File size: 18,853 Bytes
b68ef84
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
from inspect import cleandoc
from typing import Optional
import logging
import torch

from typing_extensions import override
from comfy_api.latest import ComfyExtension, io as comfy_io
from comfy_api.input_impl.video_types import VideoFromFile
from comfy_api_nodes.apis import (
    MinimaxVideoGenerationRequest,
    MinimaxVideoGenerationResponse,
    MinimaxFileRetrieveResponse,
    MinimaxTaskResultResponse,
    SubjectReferenceItem,
    MiniMaxModel,
)
from comfy_api_nodes.apis.client import (
    ApiEndpoint,
    HttpMethod,
    SynchronousOperation,
    PollingOperation,
    EmptyRequest,
)
from comfy_api_nodes.apinode_utils import (
    download_url_to_bytesio,
    upload_images_to_comfyapi,
    validate_string,
)
from server import PromptServer


I2V_AVERAGE_DURATION = 114
T2V_AVERAGE_DURATION = 234


async def _generate_mm_video(
    *,
    auth: dict[str, str],
    node_id: str,
    prompt_text: str,
    seed: int,
    model: str,
    image: Optional[torch.Tensor] = None,   # used for ImageToVideo
    subject: Optional[torch.Tensor] = None, # used for SubjectToVideo
    average_duration: Optional[int] = None,
) -> comfy_io.NodeOutput:
    if image is None:
        validate_string(prompt_text, field_name="prompt_text")
    # upload image, if passed in
    image_url = None
    if image is not None:
        image_url = (await upload_images_to_comfyapi(image, max_images=1, auth_kwargs=auth))[0]

    # TODO: figure out how to deal with subject properly, API returns invalid params when using S2V-01 model
    subject_reference = None
    if subject is not None:
        subject_url = (await upload_images_to_comfyapi(subject, max_images=1, auth_kwargs=auth))[0]
        subject_reference = [SubjectReferenceItem(image=subject_url)]


    video_generate_operation = SynchronousOperation(
        endpoint=ApiEndpoint(
            path="/proxy/minimax/video_generation",
            method=HttpMethod.POST,
            request_model=MinimaxVideoGenerationRequest,
            response_model=MinimaxVideoGenerationResponse,
        ),
        request=MinimaxVideoGenerationRequest(
            model=MiniMaxModel(model),
            prompt=prompt_text,
            callback_url=None,
            first_frame_image=image_url,
            subject_reference=subject_reference,
            prompt_optimizer=None,
        ),
        auth_kwargs=auth,
    )
    response = await video_generate_operation.execute()

    task_id = response.task_id
    if not task_id:
        raise Exception(f"MiniMax generation failed: {response.base_resp}")

    video_generate_operation = PollingOperation(
        poll_endpoint=ApiEndpoint(
            path="/proxy/minimax/query/video_generation",
            method=HttpMethod.GET,
            request_model=EmptyRequest,
            response_model=MinimaxTaskResultResponse,
            query_params={"task_id": task_id},
        ),
        completed_statuses=["Success"],
        failed_statuses=["Fail"],
        status_extractor=lambda x: x.status.value,
        estimated_duration=average_duration,
        node_id=node_id,
        auth_kwargs=auth,
    )
    task_result = await video_generate_operation.execute()

    file_id = task_result.file_id
    if file_id is None:
        raise Exception("Request was not successful. Missing file ID.")
    file_retrieve_operation = SynchronousOperation(
        endpoint=ApiEndpoint(
            path="/proxy/minimax/files/retrieve",
            method=HttpMethod.GET,
            request_model=EmptyRequest,
            response_model=MinimaxFileRetrieveResponse,
            query_params={"file_id": int(file_id)},
        ),
        request=EmptyRequest(),
        auth_kwargs=auth,
    )
    file_result = await file_retrieve_operation.execute()

    file_url = file_result.file.download_url
    if file_url is None:
        raise Exception(
            f"No video was found in the response. Full response: {file_result.model_dump()}"
        )
    logging.info("Generated video URL: %s", file_url)
    if node_id:
        if hasattr(file_result.file, "backup_download_url"):
            message = f"Result URL: {file_url}\nBackup URL: {file_result.file.backup_download_url}"
        else:
            message = f"Result URL: {file_url}"
        PromptServer.instance.send_progress_text(message, node_id)

