File size: 15,895 Bytes
186aa49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
# Copyright 2026 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 ..modular_pipeline import AutoPipelineBlocks, SequentialPipelineBlocks
from ..modular_pipeline_utils import OutputParam
from .before_denoise import (
    AnimaImageInputStep,
    AnimaImg2ImgPrepareLatentsStep,
    AnimaImg2ImgSetTimestepsStep,
    AnimaPrepareLatentsStep,
    AnimaSetTimestepsStep,
    AnimaTextConditioningStep,
    AnimaTextInputStep,
)
from .decoders import AnimaProcessImagesOutputStep, AnimaVaeDecoderStep
from .denoise import AnimaDenoiseStep
from .encoders import AnimaImg2ImgVaeEncoderStep, AnimaTextEncoderStep


# auto_docstring
class AnimaCoreDenoiseStep(SequentialPipelineBlocks):
    """
    Denoise block that takes encoded Anima text inputs and runs the denoising process.

      Components:
          text_conditioner (`AnimaTextConditioner`) transformer (`CosmosTransformer3DModel`) scheduler
          (`FlowMatchEulerDiscreteScheduler`) guider (`ClassifierFreeGuidance`)

      Inputs:
          qwen_prompt_embeds (`Tensor`):
              Qwen prompt embeddings generated by the text encoder step.
          qwen_attention_mask (`Tensor`):
              Qwen prompt attention mask generated by the text encoder step.
          t5_input_ids (`Tensor`):
              T5 prompt token ids generated by the text encoder step.
          t5_attention_mask (`Tensor`):
              T5 prompt attention mask generated by the text encoder step.
          negative_qwen_prompt_embeds (`Tensor`, *optional*):
              Negative Qwen prompt embeddings generated by the text encoder step.
          negative_qwen_attention_mask (`Tensor`, *optional*):
              Negative Qwen prompt attention mask generated by the text encoder step.
          negative_t5_input_ids (`Tensor`, *optional*):
              Negative T5 prompt token ids generated by the text encoder step.
          negative_t5_attention_mask (`Tensor`, *optional*):
              Negative T5 prompt attention mask generated by the text encoder step.
          num_images_per_prompt (`int`, *optional*, defaults to 1):
              The number of images to generate per prompt.
          height (`int`, *optional*):
              The height in pixels of the generated image.
          width (`int`, *optional*):
              The width in pixels of the generated image.
          latents (`Tensor`, *optional*):
              Pre-generated noisy latents for image generation.
          generator (`Generator`, *optional*):
              Torch generator for deterministic generation.
          num_inference_steps (`int`, *optional*, defaults to 50):
              The number of denoising steps.
          sigmas (`list`, *optional*):
              Custom sigmas for the denoising process.
          **denoiser_input_fields (`None`, *optional*):
              The conditional model inputs for the Anima denoiser.

      Outputs:
          latents (`Tensor`):
              Denoised latents.
    """

    block_classes = [
        AnimaTextConditioningStep,
        AnimaTextInputStep,
        AnimaPrepareLatentsStep,
        AnimaSetTimestepsStep,
        AnimaDenoiseStep,
    ]
    block_names = ["text_conditioning", "input", "prepare_latents", "set_timesteps", "denoise"]

    @property
    def description(self) -> str:
        return "Denoise block that takes encoded Anima text inputs and runs the denoising process."

    @property
    def outputs(self):
        return [OutputParam.template("latents")]


# auto_docstring
class AnimaDecodeStep(SequentialPipelineBlocks):
    """
    Decode Anima latents into generated images.

      Components:
          vae (`AutoencoderKLQwenImage`) image_processor (`VaeImageProcessor`)

      Inputs:
          latents (`Tensor`):
              Denoised Anima latents.
          output_type (`str`, *optional*, defaults to pil):
              Output format: 'pil', 'np', 'pt'.

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

    block_classes = [AnimaVaeDecoderStep, AnimaProcessImagesOutputStep]
    block_names = ["decode", "postprocess"]

    @property
    def description(self) -> str:
        return "Decode Anima latents into generated images."

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


# auto_docstring
class AnimaImg2ImgCoreDenoiseStep(SequentialPipelineBlocks):
    """
    Denoise block for Anima image-to-image generation. Uses image_latents already in state from
    AnimaImg2ImgVaeEncoderStep.

