nodes.py 72.7 KB
Newer Older
comfyanonymous's avatar
comfyanonymous committed
1
2
3
4
5
import torch

import os
import sys
import json
6
import hashlib
7
import traceback
8
import math
9
import time
10
import random
comfyanonymous's avatar
comfyanonymous committed
11

12
from PIL import Image, ImageOps, ImageSequence
comfyanonymous's avatar
comfyanonymous committed
13
14
from PIL.PngImagePlugin import PngInfo
import numpy as np
15
import safetensors.torch
comfyanonymous's avatar
comfyanonymous committed
16

comfyanonymous's avatar
comfyanonymous committed
17
sys.path.insert(0, os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy"))
comfyanonymous's avatar
comfyanonymous committed
18
19


20
import comfy.diffusers_load
comfyanonymous's avatar
comfyanonymous committed
21
import comfy.samplers
22
import comfy.sample
comfyanonymous's avatar
comfyanonymous committed
23
import comfy.sd
comfyanonymous's avatar
comfyanonymous committed
24
import comfy.utils
25
import comfy.controlnet
comfyanonymous's avatar
comfyanonymous committed
26

27
import comfy.clip_vision
28

29
import comfy.model_management
30
31
from comfy.cli_args import args

32
import importlib
comfyanonymous's avatar
comfyanonymous committed
33

34
import folder_paths
35
import latent_preview
space-nuko's avatar
space-nuko committed
36

37
def before_node_execution():
38
    comfy.model_management.throw_exception_if_processing_interrupted()
39

40
def interrupt_processing(value=True):
41
    comfy.model_management.interrupt_current_processing(value)
42

43
44
MAX_RESOLUTION=8192

comfyanonymous's avatar
comfyanonymous committed
45
46
47
class CLIPTextEncode:
    @classmethod
    def INPUT_TYPES(s):
48
        return {"required": {"text": ("STRING", {"multiline": True}), "clip": ("CLIP", )}}
comfyanonymous's avatar
comfyanonymous committed
49
50
51
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "encode"

52
53
    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
54
    def encode(self, clip, text):
55
56
57
        tokens = clip.tokenize(text)
        cond, pooled = clip.encode_from_tokens(tokens, return_pooled=True)
        return ([[cond, {"pooled_output": pooled}]], )
comfyanonymous's avatar
comfyanonymous committed
58
59
60
61
62
63
64
65

class ConditioningCombine:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning_1": ("CONDITIONING", ), "conditioning_2": ("CONDITIONING", )}}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "combine"

66
67
    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
68
69
70
    def combine(self, conditioning_1, conditioning_2):
        return (conditioning_1 + conditioning_2, )

FizzleDorf's avatar
FizzleDorf committed
71
72
73
class ConditioningAverage :
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
74
75
        return {"required": {"conditioning_to": ("CONDITIONING", ), "conditioning_from": ("CONDITIONING", ),
                              "conditioning_to_strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01})
FizzleDorf's avatar
FizzleDorf committed
76
77
78
79
80
81
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "addWeighted"

    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
82
    def addWeighted(self, conditioning_to, conditioning_from, conditioning_to_strength):
FizzleDorf's avatar
FizzleDorf committed
83
        out = []
comfyanonymous's avatar
comfyanonymous committed
84
85
86
87
88

        if len(conditioning_from) > 1:
            print("Warning: ConditioningAverage conditioning_from contains more than 1 cond, only the first one will actually be applied to conditioning_to.")

        cond_from = conditioning_from[0][0]
89
        pooled_output_from = conditioning_from[0][1].get("pooled_output", None)
comfyanonymous's avatar
comfyanonymous committed
90
91
92

        for i in range(len(conditioning_to)):
            t1 = conditioning_to[i][0]
93
            pooled_output_to = conditioning_to[i][1].get("pooled_output", pooled_output_from)
comfyanonymous's avatar
comfyanonymous committed
94
95
96
97
98
            t0 = cond_from[:,:t1.shape[1]]
            if t0.shape[1] < t1.shape[1]:
                t0 = torch.cat([t0] + [torch.zeros((1, (t1.shape[1] - t0.shape[1]), t1.shape[2]))], dim=1)

            tw = torch.mul(t1, conditioning_to_strength) + torch.mul(t0, (1.0 - conditioning_to_strength))
99
100
101
102
103
104
105
            t_to = conditioning_to[i][1].copy()
            if pooled_output_from is not None and pooled_output_to is not None:
                t_to["pooled_output"] = torch.mul(pooled_output_to, conditioning_to_strength) + torch.mul(pooled_output_from, (1.0 - conditioning_to_strength))
            elif pooled_output_from is not None:
                t_to["pooled_output"] = pooled_output_from

            n = [tw, t_to]
FizzleDorf's avatar
FizzleDorf committed
106
107
108
            out.append(n)
        return (out, )