    # Download and return as VideoFromFile
    video_io = await download_url_to_bytesio(file_url)
    if video_io is None:
        error_msg = f"Failed to download video from {file_url}"
        logging.error(error_msg)
        raise Exception(error_msg)
    return comfy_io.NodeOutput(VideoFromFile(video_io))


class MinimaxTextToVideoNode(comfy_io.ComfyNode):
    """
    Generates videos synchronously based on a prompt, and optional parameters using MiniMax's API.
    """

    @classmethod
    def define_schema(cls) -> comfy_io.Schema:
        return comfy_io.Schema(
            node_id="MinimaxTextToVideoNode",
            display_name="MiniMax Text to Video",
            category="api node/video/MiniMax",
            description=cleandoc(cls.__doc__ or ""),
            inputs=[
                comfy_io.String.Input(
                    "prompt_text",
                    multiline=True,
                    default="",
                    tooltip="Text prompt to guide the video generation",
                ),
                comfy_io.Combo.Input(
                    "model",
                    options=["T2V-01", "T2V-01-Director"],
                    default="T2V-01",
                    tooltip="Model to use for video generation",
                ),
                comfy_io.Int.Input(
                    "seed",
                    default=0,
                    min=0,
                    max=0xFFFFFFFFFFFFFFFF,
                    step=1,
                    control_after_generate=True,
                    tooltip="The random seed used for creating the noise.",
                    optional=True,
                ),
            ],
            outputs=[comfy_io.Video.Output()],
            hidden=[
                comfy_io.Hidden.auth_token_comfy_org,
                comfy_io.Hidden.api_key_comfy_org,
                comfy_io.Hidden.unique_id,
            ],
            is_api_node=True,
        )

    @classmethod
    async def execute(
        cls,
        prompt_text: str,
        model: str = "T2V-01",
        seed: int = 0,
    ) -> comfy_io.NodeOutput:
        return await _generate_mm_video(
            auth={
                "auth_token": cls.hidden.auth_token_comfy_org,
                "comfy_api_key": cls.hidden.api_key_comfy_org,
            },
            node_id=cls.hidden.unique_id,
            prompt_text=prompt_text,
            seed=seed,
            model=model,
            image=None,
            subject=None,
            average_duration=T2V_AVERAGE_DURATION,
        )


class MinimaxImageToVideoNode(comfy_io.ComfyNode):
    """
    Generates videos synchronously based on an image and prompt, and optional parameters using MiniMax's API.
    """

    @classmethod
    def define_schema(cls) -> comfy_io.Schema:
        return comfy_io.Schema(
            node_id="MinimaxImageToVideoNode",
            display_name="MiniMax Image to Video",
            category="api node/video/MiniMax",
            description=cleandoc(cls.__doc__ or ""),
            inputs=[
                comfy_io.Image.Input(
                    "image",
                    tooltip="Image to use as first frame of video generation",
                ),
                comfy_io.String.Input(
                    "prompt_text",
                    multiline=True,
                    default="",
                    tooltip="Text prompt to guide the video generation",
                ),
                comfy_io.Combo.Input(
                    "model",
                    options=["I2V-01-Director", "I2V-01", "I2V-01-live"],
                    default="I2V-01",
                    tooltip="Model to use for video generation",
                ),
                comfy_io.Int.Input(
                    "seed",
                    default=0,
                    min=0,
                    max=0xFFFFFFFFFFFFFFFF,
                    step=1,
                    control_after_generate=True,
                    tooltip="The random seed used for creating the noise.",
                    optional=True,
                ),
            ],
            outputs=[comfy_io.Video.Output()],
            hidden=[
                comfy_io.Hidden.auth_token_comfy_org,
                comfy_io.Hidden.api_key_comfy_org,
                comfy_io.Hidden.unique_id,
            ],
            is_api_node=True,
        )

