):
              Generated images.
    """

    model_name = "krea2"
    block_classes = [
        Krea2TextEncoderStep,
        Krea2CoreDenoiseStep,
        Krea2DecodeStep,
    ]
    block_names = ["text_encoder", "denoise", "decode"]

    _workflow_map = {
        "text2image": {"prompt": True},
    }

    @property
    def description(self) -> str:
        return (
            "Auto Modular pipeline for text-to-image generation using Krea 2: encode text -> core denoise "
            "(symmetric CFG) -> decode."
        )

    @property
    def outputs(self) -> list[OutputParam]:
        return [OutputParam.template("images")]