109
110
111
112
113
114
115
116
117
118
class ConditioningConcat:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {
            "conditioning_to": ("CONDITIONING",),
            "conditioning_from": ("CONDITIONING",),
            }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "concat"

119
    CATEGORY = "conditioning"
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136

    def concat(self, conditioning_to, conditioning_from):
        out = []

        if len(conditioning_from) > 1:
            print("Warning: ConditioningConcat conditioning_from contains more than 1 cond, only the first one will actually be applied to conditioning_to.")

        cond_from = conditioning_from[0][0]

        for i in range(len(conditioning_to)):
            t1 = conditioning_to[i][0]
            tw = torch.cat((t1, cond_from),1)
            n = [tw, conditioning_to[i][1].copy()]
            out.append(n)

        return (out, )

comfyanonymous's avatar
comfyanonymous committed
137
138
139
140
class ConditioningSetArea:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
141
142
143
144
                              "width": ("INT", {"default": 64, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 64, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
                              "x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                              "y": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
comfyanonymous's avatar
comfyanonymous committed
145
146
147
148
149
                              "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

150
151
    CATEGORY = "conditioning"

152
    def append(self, conditioning, width, height, x, y, strength):
comfyanonymous's avatar
comfyanonymous committed
153
154
155
156
157
        c = []
        for t in conditioning:
            n = [t[0], t[1].copy()]
            n[1]['area'] = (height // 8, width // 8, y // 8, x // 8)
            n[1]['strength'] = strength
158
            n[1]['set_area_to_bounds'] = False
comfyanonymous's avatar
comfyanonymous committed
159
            c.append(n)
comfyanonymous's avatar
comfyanonymous committed
160
        return (c, )
comfyanonymous's avatar
comfyanonymous committed
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
class ConditioningSetAreaPercentage:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
                              "width": ("FLOAT", {"default": 1.0, "min": 0, "max": 1.0, "step": 0.01}),
                              "height": ("FLOAT", {"default": 1.0, "min": 0, "max": 1.0, "step": 0.01}),
                              "x": ("FLOAT", {"default": 0, "min": 0, "max": 1.0, "step": 0.01}),
                              "y": ("FLOAT", {"default": 0, "min": 0, "max": 1.0, "step": 0.01}),
                              "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

    CATEGORY = "conditioning"

    def append(self, conditioning, width, height, x, y, strength):
        c = []
        for t in conditioning:
            n = [t[0], t[1].copy()]
            n[1]['area'] = ("percentage", height, width, y, x)
            n[1]['strength'] = strength
            n[1]['set_area_to_bounds'] = False
            c.append(n)
        return (c, )

187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
class ConditioningSetAreaStrength:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
                              "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

    CATEGORY = "conditioning"

    def append(self, conditioning, strength):
        c = []
        for t in conditioning:
            n = [t[0], t[1].copy()]
            n[1]['strength'] = strength
            c.append(n)
        return (c, )


Jacob Segal's avatar
Jacob Segal committed
207
208
209
210
211
212
class ConditioningSetMask:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
                              "mask": ("MASK", ),
                              "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
213
                              "set_cond_area": (["default", "mask bounds"],),
Jacob Segal's avatar
Jacob Segal committed
214
215
216
217
218
219
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

    CATEGORY = "conditioning"

220
    def append(self, conditioning, mask, set_cond_area, strength):
Jacob Segal's avatar
Jacob Segal committed
221
        c = []
222
223
224
        set_area_to_bounds = False
        if set_cond_area != "default":
            set_area_to_bounds = True
Jacob Segal's avatar
Jacob Segal committed
225
226
227
228
229
230
        if len(mask.shape) < 3:
            mask = mask.unsqueeze(0)
        for t in conditioning:
            n = [t[0], t[1].copy()]
            _, h, w = mask.shape
            n[1]['mask'] = mask
Jacob Segal's avatar
Jacob Segal committed
231
            n[1]['set_area_to_bounds'] = set_area_to_bounds
232
            n[1]['mask_strength'] = strength
Jacob Segal's avatar
Jacob Segal committed
233
234
235
            c.append(n)
        return (c, )

236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
class ConditioningZeroOut:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", )}}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "zero_out"

    CATEGORY = "advanced/conditioning"

    def zero_out(self, conditioning):
        c = []
        for t in conditioning:
            d = t[1].copy()
            if "pooled_output" in d:
                d["pooled_output"] = torch.zeros_like(d["pooled_output"])
            n = [torch.zeros_like(t[0]), d]
            c.append(n)
        return (c, )

255
256
257
258
class ConditioningSetTimestepRange:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
259
260
                             "start": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001}),
                             "end": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001})
261
262
263
264
265
266
267
268
269
270
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "set_range"

    CATEGORY = "advanced/conditioning"

    def set_range(self, conditioning, start, end):
        c = []
        for t in conditioning:
            d = t[1].copy()
271
272
            d['start_percent'] = start
            d['end_percent'] = end
273
274
275
276
            n = [t[0], d]
            c.append(n)
        return (c, )

comfyanonymous's avatar
comfyanonymous committed
277
278
279
280
281
282
283
class VAEDecode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "decode"

