File size: 23,132 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
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
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
from inspect import cleandoc
from comfy.comfy_types.node_typing import IO
from comfy_api_nodes.apis.stability_api import (
    StabilityUpscaleConservativeRequest,
    StabilityUpscaleCreativeRequest,
    StabilityAsyncResponse,
    StabilityResultsGetResponse,
    StabilityStable3_5Request,
    StabilityStableUltraRequest,
    StabilityStableUltraResponse,
    StabilityAspectRatio,
    Stability_SD3_5_Model,
    Stability_SD3_5_GenerationMode,
    get_stability_style_presets,
)
from comfy_api_nodes.apis.client import (
    ApiEndpoint,
    HttpMethod,
    SynchronousOperation,
    PollingOperation,
    EmptyRequest,
)
from comfy_api_nodes.apinode_utils import (
    bytesio_to_image_tensor,
    tensor_to_bytesio,
    validate_string,
)

import torch
import base64
from io import BytesIO
from enum import Enum


class StabilityPollStatus(str, Enum):
    finished = "finished"
    in_progress = "in_progress"
    failed = "failed"


def get_async_dummy_status(x: StabilityResultsGetResponse):
    if x.name is not None or x.errors is not None:
        return StabilityPollStatus.failed
    elif x.finish_reason is not None:
        return StabilityPollStatus.finished
    return StabilityPollStatus.in_progress


class StabilityStableImageUltraNode:
    """

    Generates images synchronously based on prompt and resolution.

    """

    RETURN_TYPES = (IO.IMAGE,)
    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
    FUNCTION = "api_call"
    API_NODE = True
    CATEGORY = "api node/image/Stability AI"

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "prompt": (
                    IO.STRING,
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "What you wish to see in the output image. A strong, descriptive prompt that clearly defines" +
                                    "What you wish to see in the output image. A strong, descriptive prompt that clearly defines" +
                                    "elements, colors, and subjects will lead to better results. " +
                                    "To control the weight of a given word use the format `(word:weight)`," +
                                    "where `word` is the word you'd like to control the weight of and `weight`" +
                                    "is a value between 0 and 1. For example: `The sky was a crisp (blue:0.3) and (green:0.8)`" +
                                    "would convey a sky that was blue and green, but more green than blue."
                    },
                ),
                "aspect_ratio": ([x.value for x in StabilityAspectRatio],
                    {
                        "default": StabilityAspectRatio.ratio_1_1,
                        "tooltip": "Aspect ratio of generated image.",
                    },
                ),
                "style_preset": (get_stability_style_presets(),
                    {
                        "tooltip": "Optional desired style of generated image.",
                    },
                ),
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 4294967294,
                        "control_after_generate": True,
                        "tooltip": "The random seed used for creating the noise.",
                    },
                ),
            },
            "optional": {
                "image": (IO.IMAGE,),
                "negative_prompt": (
                    IO.STRING,
                    {
                        "default": "",
                        "forceInput": True,
                        "tooltip": "A blurb of text describing what you do not wish to see in the output image. This is an advanced feature."
                    },
                ),
                "image_denoise": (
                    IO.FLOAT,
                    {
                        "default": 0.5,
                        "min": 0.0,
                        "max": 1.0,
                        "step": 0.01,
                        "tooltip": "Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.",
                    },
                ),
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
                "comfy_api_key": "API_KEY_COMFY_ORG",
            },
        }

    def api_call(self, prompt: str, aspect_ratio: str, style_preset: str, seed: int,

                 negative_prompt: str=None, image: torch.Tensor = None, image_denoise: float=None,

                 **kwargs):
        validate_string(prompt, strip_whitespace=False)
        # prepare image binary if image present
        image_binary = None
        if image is not None:
            image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read()
        else:
            image_denoise = None

        if not negative_prompt:
            negative_prompt = None
        if style_preset == "None":
            style_preset = None

        files = {
            "image": image_binary
        }

        operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path="/proxy/stability/v2beta/stable-image/generate/ultra",
                method=HttpMethod.POST,
                request_model=StabilityStableUltraRequest,
                response_model=StabilityStableUltraResponse,
            ),
            request=StabilityStableUltraRequest(
                prompt=prompt,
                negative_prompt=negative_prompt,
                aspect_ratio=aspect_ratio,
                seed=seed,
                strength=image_denoise,
                style_preset=style_preset,
            ),
            files=files,
            content_type="multipart/form-data",
            auth_kwargs=kwargs,
        )
        response_api = operation.execute()

        if response_api.finish_reason != "SUCCESS":
            raise Exception(f"Stable Image Ultra generation failed: {response_api.finish_reason}.")

