File size: 15,382 Bytes
62bb9d8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import logging
import base64
import aiohttp
import torch
from io import BytesIO
from typing import Optional
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 (
    VeoGenVidRequest,
    VeoGenVidResponse,
    VeoGenVidPollRequest,
    VeoGenVidPollResponse,
)
from comfy_api_nodes.apis.client import (
    ApiEndpoint,
    HttpMethod,
    SynchronousOperation,
    PollingOperation,
)

from comfy_api_nodes.apinode_utils import (
    downscale_image_tensor,
    tensor_to_base64_string,
)

AVERAGE_DURATION_VIDEO_GEN = 32

def convert_image_to_base64(image: torch.Tensor):
    if image is None:
        return None

    scaled_image = downscale_image_tensor(image, total_pixels=2048*2048)
    return tensor_to_base64_string(scaled_image)


def get_video_url_from_response(poll_response: VeoGenVidPollResponse) -> Optional[str]:
    if (
        poll_response.response
        and hasattr(poll_response.response, "videos")
        and poll_response.response.videos
        and len(poll_response.response.videos) > 0
    ):
        video = poll_response.response.videos[0]
    else:
        return None
    if hasattr(video, "gcsUri") and video.gcsUri:
        return str(video.gcsUri)
    return None


class VeoVideoGenerationNode(comfy_io.ComfyNode):
    """
    Generates videos from text prompts using Google's Veo API.

    This node can create videos from text descriptions and optional image inputs,
    with control over parameters like aspect ratio, duration, and more.
    """

    @classmethod
    def define_schema(cls):
        return comfy_io.Schema(
            node_id="VeoVideoGenerationNode",
            display_name="Google Veo 2 Video Generation",
            category="api node/video/Veo",
            description="Generates videos from text prompts using Google's Veo 2 API",
            inputs=[
                comfy_io.String.Input(
                    "prompt",
                    multiline=True,
                    default="",
                    tooltip="Text description of the video",
                ),
                comfy_io.Combo.Input(
                    "aspect_ratio",
                    options=["16:9", "9:16"],
                    default="16:9",
                    tooltip="Aspect ratio of the output video",
                ),
                comfy_io.String.Input(
                    "negative_prompt",
                    multiline=True,
                    default="",
                    tooltip="Negative text prompt to guide what to avoid in the video",
                    optional=True,
                ),
                comfy_io.Int.Input(
                    "duration_seconds",
                    default=5,
                    min=5,
                    max=8,
                    step=1,
                    display_mode=comfy_io.NumberDisplay.number,
                    tooltip="Duration of the output video in seconds",
                    optional=True,
                ),
                comfy_io.Boolean.Input(
                    "enhance_prompt",
                    default=True,
                    tooltip="Whether to enhance the prompt with AI assistance",
                    optional=True,
                ),
                comfy_io.Combo.Input(
                    "person_generation",
                    options=["ALLOW", "BLOCK"],
                    default="ALLOW",
                    tooltip="Whether to allow generating people in the video",
                    optional=True,
                ),
                comfy_io.Int.Input(
                    "seed",
                    default=0,
                    min=0,
                    max=0xFFFFFFFF,
                    step=1,
                    display_mode=comfy_io.NumberDisplay.number,
                    control_after_generate=True,
                    tooltip="Seed for video generation (0 for random)",
                    optional=True,
                ),
                comfy_io.Image.Input(
                    "image",
                    tooltip="Optional reference image to guide video generation",
                    optional=True,
                ),
                comfy_io.Combo.Input(
                    "model",
                    options=["veo-2.0-generate-001"],
                    default="veo-2.0-generate-001",
                    tooltip="Veo 2 model to use for video generation",
                    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,
        aspect_ratio="16:9",
        negative_prompt="",
        duration_seconds=5,
        enhance_prompt=True,
        person_generation="ALLOW",
        seed=0,
        image=None,
        model="veo-2.0-generate-001",
        generate_audio=False,
    ):
        # Prepare the instances for the request
        instances = []

        instance = {
            "prompt": prompt
        }

        # Add image if provided
        if image is not None:
            image_base64 = convert_image_to_base64(image)
            if image_base64:
                instance["image"] = {
                    "bytesBase64Encoded": image_base64,
                    "mimeType": "image/png"
                }

        instances.append(instance)