284
285
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
286
    def decode(self, vae, samples):
287
        return (vae.decode(samples["samples"]), )
comfyanonymous's avatar
comfyanonymous committed
288

289
290
291
class VAEDecodeTiled:
    @classmethod
    def INPUT_TYPES(s):
292
        return {"required": {"samples": ("LATENT", ), "vae": ("VAE", ),
comfyanonymous's avatar
comfyanonymous committed
293
                             "tile_size": ("INT", {"default": 512, "min": 320, "max": 4096, "step": 64})
294
                            }}
295
296
297
298
299
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "decode"

    CATEGORY = "_for_testing"

300
    def decode(self, vae, samples, tile_size):
301
        return (vae.decode_tiled(samples["samples"], tile_x=tile_size // 8, tile_y=tile_size // 8, ), )
302

comfyanonymous's avatar
comfyanonymous committed
303
304
305
306
307
308
309
class VAEEncode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "pixels": ("IMAGE", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

310
311
    CATEGORY = "latent"

312
313
314
315
    @staticmethod
    def vae_encode_crop_pixels(pixels):
        x = (pixels.shape[1] // 8) * 8
        y = (pixels.shape[2] // 8) * 8
316
        if pixels.shape[1] != x or pixels.shape[2] != y:
317
318
319
320
            x_offset = (pixels.shape[1] % 8) // 2
            y_offset = (pixels.shape[2] % 8) // 2
            pixels = pixels[:, x_offset:x + x_offset, y_offset:y + y_offset, :]
        return pixels
321

322
323
324
    def encode(self, vae, pixels):
        pixels = self.vae_encode_crop_pixels(pixels)
        t = vae.encode(pixels[:,:,:,:3])
325
        return ({"samples":t}, )
comfyanonymous's avatar
comfyanonymous committed
326

comfyanonymous's avatar
comfyanonymous committed
327
328
329
class VAEEncodeTiled:
    @classmethod
    def INPUT_TYPES(s):
330
        return {"required": {"pixels": ("IMAGE", ), "vae": ("VAE", ),
331
                             "tile_size": ("INT", {"default": 512, "min": 320, "max": 4096, "step": 64})
332
                            }}
comfyanonymous's avatar
comfyanonymous committed
333
334
335
336
337
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

    CATEGORY = "_for_testing"

338
    def encode(self, vae, pixels, tile_size):
339
        pixels = VAEEncode.vae_encode_crop_pixels(pixels)
340
        t = vae.encode_tiled(pixels[:,:,:,:3], tile_x=tile_size, tile_y=tile_size, )
comfyanonymous's avatar
comfyanonymous committed
341
        return ({"samples":t}, )
342

343
344
345
class VAEEncodeForInpaint:
    @classmethod
    def INPUT_TYPES(s):
346
        return {"required": { "pixels": ("IMAGE", ), "vae": ("VAE", ), "mask": ("MASK", ), "grow_mask_by": ("INT", {"default": 6, "min": 0, "max": 64, "step": 1}),}}
347
348
349
350
351
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

    CATEGORY = "latent/inpaint"

352
    def encode(self, vae, pixels, mask, grow_mask_by=6):
353
354
        x = (pixels.shape[1] // 8) * 8
        y = (pixels.shape[2] // 8) * 8
355
        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(pixels.shape[1], pixels.shape[2]), mode="bilinear")
356

357
        pixels = pixels.clone()
358
        if pixels.shape[1] != x or pixels.shape[2] != y:
359
360
361
362
            x_offset = (pixels.shape[1] % 8) // 2
            y_offset = (pixels.shape[2] % 8) // 2
            pixels = pixels[:,x_offset:x + x_offset, y_offset:y + y_offset,:]
            mask = mask[:,:,x_offset:x + x_offset, y_offset:y + y_offset]
363

364
        #grow mask by a few pixels to keep things seamless in latent space
365
366
367
368
369
370
371
372
        if grow_mask_by == 0:
            mask_erosion = mask
        else:
            kernel_tensor = torch.ones((1, 1, grow_mask_by, grow_mask_by))
            padding = math.ceil((grow_mask_by - 1) / 2)

            mask_erosion = torch.clamp(torch.nn.functional.conv2d(mask.round(), kernel_tensor, padding=padding), 0, 1)

373
        m = (1.0 - mask.round()).squeeze(1)
374
375
        for i in range(3):
            pixels[:,:,:,i] -= 0.5
376
            pixels[:,:,:,i] *= m
377
378
379
            pixels[:,:,:,i] += 0.5
        t = vae.encode(pixels)

380
        return ({"samples":t, "noise_mask": (mask_erosion[:,:,:x,:y].round())}, )
comfyanonymous's avatar
comfyanonymous committed
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

class InpaintModelConditioning:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"positive": ("CONDITIONING", ),
                             "negative": ("CONDITIONING", ),
                             "vae": ("VAE", ),
                             "pixels": ("IMAGE", ),
                             "mask": ("MASK", ),
                             }}