    @classmethod
    async def execute(
        cls,
        image: torch.Tensor,
        prompt_text: str,
        model: str = "I2V-01",
        seed: int = 0,
    ) -> comfy_io.NodeOutput:
        return await _generate_mm_video(
            auth={
                "auth_token": cls.hidden.auth_token_comfy_org,
                "comfy_api_key": cls.hidden.api_key_comfy_org,
            },
            node_id=cls.hidden.unique_id,
            prompt_text=prompt_text,
            seed=seed,
            model=model,
            image=image,
            subject=None,
            average_duration=I2V_AVERAGE_DURATION,
        )


class MinimaxSubjectToVideoNode(comfy_io.ComfyNode):
    """
    Generates videos synchronously based on an image and prompt, and optional parameters using MiniMax's API.
    """

    @classmethod
    def define_schema(cls) -> comfy_io.Schema:
        return comfy_io.Schema(
            node_id="MinimaxSubjectToVideoNode",
            display_name="MiniMax Subject to Video",
            category="api node/video/MiniMax",
            description=cleandoc(cls.__doc__ or ""),
            inputs=[
                comfy_io.Image.Input(
                    "subject",
                    tooltip="Image of subject to reference for video generation",
                ),
                comfy_io.String.Input(
                    "prompt_text",
                    multiline=True,
                    default="",
                    tooltip="Text prompt to guide the video generation",
                ),
                comfy_io.Combo.Input(
                    "model",
                    options=["S2V-01"],
                    default="S2V-01",
                    tooltip="Model to use for video generation",
                ),
                comfy_io.Int.Input(
                    "seed",
                    default=0,
                    min=0,
                    max=0xFFFFFFFFFFFFFFFF,
                    step=1,
                    control_after_generate=True,
                    tooltip="The random seed used for creating the noise.",
                    optional=True,
                ),
            ],
            outputs=[comfy_io.Video.Output()],
            hidden=[
                comfy_io.Hidden.auth_token_comfy_org,
                comfy_io.Hidden.api_key_comfy_org,
                comfy_io.Hidden.unique_id,
            ],
            is_api_node=True,
        )

    @classmethod
    async def execute(
        cls,
        subject: torch.Tensor,
        prompt_text: str,
        model: str = "S2V-01",
        seed: int = 0,
    ) -> comfy_io.NodeOutput:
        return await _generate_mm_video(
            auth={
                "auth_token": cls.hidden.auth_token_comfy_org,
                "comfy_api_key": cls.hidden.api_key_comfy_org,
            },
            node_id=cls.hidden.unique_id,
            prompt_text=prompt_text,
            seed=seed,
            model=model,
            image=None,
            subject=subject,
            average_duration=T2V_AVERAGE_DURATION,
        )


class MinimaxHailuoVideoNode(comfy_io.ComfyNode):
    """Generates videos from prompt, with optional start frame using the new MiniMax Hailuo-02 model."""

    @classmethod
    def define_schema(cls) -> comfy_io.Schema:
        return comfy_io.Schema(
            node_id="MinimaxHailuoVideoNode",
            display_name="MiniMax Hailuo Video",
            category="api node/video/MiniMax",
            description=cleandoc(cls.__doc__ or ""),
            inputs=[
                comfy_io.String.Input(
                    "prompt_text",
                    multiline=True,
                    default="",
                    tooltip="Text prompt to guide the video generation.",
                ),
                comfy_io.Int.Input(
                    "seed",
                    default=0,
                    min=0,
                    max=0xFFFFFFFFFFFFFFFF,
                    step=1,
                    control_after_generate=True,
                    tooltip="The random seed used for creating the noise.",
                    optional=True,
                ),
                comfy_io.Image.Input(
                    "first_frame_image",
                    tooltip="Optional image to use as the first frame to generate a video.",
                    optional=True,
                ),
                comfy_io.Boolean.Input(
                    "prompt_optimizer",
                    default=True,
                    tooltip="Optimize prompt to improve generation quality when needed.",
                    optional=True,
                ),
                comfy_io.Combo.Input(
                    "duration",
                    options=[6, 10],
                    default=6,
                    tooltip="The length of the output video in seconds.",
                    optional=True,
                ),
                comfy_io.Combo.Input(
                    "resolution",
                    options=["768P", "1080P"],
                    default="768P",
                    tooltip="The dimensions of the video display. 1080p is 1920x1080, 768p is 1366x768.",
                    optional=True,
                ),
            ],
            outputs=[comfy_io.Video.Output()],
            hidden=[
                comfy_io.Hidden.auth_token_comfy_org,
                comfy_io.Hidden.api_key_comfy_org,
                comfy_io.Hidden.unique_id,
            ],
            is_api_node=True,
        )