        image_data = base64.b64decode(response_api.image)
        returned_image = bytesio_to_image_tensor(BytesIO(image_data))

        return (returned_image,)


class StabilityStableImageSD_3_5Node:
    """

    Generates images synchronously based on prompt and resolution.

    """

    RETURN_TYPES = (IO.IMAGE,)
    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
    FUNCTION = "api_call"
    API_NODE = True
    CATEGORY = "api node/image/Stability AI"

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "prompt": (
                    IO.STRING,
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results."
                    },
                ),
                "model": ([x.value for x in Stability_SD3_5_Model],),
                "aspect_ratio": ([x.value for x in StabilityAspectRatio],
                    {
                        "default": StabilityAspectRatio.ratio_1_1,
                        "tooltip": "Aspect ratio of generated image.",
                    },
                ),
                "style_preset": (get_stability_style_presets(),
                    {
                        "tooltip": "Optional desired style of generated image.",
                    },
                ),
                "cfg_scale": (
                    IO.FLOAT,
                    {
                        "default": 4.0,
                        "min": 1.0,
                        "max": 10.0,
                        "step": 0.1,
                        "tooltip": "How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt)",
                    },
                ),
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 4294967294,
                        "control_after_generate": True,
                        "tooltip": "The random seed used for creating the noise.",
                    },
                ),
            },
            "optional": {
                "image": (IO.IMAGE,),
                "negative_prompt": (
                    IO.STRING,
                    {
                        "default": "",
                        "forceInput": True,
                        "tooltip": "Keywords of what you do not wish to see in the output image. This is an advanced feature."
                    },
                ),
                "image_denoise": (
                    IO.FLOAT,
                    {
                        "default": 0.5,
                        "min": 0.0,
                        "max": 1.0,
                        "step": 0.01,
                        "tooltip": "Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.",
                    },
                ),
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
                "comfy_api_key": "API_KEY_COMFY_ORG",
            },
        }

    def api_call(self, model: str, prompt: str, aspect_ratio: str, style_preset: str, seed: int, cfg_scale: float,

                 negative_prompt: str=None, image: torch.Tensor = None, image_denoise: float=None,

                 **kwargs):
        validate_string(prompt, strip_whitespace=False)
        # prepare image binary if image present
        image_binary = None
        mode = Stability_SD3_5_GenerationMode.text_to_image
        if image is not None:
            image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read()
            mode = Stability_SD3_5_GenerationMode.image_to_image
            aspect_ratio = None
        else:
            image_denoise = None

        if not negative_prompt:
            negative_prompt = None
        if style_preset == "None":
            style_preset = None

        files = {
            "image": image_binary
        }

        operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path="/proxy/stability/v2beta/stable-image/generate/sd3",
                method=HttpMethod.POST,
                request_model=StabilityStable3_5Request,
                response_model=StabilityStableUltraResponse,
            ),
            request=StabilityStable3_5Request(
                prompt=prompt,
                negative_prompt=negative_prompt,
                aspect_ratio=aspect_ratio,
                seed=seed,
                strength=image_denoise,
                style_preset=style_preset,
                cfg_scale=cfg_scale,
                model=model,
                mode=mode,
            ),
            files=files,
            content_type="multipart/form-data",
            auth_kwargs=kwargs,
        )
        response_api = operation.execute()

        if response_api.finish_reason != "SUCCESS":
            raise Exception(f"Stable Diffusion 3.5 Image generation failed: {response_api.finish_reason}.")

        image_data = base64.b64decode(response_api.image)
        returned_image = bytesio_to_image_tensor(BytesIO(image_data))

        return (returned_image,)


class StabilityUpscaleConservativeNode:
    """

    Upscale image with minimal alterations to 4K resolution.