    RETURN_TYPES = ("CONDITIONING","CONDITIONING","LATENT")
    RETURN_NAMES = ("positive", "negative", "latent")
    FUNCTION = "encode"

    CATEGORY = "conditioning/inpaint"

    def encode(self, positive, negative, pixels, vae, mask):
        x = (pixels.shape[1] // 8) * 8
        y = (pixels.shape[2] // 8) * 8
        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(pixels.shape[1], pixels.shape[2]), mode="bilinear")

        orig_pixels = pixels
        pixels = orig_pixels.clone()
        if pixels.shape[1] != x or pixels.shape[2] != y:
            x_offset = (pixels.shape[1] % 8) // 2
            y_offset = (pixels.shape[2] % 8) // 2
            pixels = pixels[:,x_offset:x + x_offset, y_offset:y + y_offset,:]
            mask = mask[:,:,x_offset:x + x_offset, y_offset:y + y_offset]

        m = (1.0 - mask.round()).squeeze(1)
        for i in range(3):
            pixels[:,:,:,i] -= 0.5
            pixels[:,:,:,i] *= m
            pixels[:,:,:,i] += 0.5
        concat_latent = vae.encode(pixels)
        orig_latent = vae.encode(orig_pixels)

        out_latent = {}

        out_latent["samples"] = orig_latent
        out_latent["noise_mask"] = mask

        out = []
        for conditioning in [positive, negative]:
            c = []
            for t in conditioning:
                d = t[1].copy()
                d["concat_latent_image"] = concat_latent
                d["concat_mask"] = mask
                n = [t[0], d]
                c.append(n)
            out.append(c)
        return (out[0], out[1], out_latent)


Dr.Lt.Data's avatar
Dr.Lt.Data committed
438
439
class SaveLatent:
    def __init__(self):
440
        self.output_dir = folder_paths.get_output_directory()
Dr.Lt.Data's avatar
Dr.Lt.Data committed
441
442
443
444

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT", ),
445
                              "filename_prefix": ("STRING", {"default": "latents/ComfyUI"})},
Dr.Lt.Data's avatar
Dr.Lt.Data committed
446
447
448
449
450
451
452
453
454
455
                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
                }
    RETURN_TYPES = ()
    FUNCTION = "save"

    OUTPUT_NODE = True

    CATEGORY = "_for_testing"

    def save(self, samples, filename_prefix="ComfyUI", prompt=None, extra_pnginfo=None):
456
        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir)
Dr.Lt.Data's avatar
Dr.Lt.Data committed
457
458
459
460
461
462

        # support save metadata for latent sharing
        prompt_info = ""
        if prompt is not None:
            prompt_info = json.dumps(prompt)

463
464
465
466
467
468
        metadata = None
        if not args.disable_metadata:
            metadata = {"prompt": prompt_info}
            if extra_pnginfo is not None:
                for x in extra_pnginfo:
                    metadata[x] = json.dumps(extra_pnginfo[x])
Dr.Lt.Data's avatar
Dr.Lt.Data committed
469
470

        file = f"{filename}_{counter:05}_.latent"
471
472
473
474
475
476
477
478

        results = list()
        results.append({
            "filename": file,
            "subfolder": subfolder,
            "type": "output"
        })

Dr.Lt.Data's avatar
Dr.Lt.Data committed
479
480
        file = os.path.join(full_output_folder, file)

481
482
        output = {}
        output["latent_tensor"] = samples["samples"]
483
        output["latent_format_version_0"] = torch.tensor([])
484

485
        comfy.utils.save_torch_file(output, file, metadata=metadata)
486
        return { "ui": { "latents": results } }
Dr.Lt.Data's avatar
Dr.Lt.Data committed
487
488
489
490
491


class LoadLatent:
    @classmethod
    def INPUT_TYPES(s):
492
493
        input_dir = folder_paths.get_input_directory()
        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f)) and f.endswith(".latent")]
Dr.Lt.Data's avatar
Dr.Lt.Data committed
494
495
496
497
498
499
500
501
        return {"required": {"latent": [sorted(files), ]}, }

    CATEGORY = "_for_testing"

    RETURN_TYPES = ("LATENT", )
    FUNCTION = "load"

    def load(self, latent):
502
503
        latent_path = folder_paths.get_annotated_filepath(latent)
        latent = safetensors.torch.load_file(latent_path, device="cpu")
504
505
506
507
        multiplier = 1.0
        if "latent_format_version_0" not in latent:
            multiplier = 1.0 / 0.18215
        samples = {"samples": latent["latent_tensor"].float() * multiplier}
508
        return (samples, )
Dr.Lt.Data's avatar
Dr.Lt.Data committed
509