    @classmethod
    async def execute(
        cls,
        prompt_text: str,
        seed: int = 0,
        first_frame_image: Optional[torch.Tensor] = None,  # used for ImageToVideo
        prompt_optimizer: bool = True,
        duration: int = 6,
        resolution: str = "768P",
        model: str = "MiniMax-Hailuo-02",
    ) -> comfy_io.NodeOutput:
        auth = {
            "auth_token": cls.hidden.auth_token_comfy_org,
            "comfy_api_key": cls.hidden.api_key_comfy_org,
        }
        if first_frame_image is None:
            validate_string(prompt_text, field_name="prompt_text")

        if model == "MiniMax-Hailuo-02" and resolution.upper() == "1080P" and duration != 6:
            raise Exception(
                "When model is MiniMax-Hailuo-02 and resolution is 1080P, duration is limited to 6 seconds."
            )

        # upload image, if passed in
        image_url = None
        if first_frame_image is not None:
            image_url = (await upload_images_to_comfyapi(first_frame_image, max_images=1, auth_kwargs=auth))[0]

        video_generate_operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path="/proxy/minimax/video_generation",
                method=HttpMethod.POST,
                request_model=MinimaxVideoGenerationRequest,
                response_model=MinimaxVideoGenerationResponse,
            ),
            request=MinimaxVideoGenerationRequest(
                model=MiniMaxModel(model),
                prompt=prompt_text,
                callback_url=None,
                first_frame_image=image_url,
                prompt_optimizer=prompt_optimizer,
                duration=duration,
                resolution=resolution,
            ),
            auth_kwargs=auth,
        )
        response = await video_generate_operation.execute()

        task_id = response.task_id
        if not task_id:
            raise Exception(f"MiniMax generation failed: {response.base_resp}")

        average_duration = 120 if resolution == "768P" else 240
        video_generate_operation = PollingOperation(
            poll_endpoint=ApiEndpoint(
                path="/proxy/minimax/query/video_generation",
                method=HttpMethod.GET,
                request_model=EmptyRequest,
                response_model=MinimaxTaskResultResponse,
                query_params={"task_id": task_id},
            ),
            completed_statuses=["Success"],
            failed_statuses=["Fail"],
            status_extractor=lambda x: x.status.value,
            estimated_duration=average_duration,
            node_id=cls.hidden.unique_id,
            auth_kwargs=auth,
        )
        task_result = await video_generate_operation.execute()

        file_id = task_result.file_id
        if file_id is None:
            raise Exception("Request was not successful. Missing file ID.")
        file_retrieve_operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path="/proxy/minimax/files/retrieve",
                method=HttpMethod.GET,
                request_model=EmptyRequest,
                response_model=MinimaxFileRetrieveResponse,
                query_params={"file_id": int(file_id)},
            ),
            request=EmptyRequest(),
            auth_kwargs=auth,
        )
        file_result = await file_retrieve_operation.execute()

        file_url = file_result.file.download_url
        if file_url is None:
            raise Exception(
                f"No video was found in the response. Full response: {file_result.model_dump()}"
            )
        logging.info(f"Generated video URL: {file_url}")
        if cls.hidden.unique_id:
            if hasattr(file_result.file, "backup_download_url"):
                message = f"Result URL: {file_url}\nBackup URL: {file_result.file.backup_download_url}"
            else:
                message = f"Result URL: {file_url}"
            PromptServer.instance.send_progress_text(message, cls.hidden.unique_id)

        video_io = await download_url_to_bytesio(file_url)
        if video_io is None:
            error_msg = f"Failed to download video from {file_url}"
            logging.error(error_msg)
            raise Exception(error_msg)
        return comfy_io.NodeOutput(VideoFromFile(video_io))


class MinimaxExtension(ComfyExtension):
    @override
    async def get_node_list(self) -> list[type[comfy_io.ComfyNode]]:
        return [
            MinimaxTextToVideoNode,
            MinimaxImageToVideoNode,
            # MinimaxSubjectToVideoNode,
            MinimaxHailuoVideoNode,
        ]


async def comfy_entrypoint() -> MinimaxExtension:
    return MinimaxExtension()