File size: 11,522 Bytes
77f10a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from typing import Union
import logging
import torch

from comfy.comfy_types.node_typing import IO
from comfy_api.input_impl.video_types import VideoFromFile
from comfy_api_nodes.apis import (
    MinimaxVideoGenerationRequest,
    MinimaxVideoGenerationResponse,
    MinimaxFileRetrieveResponse,
    MinimaxTaskResultResponse,
    SubjectReferenceItem,
    Model
)
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

class MinimaxTextToVideoNode:
    """

    Generates videos synchronously based on a prompt, and optional parameters using MiniMax's API.

    """

    AVERAGE_DURATION = T2V_AVERAGE_DURATION

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "prompt_text": (
                    "STRING",
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "Text prompt to guide the video generation",
                    },
                ),
                "model": (
                    [
                        "T2V-01",
                        "T2V-01-Director",
                    ],
                    {
                        "default": "T2V-01",
                        "tooltip": "Model to use for video generation",
                    },
                ),
            },
            "optional": {
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 0xFFFFFFFFFFFFFFFF,
                        "control_after_generate": True,
                        "tooltip": "The random seed used for creating the noise.",
                    },
                ),
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
                "comfy_api_key": "API_KEY_COMFY_ORG",
                "unique_id": "UNIQUE_ID",
            },
        }

    RETURN_TYPES = ("VIDEO",)
    DESCRIPTION = "Generates videos from prompts using MiniMax's API"
    FUNCTION = "generate_video"
    CATEGORY = "api node/video/MiniMax"
    API_NODE = True
    OUTPUT_NODE = True

    def generate_video(

        self,

        prompt_text,

        seed=0,

        model="T2V-01",

        image: torch.Tensor=None, # used for ImageToVideo

        subject: torch.Tensor=None, # used for SubjectToVideo

        unique_id: Union[str, None]=None,

        **kwargs,

    ):
        '''

        Function used between MiniMax nodes - supports T2V, I2V, and S2V, based on provided arguments.

        '''
        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 = upload_images_to_comfyapi(image, max_images=1, auth_kwargs=kwargs)[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 = upload_images_to_comfyapi(subject, max_images=1, auth_kwargs=kwargs)[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=Model(model),
                prompt=prompt_text,
                callback_url=None,
                first_frame_image=image_url,
                subject_reference=subject_reference,
                prompt_optimizer=None,
            ),
            auth_kwargs=kwargs,
        )
        response = 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=self.AVERAGE_DURATION,
            node_id=unique_id,
            auth_kwargs=kwargs,
        )
        task_result = 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=kwargs,
        )
        file_result = 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 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, unique_id)

        video_io = 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 (VideoFromFile(video_io),)


class MinimaxImageToVideoNode(MinimaxTextToVideoNode):
    """

    Generates videos synchronously based on an image and prompt, and optional parameters using MiniMax's API.

    """

    AVERAGE_DURATION = I2V_AVERAGE_DURATION

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "image": (
                    IO.IMAGE,
                    {
                        "tooltip": "Image to use as first frame of video generation"
                    },
                ),
                "prompt_text": (
                    "STRING",
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "Text prompt to guide the video generation",
                    },
                ),
                "model": (
                    [
                        "I2V-01-Director",
                        "I2V-01",
                        "I2V-01-live",
                    ],
                    {
                        "default": "I2V-01",
                        "tooltip": "Model to use for video generation",
                    },
                ),
            },
            "optional": {
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 0xFFFFFFFFFFFFFFFF,
                        "control_after_generate": True,
                        "tooltip": "The random seed used for creating the noise.",
                    },
                ),
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
                "comfy_api_key": "API_KEY_COMFY_ORG",
                "unique_id": "UNIQUE_ID",
            },
        }

    RETURN_TYPES = ("VIDEO",)
    DESCRIPTION = "Generates videos from an image and prompts using MiniMax's API"
    FUNCTION = "generate_video"
    CATEGORY = "api node/video/MiniMax"
    API_NODE = True
    OUTPUT_NODE = True


class MinimaxSubjectToVideoNode(MinimaxTextToVideoNode):
    """

    Generates videos synchronously based on an image and prompt, and optional parameters using MiniMax's API.

    """

    AVERAGE_DURATION = T2V_AVERAGE_DURATION

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "subject": (
                    IO.IMAGE,
                    {
                        "tooltip": "Image of subject to reference video generation"
                    },
                ),
                "prompt_text": (
                    "STRING",
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "Text prompt to guide the video generation",
                    },
                ),
                "model": (
                    [
                        "S2V-01",
                    ],
                    {
                        "default": "S2V-01",
                        "tooltip": "Model to use for video generation",
                    },
                ),
            },
            "optional": {
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 0xFFFFFFFFFFFFFFFF,
                        "control_after_generate": True,
                        "tooltip": "The random seed used for creating the noise.",
                    },
                ),
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
                "comfy_api_key": "API_KEY_COMFY_ORG",
                "unique_id": "UNIQUE_ID",
            },
        }

    RETURN_TYPES = ("VIDEO",)
    DESCRIPTION = "Generates videos from an image and prompts using MiniMax's API"
    FUNCTION = "generate_video"
    CATEGORY = "api node/video/MiniMax"
    API_NODE = True
    OUTPUT_NODE = True


# A dictionary that contains all nodes you want to export with their names
# NOTE: names should be globally unique
NODE_CLASS_MAPPINGS = {
    "MinimaxTextToVideoNode": MinimaxTextToVideoNode,
    "MinimaxImageToVideoNode": MinimaxImageToVideoNode,
    # "MinimaxSubjectToVideoNode": MinimaxSubjectToVideoNode,
}

# A dictionary that contains the friendly/humanly readable titles for the nodes
NODE_DISPLAY_NAME_MAPPINGS = {
    "MinimaxTextToVideoNode": "MiniMax Text to Video",
    "MinimaxImageToVideoNode": "MiniMax Image to Video",
    "MinimaxSubjectToVideoNode": "MiniMax Subject to Video",
}