    """

    RETURN_TYPES = (IO.IMAGE,)
    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
    FUNCTION = "api_call"
    API_NODE = True
    CATEGORY = "api node/image/Stability AI"

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "image": (IO.IMAGE,),
                "prompt": (
                    IO.STRING,
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results."
                    },
                ),
                "creativity": (
                    IO.FLOAT,
                    {
                        "default": 0.35,
                        "min": 0.2,
                        "max": 0.5,
                        "step": 0.01,
                        "tooltip": "Controls the likelihood of creating additional details not heavily conditioned by the init image.",
                    },
                ),
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 4294967294,
                        "control_after_generate": True,
                        "tooltip": "The random seed used for creating the noise.",
                    },
                ),
            },
            "optional": {
                "negative_prompt": (
                    IO.STRING,
                    {
                        "default": "",
                        "forceInput": True,
                        "tooltip": "Keywords of what you do not wish to see in the output image. This is an advanced feature."
                    },
                ),
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
                "comfy_api_key": "API_KEY_COMFY_ORG",
            },
        }

    def api_call(self, image: torch.Tensor, prompt: str, creativity: float, seed: int, negative_prompt: str=None,

                 **kwargs):
        validate_string(prompt, strip_whitespace=False)
        image_binary = tensor_to_bytesio(image, total_pixels=1024*1024).read()

        if not negative_prompt:
            negative_prompt = None

        files = {
            "image": image_binary
        }

        operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path="/proxy/stability/v2beta/stable-image/upscale/conservative",
                method=HttpMethod.POST,
                request_model=StabilityUpscaleConservativeRequest,
                response_model=StabilityStableUltraResponse,
            ),
            request=StabilityUpscaleConservativeRequest(
                prompt=prompt,
                negative_prompt=negative_prompt,
                creativity=round(creativity,2),
                seed=seed,
            ),
            files=files,
            content_type="multipart/form-data",
            auth_kwargs=kwargs,
        )
        response_api = operation.execute()

        if response_api.finish_reason != "SUCCESS":
            raise Exception(f"Stability Upscale Conservative generation failed: {response_api.finish_reason}.")

        image_data = base64.b64decode(response_api.image)
        returned_image = bytesio_to_image_tensor(BytesIO(image_data))

        return (returned_image,)


class StabilityUpscaleCreativeNode:
    """

    Upscale image with minimal alterations to 4K resolution.

    """

    RETURN_TYPES = (IO.IMAGE,)
    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
    FUNCTION = "api_call"
    API_NODE = True
    CATEGORY = "api node/image/Stability AI"

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "image": (IO.IMAGE,),
                "prompt": (
                    IO.STRING,
                    {
                        "multiline": True,
                        "default": "",
                        "tooltip": "What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results."
                    },
                ),
                "creativity": (
                    IO.FLOAT,
                    {
                        "default": 0.3,
                        "min": 0.1,
                        "max": 0.5,
                        "step": 0.01,
                        "tooltip": "Controls the likelihood of creating additional details not heavily conditioned by the init image.",
                    },
                ),
                "style_preset": (get_stability_style_presets(),
                    {
                        "tooltip": "Optional desired style of generated image.",
                    },
                ),
                "seed": (
                    IO.INT,
                    {
                        "default": 0,
                        "min": 0,
                        "max": 4294967294,
                        "control_after_generate": True,
                        "tooltip": "The random seed used for creating the noise.",
                    },
                ),
            },
            "optional": {
                "negative_prompt": (
                    IO.STRING,
                    {
                        "default": "",
                        "forceInput": True,
                        "tooltip": "Keywords of what you do not wish to see in the output image. This is an advanced feature."
                    },
                ),
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
                "comfy_api_key": "API_KEY_COMFY_ORG",
            },
        }

    def api_call(self, image: torch.Tensor, prompt: str, creativity: float, style_preset: str, seed: int, negative_prompt: str=None,