510
511
512
513
514
515
516
517
518
519
520
521
522
523
    @classmethod
    def IS_CHANGED(s, latent):
        image_path = folder_paths.get_annotated_filepath(latent)
        m = hashlib.sha256()
        with open(image_path, 'rb') as f:
            m.update(f.read())
        return m.digest().hex()

    @classmethod
    def VALIDATE_INPUTS(s, latent):
        if not folder_paths.exists_annotated_filepath(latent):
            return "Invalid latent file: {}".format(latent)
        return True

Dr.Lt.Data's avatar
Dr.Lt.Data committed
524

comfyanonymous's avatar
comfyanonymous committed
525
526
527
class CheckpointLoader:
    @classmethod
    def INPUT_TYPES(s):
528
529
        return {"required": { "config_name": (folder_paths.get_filename_list("configs"), ),
                              "ckpt_name": (folder_paths.get_filename_list("checkpoints"), )}}
comfyanonymous's avatar
comfyanonymous committed
530
531
532
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

533
    CATEGORY = "advanced/loaders"
534

comfyanonymous's avatar
comfyanonymous committed
535
    def load_checkpoint(self, config_name, ckpt_name, output_vae=True, output_clip=True):
536
537
        config_path = folder_paths.get_full_path("configs", config_name)
        ckpt_path = folder_paths.get_full_path("checkpoints", ckpt_name)
538
        return comfy.sd.load_checkpoint(config_path, ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
comfyanonymous's avatar
comfyanonymous committed
539

540
541
542
class CheckpointLoaderSimple:
    @classmethod
    def INPUT_TYPES(s):
543
        return {"required": { "ckpt_name": (folder_paths.get_filename_list("checkpoints"), ),
544
545
546
547
                             }}
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

548
    CATEGORY = "loaders"
549

550
    def load_checkpoint(self, ckpt_name, output_vae=True, output_clip=True):
551
        ckpt_path = folder_paths.get_full_path("checkpoints", ckpt_name)
552
        out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
553
        return out[:3]
554

sALTaccount's avatar
sALTaccount committed
555
556
557
class DiffusersLoader:
    @classmethod
    def INPUT_TYPES(cls):
558
        paths = []
sALTaccount's avatar
sALTaccount committed
559
        for search_path in folder_paths.get_folder_paths("diffusers"):
560
            if os.path.exists(search_path):
561
562
563
564
                for root, subdir, files in os.walk(search_path, followlinks=True):
                    if "model_index.json" in files:
                        paths.append(os.path.relpath(root, start=search_path))

565
        return {"required": {"model_path": (paths,), }}
sALTaccount's avatar
sALTaccount committed
566
567
568
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

569
    CATEGORY = "advanced/loaders/deprecated"
sALTaccount's avatar
sALTaccount committed
570
571

    def load_checkpoint(self, model_path, output_vae=True, output_clip=True):
sALTaccount's avatar
sALTaccount committed
572
573
        for search_path in folder_paths.get_folder_paths("diffusers"):
            if os.path.exists(search_path):
574
575
576
                path = os.path.join(search_path, model_path)
                if os.path.exists(path):
                    model_path = path
sALTaccount's avatar
sALTaccount committed
577
                    break
578

579
        return comfy.diffusers_load.load_diffusers(model_path, output_vae=output_vae, output_clip=output_clip, embedding_directory=folder_paths.get_folder_paths("embeddings"))
sALTaccount's avatar
sALTaccount committed
580
581


582
583
584
585
586
587
588
589
class unCLIPCheckpointLoader:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "ckpt_name": (folder_paths.get_filename_list("checkpoints"), ),
                             }}
    RETURN_TYPES = ("MODEL", "CLIP", "VAE", "CLIP_VISION")
    FUNCTION = "load_checkpoint"

590
    CATEGORY = "loaders"
591
592
593
594
595
596

    def load_checkpoint(self, ckpt_name, output_vae=True, output_clip=True):
        ckpt_path = folder_paths.get_full_path("checkpoints", ckpt_name)
        out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, output_clipvision=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
        return out

comfyanonymous's avatar
comfyanonymous committed
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
class CLIPSetLastLayer:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "clip": ("CLIP", ),
                              "stop_at_clip_layer": ("INT", {"default": -1, "min": -24, "max": -1, "step": 1}),
                              }}
    RETURN_TYPES = ("CLIP",)
    FUNCTION = "set_last_layer"

    CATEGORY = "conditioning"

    def set_last_layer(self, clip, stop_at_clip_layer):
        clip = clip.clone()
        clip.clip_layer(stop_at_clip_layer)
        return (clip,)

613
class LoraLoader:
614
615
616
    def __init__(self):
        self.loaded_lora = None

617
618
619
620
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
                              "clip": ("CLIP", ),
621
                              "lora_name": (folder_paths.get_filename_list("loras"), ),
622
623
                              "strength_model": ("FLOAT", {"default": 1.0, "min": -20.0, "max": 20.0, "step": 0.01}),
                              "strength_clip": ("FLOAT", {"default": 1.0, "min": -20.0, "max": 20.0, "step": 0.01}),
624
625
626
627
628
629
630
                              }}
    RETURN_TYPES = ("MODEL", "CLIP")
    FUNCTION = "load_lora"