      Components:
          text_conditioner (`AnimaTextConditioner`) transformer (`CosmosTransformer3DModel`) scheduler
          (`FlowMatchEulerDiscreteScheduler`) guider (`ClassifierFreeGuidance`)

      Inputs:
          qwen_prompt_embeds (`Tensor`):
              Qwen prompt embeddings generated by the text encoder step.
          qwen_attention_mask (`Tensor`):
              Qwen prompt attention mask generated by the text encoder step.
          t5_input_ids (`Tensor`):
              T5 prompt token ids generated by the text encoder step.
          t5_attention_mask (`Tensor`):
              T5 prompt attention mask generated by the text encoder step.
          negative_qwen_prompt_embeds (`Tensor`, *optional*):
              Negative Qwen prompt embeddings generated by the text encoder step.
          negative_qwen_attention_mask (`Tensor`, *optional*):
              Negative Qwen prompt attention mask generated by the text encoder step.
          negative_t5_input_ids (`Tensor`, *optional*):
              Negative T5 prompt token ids generated by the text encoder step.
          negative_t5_attention_mask (`Tensor`, *optional*):
              Negative T5 prompt attention mask generated by the text encoder step.
          num_images_per_prompt (`int`, *optional*, defaults to 1):
              The number of images to generate per prompt.
          image_latents (`Tensor`):
              image latents used to guide the image generation. Can be generated from vae_encoder step.
          height (`int`, *optional*):
              The height in pixels of the generated image.
          width (`int`, *optional*):
              The width in pixels of the generated image.
          num_inference_steps (`int`, *optional*, defaults to 50):
              The number of denoising steps.
          sigmas (`list`, *optional*):
              Custom sigmas for the denoising process.
          strength (`float`, *optional*, defaults to 0.9):
              Strength for img2img/inpainting.
          generator (`Generator`, *optional*):
              Torch generator for deterministic generation.
          latents (`Tensor`, *optional*):
              Pre-generated noisy latents for image generation.
          **denoiser_input_fields (`None`, *optional*):
              The conditional model inputs for the Anima denoiser.

      Outputs:
          latents (`Tensor`):
              Denoised latents.
    """

    block_classes = [
        AnimaTextConditioningStep,
        AnimaTextInputStep,
        AnimaImageInputStep,
        AnimaImg2ImgSetTimestepsStep,
        AnimaImg2ImgPrepareLatentsStep,
        AnimaDenoiseStep,
    ]
    block_names = ["text_conditioning", "input", "image_input", "set_timesteps", "prepare_latents", "denoise"]

    @property
    def description(self) -> str:
        return (
            "Denoise block for Anima image-to-image generation. "
            "Uses image_latents already in state from AnimaImg2ImgVaeEncoderStep."
        )

    @property
    def outputs(self):
        return [OutputParam.template("latents")]


# auto_docstring
class AnimaAutoCoreDenoiseStep(AutoPipelineBlocks):
    """
    Denoise step that selects between text-to-image and image-to-image denoising based on whether image_latents is
    present in state. - `AnimaCoreDenoiseStep` (text2image) is used when no image_latents are present. -
    `AnimaImg2ImgCoreDenoiseStep` (img2img) is used when image_latents are present.

      Components:
          text_conditioner (`AnimaTextConditioner`) transformer (`CosmosTransformer3DModel`) scheduler
          (`FlowMatchEulerDiscreteScheduler`) guider (`ClassifierFreeGuidance`)

      Inputs:
          qwen_prompt_embeds (`Tensor`):
              Qwen prompt embeddings generated by the text encoder step.
          qwen_attention_mask (`Tensor`):
              Qwen prompt attention mask generated by the text encoder step.
          t5_input_ids (`Tensor`):
              T5 prompt token ids generated by the text encoder step.
          t5_attention_mask (`Tensor`):
              T5 prompt attention mask generated by the text encoder step.
          negative_qwen_prompt_embeds (`Tensor`, *optional*):
              Negative Qwen prompt embeddings generated by the text encoder step.
          negative_qwen_attention_mask (`Tensor`, *optional*):
              Negative Qwen prompt attention mask generated by the text encoder step.
          negative_t5_input_ids (`Tensor`, *optional*):
              Negative T5 prompt token ids generated by the text encoder step.
          negative_t5_attention_mask (`Tensor`, *optional*):
              Negative T5 prompt attention mask generated by the text encoder step.
          num_images_per_prompt (`int`, *optional*, defaults to 1):
              The number of images to generate per prompt.
          image_latents (`Tensor`, *optional*):
              image latents used to guide the image generation. Can be generated from vae_encoder step.
          height (`int`, *optional*):
              The height in pixels of the generated image.
          width (`int`, *optional*):
              The width in pixels of the generated image.
          num_inference_steps (`int`):
              The number of denoising steps.
          sigmas (`list`, *optional*):
              Custom sigmas for the denoising process.
          strength (`float`, *optional*, defaults to 0.9):
              Strength for img2img/inpainting.
          generator (`Generator`, *optional*):
              Torch generator for deterministic generation.
          latents (`Tensor`):
              Pre-generated noisy latents for image generation.
          **denoiser_input_fields (`None`, *optional*):
              The conditional model inputs for the Anima denoiser.