        # Create parameters dictionary
        parameters = {
            "aspectRatio": aspect_ratio,
            "personGeneration": person_generation,
            "durationSeconds": duration_seconds,
            "enhancePrompt": enhance_prompt,
        }

        # Add optional parameters if provided
        if negative_prompt:
            parameters["negativePrompt"] = negative_prompt
        if seed > 0:
            parameters["seed"] = seed
        # Only add generateAudio for Veo 3 models
        if "veo-3.0" in model:
            parameters["generateAudio"] = generate_audio

        auth = {
            "auth_token": cls.hidden.auth_token_comfy_org,
            "comfy_api_key": cls.hidden.api_key_comfy_org,
        }
        # Initial request to start video generation
        initial_operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path=f"/proxy/veo/{model}/generate",
                method=HttpMethod.POST,
                request_model=VeoGenVidRequest,
                response_model=VeoGenVidResponse
            ),
            request=VeoGenVidRequest(
                instances=instances,
                parameters=parameters
            ),
            auth_kwargs=auth,
        )

        initial_response = await initial_operation.execute()
        operation_name = initial_response.name

        logging.info(f"Veo generation started with operation name: {operation_name}")

        # Define status extractor function
        def status_extractor(response):
            # Only return "completed" if the operation is done, regardless of success or failure
            # We'll check for errors after polling completes
            return "completed" if response.done else "pending"

        # Define progress extractor function
        def progress_extractor(response):
            # Could be enhanced if the API provides progress information
            return None

        # Define the polling operation
        poll_operation = PollingOperation(
            poll_endpoint=ApiEndpoint(
                path=f"/proxy/veo/{model}/poll",
                method=HttpMethod.POST,
                request_model=VeoGenVidPollRequest,
                response_model=VeoGenVidPollResponse
            ),
            completed_statuses=["completed"],
            failed_statuses=[],  # No failed statuses, we'll handle errors after polling
            status_extractor=status_extractor,
            progress_extractor=progress_extractor,
            request=VeoGenVidPollRequest(
                operationName=operation_name
            ),
            auth_kwargs=auth,
            poll_interval=5.0,
            result_url_extractor=get_video_url_from_response,
            node_id=cls.hidden.unique_id,
            estimated_duration=AVERAGE_DURATION_VIDEO_GEN,
        )

        # Execute the polling operation
        poll_response = await poll_operation.execute()

        # Now check for errors in the final response
        # Check for error in poll response
        if hasattr(poll_response, 'error') and poll_response.error:
            error_message = f"Veo API error: {poll_response.error.message} (code: {poll_response.error.code})"
            logging.error(error_message)
            raise Exception(error_message)

        # Check for RAI filtered content
        if (hasattr(poll_response.response, 'raiMediaFilteredCount') and
            poll_response.response.raiMediaFilteredCount > 0):

            # Extract reason message if available
            if (hasattr(poll_response.response, 'raiMediaFilteredReasons') and
                poll_response.response.raiMediaFilteredReasons):
                reason = poll_response.response.raiMediaFilteredReasons[0]
                error_message = f"Content filtered by Google's Responsible AI practices: {reason} ({poll_response.response.raiMediaFilteredCount} videos filtered.)"
            else:
                error_message = f"Content filtered by Google's Responsible AI practices ({poll_response.response.raiMediaFilteredCount} videos filtered.)"

            logging.error(error_message)
            raise Exception(error_message)

        # Extract video data
        if poll_response.response and hasattr(poll_response.response, 'videos') and poll_response.response.videos and len(poll_response.response.videos) > 0:
            video = poll_response.response.videos[0]