    CATEGORY = "loaders"

    def load_lora(self, model, clip, lora_name, strength_model, strength_clip):
631
632
633
        if strength_model == 0 and strength_clip == 0:
            return (model, clip)

634
        lora_path = folder_paths.get_full_path("loras", lora_name)
635
636
637
638
639
        lora = None
        if self.loaded_lora is not None:
            if self.loaded_lora[0] == lora_path:
                lora = self.loaded_lora[1]
            else:
640
641
642
                temp = self.loaded_lora
                self.loaded_lora = None
                del temp
643
644
645
646
647
648

        if lora is None:
            lora = comfy.utils.load_torch_file(lora_path, safe_load=True)
            self.loaded_lora = (lora_path, lora)

        model_lora, clip_lora = comfy.sd.load_lora_for_models(model, clip, lora, strength_model, strength_clip)
649
650
        return (model_lora, clip_lora)

651
652
653
654
655
656
657
658
659
660
661
662
663
class LoraLoaderModelOnly(LoraLoader):
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
                              "lora_name": (folder_paths.get_filename_list("loras"), ),
                              "strength_model": ("FLOAT", {"default": 1.0, "min": -20.0, "max": 20.0, "step": 0.01}),
                              }}
    RETURN_TYPES = ("MODEL",)
    FUNCTION = "load_lora_model_only"

    def load_lora_model_only(self, model, lora_name, strength_model):
        return (self.load_lora(model, None, lora_name, strength_model, 0)[0],)

comfyanonymous's avatar
comfyanonymous committed
664
class VAELoader:
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
    @staticmethod
    def vae_list():
        vaes = folder_paths.get_filename_list("vae")
        approx_vaes = folder_paths.get_filename_list("vae_approx")
        sdxl_taesd_enc = False
        sdxl_taesd_dec = False
        sd1_taesd_enc = False
        sd1_taesd_dec = False

        for v in approx_vaes:
            if v.startswith("taesd_decoder."):
                sd1_taesd_dec = True
            elif v.startswith("taesd_encoder."):
                sd1_taesd_enc = True
            elif v.startswith("taesdxl_decoder."):
                sdxl_taesd_dec = True
            elif v.startswith("taesdxl_encoder."):
                sdxl_taesd_enc = True
        if sd1_taesd_dec and sd1_taesd_enc:
            vaes.append("taesd")
        if sdxl_taesd_dec and sdxl_taesd_enc:
            vaes.append("taesdxl")
        return vaes

    @staticmethod
    def load_taesd(name):
        sd = {}
        approx_vaes = folder_paths.get_filename_list("vae_approx")

        encoder = next(filter(lambda a: a.startswith("{}_encoder.".format(name)), approx_vaes))
        decoder = next(filter(lambda a: a.startswith("{}_decoder.".format(name)), approx_vaes))

        enc = comfy.utils.load_torch_file(folder_paths.get_full_path("vae_approx", encoder))
        for k in enc:
            sd["taesd_encoder.{}".format(k)] = enc[k]

        dec = comfy.utils.load_torch_file(folder_paths.get_full_path("vae_approx", decoder))
        for k in dec:
            sd["taesd_decoder.{}".format(k)] = dec[k]

        if name == "taesd":
            sd["vae_scale"] = torch.tensor(0.18215)
        elif name == "taesdxl":
            sd["vae_scale"] = torch.tensor(0.13025)
        return sd

comfyanonymous's avatar
comfyanonymous committed
711
712
    @classmethod
    def INPUT_TYPES(s):
713
        return {"required": { "vae_name": (s.vae_list(), )}}
comfyanonymous's avatar
comfyanonymous committed
714
715
716
    RETURN_TYPES = ("VAE",)
    FUNCTION = "load_vae"

717
718
    CATEGORY = "loaders"

comfyanonymous's avatar
comfyanonymous committed
719
720
    #TODO: scale factor?
    def load_vae(self, vae_name):
721
722
723
724
725
        if vae_name in ["taesd", "taesdxl"]:
            sd = self.load_taesd(vae_name)
        else:
            vae_path = folder_paths.get_full_path("vae", vae_name)
            sd = comfy.utils.load_torch_file(vae_path)
comfyanonymous's avatar
comfyanonymous committed
726
        vae = comfy.sd.VAE(sd=sd)
comfyanonymous's avatar
comfyanonymous committed
727
728
        return (vae,)

comfyanonymous's avatar
comfyanonymous committed
729
730
731
class ControlNetLoader:
    @classmethod
    def INPUT_TYPES(s):
732
        return {"required": { "control_net_name": (folder_paths.get_filename_list("controlnet"), )}}
comfyanonymous's avatar
comfyanonymous committed
733
734
735
736
737
738
739