                 **kwargs):
        validate_string(prompt, strip_whitespace=False)
        image_binary = tensor_to_bytesio(image, total_pixels=1024*1024).read()

        if not negative_prompt:
            negative_prompt = None
        if style_preset == "None":
            style_preset = None

        files = {
            "image": image_binary
        }

        operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path="/proxy/stability/v2beta/stable-image/upscale/creative",
                method=HttpMethod.POST,
                request_model=StabilityUpscaleCreativeRequest,
                response_model=StabilityAsyncResponse,
            ),
            request=StabilityUpscaleCreativeRequest(
                prompt=prompt,
                negative_prompt=negative_prompt,
                creativity=round(creativity,2),
                style_preset=style_preset,
                seed=seed,
            ),
            files=files,
            content_type="multipart/form-data",
            auth_kwargs=kwargs,
        )
        response_api = operation.execute()

        operation = PollingOperation(
            poll_endpoint=ApiEndpoint(
                path=f"/proxy/stability/v2beta/results/{response_api.id}",
                method=HttpMethod.GET,
                request_model=EmptyRequest,
                response_model=StabilityResultsGetResponse,
            ),
            poll_interval=3,
            completed_statuses=[StabilityPollStatus.finished],
            failed_statuses=[StabilityPollStatus.failed],
            status_extractor=lambda x: get_async_dummy_status(x),
            auth_kwargs=kwargs,
        )
        response_poll: StabilityResultsGetResponse = operation.execute()

        if response_poll.finish_reason != "SUCCESS":
            raise Exception(f"Stability Upscale Creative generation failed: {response_poll.finish_reason}.")

        image_data = base64.b64decode(response_poll.result)
        returned_image = bytesio_to_image_tensor(BytesIO(image_data))

        return (returned_image,)


class StabilityUpscaleFastNode:
    """

    Quickly upscales an image via Stability API call to 4x its original size; intended for upscaling low-quality/compressed images.

    """

    RETURN_TYPES = (IO.IMAGE,)
    DESCRIPTION = cleandoc(__doc__ or "")  # Handle potential None value
    FUNCTION = "api_call"
    API_NODE = True
    CATEGORY = "api node/image/Stability AI"

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "image": (IO.IMAGE,),
            },
            "optional": {
            },
            "hidden": {
                "auth_token": "AUTH_TOKEN_COMFY_ORG",
                "comfy_api_key": "API_KEY_COMFY_ORG",
            },
        }

    def api_call(self, image: torch.Tensor,

                 **kwargs):
        image_binary = tensor_to_bytesio(image, total_pixels=4096*4096).read()

        files = {
            "image": image_binary
        }

        operation = SynchronousOperation(
            endpoint=ApiEndpoint(
                path="/proxy/stability/v2beta/stable-image/upscale/fast",
                method=HttpMethod.POST,
                request_model=EmptyRequest,
                response_model=StabilityStableUltraResponse,
            ),
            request=EmptyRequest(),
            files=files,
            content_type="multipart/form-data",
            auth_kwargs=kwargs,
        )
        response_api = operation.execute()

        if response_api.finish_reason != "SUCCESS":
            raise Exception(f"Stability Upscale Fast failed: {response_api.finish_reason}.")

        image_data = base64.b64decode(response_api.image)
        returned_image = bytesio_to_image_tensor(BytesIO(image_data))

        return (returned_image,)


# A dictionary that contains all nodes you want to export with their names
# NOTE: names should be globally unique
NODE_CLASS_MAPPINGS = {
    "StabilityStableImageUltraNode": StabilityStableImageUltraNode,
    "StabilityStableImageSD_3_5Node": StabilityStableImageSD_3_5Node,
    "StabilityUpscaleConservativeNode": StabilityUpscaleConservativeNode,
    "StabilityUpscaleCreativeNode": StabilityUpscaleCreativeNode,
    "StabilityUpscaleFastNode": StabilityUpscaleFastNode,
}

# A dictionary that contains the friendly/humanly readable titles for the nodes
NODE_DISPLAY_NAME_MAPPINGS = {
    "StabilityStableImageUltraNode": "Stability AI Stable Image Ultra",
    "StabilityStableImageSD_3_5Node": "Stability AI Stable Diffusion 3.5 Image",
    "StabilityUpscaleConservativeNode": "Stability AI Upscale Conservative",
    "StabilityUpscaleCreativeNode": "Stability AI Upscale Creative",
    "StabilityUpscaleFastNode": "Stability AI Upscale Fast",
}