            # Check if video is provided as base64 or URL
            if hasattr(video, 'bytesBase64Encoded') and video.bytesBase64Encoded:
                # Decode base64 string to bytes
                video_data = base64.b64decode(video.bytesBase64Encoded)
            elif hasattr(video, 'gcsUri') and video.gcsUri:
                # Download from URL
                async with aiohttp.ClientSession() as session:
                    async with session.get(video.gcsUri) as video_response:
                        video_data = await video_response.content.read()
            else:
                raise Exception("Video returned but no data or URL was provided")
        else:
            raise Exception("Video generation completed but no video was returned")

        if not video_data:
            raise Exception("No video data was returned")

        logging.info("Video generation completed successfully")

        # Convert video data to BytesIO object
        video_io = BytesIO(video_data)

        # Return VideoFromFile object
        return comfy_io.NodeOutput(VideoFromFile(video_io))


class Veo3VideoGenerationNode(VeoVideoGenerationNode):
    """
    Generates videos from text prompts using Google's Veo 3 API.

    Supported models:
    - veo-3.0-generate-001
    - veo-3.0-fast-generate-001

    This node extends the base Veo node with Veo 3 specific features including
    audio generation and fixed 8-second duration.
    """

    @classmethod
    def define_schema(cls):
        return comfy_io.Schema(
            node_id="Veo3VideoGenerationNode",
            display_name="Google Veo 3 Video Generation",
            category="api node/video/Veo",
            description="Generates videos from text prompts using Google's Veo 3 API",
            inputs=[
                comfy_io.String.Input(
                    "prompt",
                    multiline=True,
                    default="",
                    tooltip="Text description of the video",
                ),
                comfy_io.Combo.Input(
                    "aspect_ratio",
                    options=["16:9", "9:16"],
                    default="16:9",
                    tooltip="Aspect ratio of the output video",
                ),
                comfy_io.String.Input(
                    "negative_prompt",
                    multiline=True,
                    default="",
                    tooltip="Negative text prompt to guide what to avoid in the video",
                    optional=True,
                ),
                comfy_io.Int.Input(
                    "duration_seconds",
                    default=8,
                    min=8,
                    max=8,
                    step=1,
                    display_mode=comfy_io.NumberDisplay.number,
                    tooltip="Duration of the output video in seconds (Veo 3 only supports 8 seconds)",
                    optional=True,
                ),
                comfy_io.Boolean.Input(
                    "enhance_prompt",
                    default=True,
                    tooltip="Whether to enhance the prompt with AI assistance",
                    optional=True,
                ),
                comfy_io.Combo.Input(
                    "person_generation",
                    options=["ALLOW", "BLOCK"],
                    default="ALLOW",
                    tooltip="Whether to allow generating people in the video",
                    optional=True,
                ),
                comfy_io.Int.Input(
                    "seed",
                    default=0,
                    min=0,
                    max=0xFFFFFFFF,
                    step=1,
                    display_mode=comfy_io.NumberDisplay.number,
                    control_after_generate=True,
                    tooltip="Seed for video generation (0 for random)",
                    optional=True,
                ),
                comfy_io.Image.Input(
                    "image",
                    tooltip="Optional reference image to guide video generation",
                    optional=True,
                ),
                comfy_io.Combo.Input(
                    "model",
                    options=["veo-3.0-generate-001", "veo-3.0-fast-generate-001"],
                    default="veo-3.0-generate-001",
                    tooltip="Veo 3 model to use for video generation",
                    optional=True,
                ),
                comfy_io.Boolean.Input(
                    "generate_audio",
                    default=False,
                    tooltip="Generate audio for the video. Supported by all Veo 3 models.",
                    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,
        )


class VeoExtension(ComfyExtension):
    @override
    async def get_node_list(self) -> list[type[comfy_io.ComfyNode]]:
        return [
            VeoVideoGenerationNode,
            Veo3VideoGenerationNode,
        ]

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