      Outputs:
          latents (`Tensor`):
              Denoised latents.
    """

    block_classes = [AnimaImg2ImgCoreDenoiseStep, AnimaCoreDenoiseStep]
    block_names = ["img2img", "text2image"]
    block_trigger_inputs = ["image_latents", None]

    @property
    def description(self) -> str:
        return (
            "Denoise step that selects between text-to-image and image-to-image denoising based on whether "
            "image_latents is present in state."
            " - `AnimaCoreDenoiseStep` (text2image) is used when no image_latents are present."
            " - `AnimaImg2ImgCoreDenoiseStep` (img2img) is used when image_latents are present."
        )


# auto_docstring
class AnimaAutoVaeImageEncoderStep(AutoPipelineBlocks):
    """
    VAE Image Encoder step that encodes the input image to produce image_latents. Skipped when no image is provided
    (text-to-image workflow).

      Components:
          vae (`AutoencoderKLQwenImage`) image_processor (`VaeImageProcessor`)

      Inputs:
          image (`Image | list`, *optional*):
              Reference image(s) for denoising. Can be a single image or list of images.
          height (`int`, *optional*):
              The height in pixels of the generated image.
          width (`int`, *optional*):
              The width in pixels of the generated image.
          generator (`Generator`, *optional*):
              Torch generator for deterministic generation.

      Outputs:
          image_latents (`Tensor`):
              Encoded image latents.
          height (`int`):
              Image height used for generation.
          width (`int`):
              Image width used for generation.
    """

    block_classes = [AnimaImg2ImgVaeEncoderStep]
    block_names = ["vae_encoder"]
    block_trigger_inputs = ["image"]

    @property
    def description(self) -> str:
        return (
            "VAE Image Encoder step that encodes the input image to produce image_latents. "
            "Skipped when no image is provided (text-to-image workflow)."
        )


# auto_docstring
class AnimaAutoBlocks(SequentialPipelineBlocks):
    """
    Auto Modular pipeline for text-to-image and image-to-image generation using Anima.

      Supported workflows:
        - `text2image`: requires `prompt`
        - `img2img`: requires `image`, `prompt`

      Components:
          text_encoder (`Qwen3Model`) tokenizer (`Qwen2Tokenizer`) t5_tokenizer (`T5Tokenizer`) guider
          (`ClassifierFreeGuidance`) vae (`AutoencoderKLQwenImage`) image_processor (`VaeImageProcessor`)
          text_conditioner (`AnimaTextConditioner`) transformer (`CosmosTransformer3DModel`) scheduler
          (`FlowMatchEulerDiscreteScheduler`)

      Inputs:
          prompt (`str`):
              The prompt or prompts to guide image generation.
          negative_prompt (`str`, *optional*):
              The prompt or prompts not to guide the image generation.
          max_sequence_length (`int`, *optional*, defaults to 512):
              Maximum sequence length for prompt encoding.
          image (`Image | list`, *optional*):
              Reference image(s) for denoising. Can be a single image or list of images.
          height (`int`, *optional*):
              The height in pixels of the generated image.
          width (`int`, *optional*):
              The width in pixels of the generated image.
          generator (`Generator`, *optional*):
              Torch generator for deterministic generation.
          num_images_per_prompt (`int`, *optional*, defaults to 1):
              The number of images to generate per prompt.
          image_latents (`Tensor`, *optional*):
              image latents used to guide the image generation. Can be generated from vae_encoder step.
          num_inference_steps (`int`):
              The number of denoising steps.
          sigmas (`list`, *optional*):
              Custom sigmas for the denoising process.
          strength (`float`, *optional*, defaults to 0.9):
              Strength for img2img/inpainting.
          latents (`Tensor`):
              Pre-generated noisy latents for image generation.
          **denoiser_input_fields (`None`, *optional*):
              The conditional model inputs for the Anima denoiser.
          output_type (`str`, *optional*, defaults to pil):
              Output format: 'pil', 'np', 'pt'.

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

    block_classes = [
        AnimaTextEncoderStep,
        AnimaAutoVaeImageEncoderStep,
        AnimaAutoCoreDenoiseStep,
        AnimaDecodeStep,
    ]
    block_names = ["text_encoder", "vae_encoder", "denoise", "decode"]
    _workflow_map = {
        "text2image": {"prompt": True},
        "img2img": {"image": True, "prompt": True},
    }

    @property
    def description(self) -> str:
        return "Auto Modular pipeline for text-to-image and image-to-image generation using Anima."

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