    RETURN_TYPES = ("CONTROL_NET",)
    FUNCTION = "load_controlnet"

    CATEGORY = "loaders"

    def load_controlnet(self, control_net_name):
740
        controlnet_path = folder_paths.get_full_path("controlnet", control_net_name)
741
        controlnet = comfy.controlnet.load_controlnet(controlnet_path)
comfyanonymous's avatar
comfyanonymous committed
742
743
        return (controlnet,)

744
745
746
747
class DiffControlNetLoader:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
748
                              "control_net_name": (folder_paths.get_filename_list("controlnet"), )}}
749
750
751
752
753
754
755

    RETURN_TYPES = ("CONTROL_NET",)
    FUNCTION = "load_controlnet"

    CATEGORY = "loaders"

    def load_controlnet(self, model, control_net_name):
756
        controlnet_path = folder_paths.get_full_path("controlnet", control_net_name)
757
        controlnet = comfy.controlnet.load_controlnet(controlnet_path, model)
758
759
        return (controlnet,)

comfyanonymous's avatar
comfyanonymous committed
760
761
762
763

class ControlNetApply:
    @classmethod
    def INPUT_TYPES(s):
764
765
766
767
768
        return {"required": {"conditioning": ("CONDITIONING", ),
                             "control_net": ("CONTROL_NET", ),
                             "image": ("IMAGE", ),
                             "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01})
                             }}
comfyanonymous's avatar
comfyanonymous committed
769
770
771
772
773
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_controlnet"

    CATEGORY = "conditioning"

774
    def apply_controlnet(self, conditioning, control_net, image, strength):
775
776
777
        if strength == 0:
            return (conditioning, )

comfyanonymous's avatar
comfyanonymous committed
778
779
780
781
        c = []
        control_hint = image.movedim(-1,1)
        for t in conditioning:
            n = [t[0], t[1].copy()]
comfyanonymous's avatar
comfyanonymous committed
782
783
784
785
            c_net = control_net.copy().set_cond_hint(control_hint, strength)
            if 'control' in t[1]:
                c_net.set_previous_controlnet(t[1]['control'])
            n[1]['control'] = c_net
786
            n[1]['control_apply_to_uncond'] = True
comfyanonymous's avatar
comfyanonymous committed
787
788
789
            c.append(n)
        return (c, )

790
791
792
793
794
795
796
797
798

class ControlNetApplyAdvanced:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"positive": ("CONDITIONING", ),
                             "negative": ("CONDITIONING", ),
                             "control_net": ("CONTROL_NET", ),
                             "image": ("IMAGE", ),
                             "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
799
800
                             "start_percent": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001}),
                             "end_percent": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001})
801
802
803
804
805
806
807
808
                             }}

    RETURN_TYPES = ("CONDITIONING","CONDITIONING")
    RETURN_NAMES = ("positive", "negative")
    FUNCTION = "apply_controlnet"

    CATEGORY = "conditioning"

809
    def apply_controlnet(self, positive, negative, control_net, image, strength, start_percent, end_percent):
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
        if strength == 0:
            return (positive, negative)

        control_hint = image.movedim(-1,1)
        cnets = {}

        out = []
        for conditioning in [positive, negative]:
            c = []
            for t in conditioning:
                d = t[1].copy()

                prev_cnet = d.get('control', None)
                if prev_cnet in cnets:
                    c_net = cnets[prev_cnet]
                else:
826
                    c_net = control_net.copy().set_cond_hint(control_hint, strength, (start_percent, end_percent))
827
828
829
830
831
832
833
834
835
836
837
                    c_net.set_previous_controlnet(prev_cnet)
                    cnets[prev_cnet] = c_net

                d['control'] = c_net
                d['control_apply_to_uncond'] = False
                n = [t[0], d]
                c.append(n)
            out.append(c)
        return (out[0], out[1])


838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
class UNETLoader:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "unet_name": (folder_paths.get_filename_list("unet"), ),
                             }}
    RETURN_TYPES = ("MODEL",)
    FUNCTION = "load_unet"

    CATEGORY = "advanced/loaders"

    def load_unet(self, unet_name):
        unet_path = folder_paths.get_full_path("unet", unet_name)
        model = comfy.sd.load_unet(unet_path)
        return (model,)

853
854
855
class CLIPLoader:
    @classmethod
    def INPUT_TYPES(s):
856
        return {"required": { "clip_name": (folder_paths.get_filename_list("clip"), ),
857
                              "type": (["stable_diffusion", "stable_cascade"], ),
858
859
860
861
                             }}
    RETURN_TYPES = ("CLIP",)
    FUNCTION = "load_clip"

862
    CATEGORY = "advanced/loaders"
863

864
865
866
867
868
    def load_clip(self, clip_name, type="stable_diffusion"):
        clip_type = comfy.sd.CLIPType.STABLE_DIFFUSION
        if type == "stable_cascade":
            clip_type = comfy.sd.CLIPType.STABLE_CASCADE

869
        clip_path = folder_paths.get_full_path("clip", clip_name)
870
        clip = comfy.sd.load_clip(ckpt_paths=[clip_path], embedding_directory=folder_paths.get_folder_paths("embeddings"), clip_type=clip_type)
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
        return (clip,)

class DualCLIPLoader:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "clip_name1": (folder_paths.get_filename_list("clip"), ), "clip_name2": (folder_paths.get_filename_list("clip"), ),
                             }}
    RETURN_TYPES = ("CLIP",)
    FUNCTION = "load_clip"

    CATEGORY = "advanced/loaders"

    def load_clip(self, clip_name1, clip_name2):
        clip_path1 = folder_paths.get_full_path("clip", clip_name1)
        clip_path2 = folder_paths.get_full_path("clip", clip_name2)
        clip = comfy.sd.load_clip(ckpt_paths=[clip_path1, clip_path2], embedding_directory=folder_paths.get_folder_paths("embeddings"))
887
888
        return (clip,)

889
890
891
class CLIPVisionLoader:
    @classmethod
    def INPUT_TYPES(s):
892
        return {"required": { "clip_name": (folder_paths.get_filename_list("clip_vision"), ),
893
894
895
896
897
898
899
                             }}
    RETURN_TYPES = ("CLIP_VISION",)
    FUNCTION = "load_clip"

    CATEGORY = "loaders"

    def load_clip(self, clip_name):
900
        clip_path = folder_paths.get_full_path("clip_vision", clip_name)
901
        clip_vision = comfy.clip_vision.load(clip_path)
902
903
904
905
906
907
908
909
        return (clip_vision,)

class CLIPVisionEncode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "clip_vision": ("CLIP_VISION",),
                              "image": ("IMAGE",)
                             }}
comfyanonymous's avatar
comfyanonymous committed
910
    RETURN_TYPES = ("CLIP_VISION_OUTPUT",)
911
912
    FUNCTION = "encode"

913
    CATEGORY = "conditioning"
914
915
916
917
918
919
920
921

    def encode(self, clip_vision, image):
        output = clip_vision.encode_image(image)
        return (output,)

class StyleModelLoader:
    @classmethod
    def INPUT_TYPES(s):
922
        return {"required": { "style_model_name": (folder_paths.get_filename_list("style_models"), )}}
923
924
925
926
927
928
929

    RETURN_TYPES = ("STYLE_MODEL",)
    FUNCTION = "load_style_model"

    CATEGORY = "loaders"

    def load_style_model(self, style_model_name):
930
        style_model_path = folder_paths.get_full_path("style_models", style_model_name)
931
932
933
934
935
936
937
        style_model = comfy.sd.load_style_model(style_model_path)
        return (style_model,)


class StyleModelApply:
    @classmethod
    def INPUT_TYPES(s):
938
939
940
        return {"required": {"conditioning": ("CONDITIONING", ),
                             "style_model": ("STYLE_MODEL", ),
                             "clip_vision_output": ("CLIP_VISION_OUTPUT", ),
941
942
943
944
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_stylemodel"

comfyanonymous's avatar
comfyanonymous committed
945
    CATEGORY = "conditioning/style_model"
946

947
    def apply_stylemodel(self, clip_vision_output, style_model, conditioning):
948
        cond = style_model.get_cond(clip_vision_output).flatten(start_dim=0, end_dim=1).unsqueeze(dim=0)
949
        c = []
950
951
        for t in conditioning:
            n = [torch.cat((t[0], cond), dim=1), t[1].copy()]
952
953
954
            c.append(n)
        return (c, )

955
956
957
958
959
960
class unCLIPConditioning:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
                             "clip_vision_output": ("CLIP_VISION_OUTPUT", ),
                             "strength": ("FLOAT", {"default": 1.0, "min": -10.0, "max": 10.0, "step": 0.01}),
961
                             "noise_augmentation": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.01}),
962
963
964
965
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_adm"

966
    CATEGORY = "conditioning"
967

968
    def apply_adm(self, conditioning, clip_vision_output, strength, noise_augmentation):
969
970
971
        if strength == 0:
            return (conditioning, )

972
973
974
        c = []
        for t in conditioning:
            o = t[1].copy()
975
976
977
            x = {"clip_vision_output": clip_vision_output, "strength": strength, "noise_augmentation": noise_augmentation}
            if "unclip_conditioning" in o:
                o["unclip_conditioning"] = o["unclip_conditioning"][:] + [x]
978
            else:
979
                o["unclip_conditioning"] = [x]
980
981
982
983
            n = [t[0], o]
            c.append(n)
        return (c, )

984
985
986
987
988
989
990
991
class GLIGENLoader:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "gligen_name": (folder_paths.get_filename_list("gligen"), )}}

    RETURN_TYPES = ("GLIGEN",)
    FUNCTION = "load_gligen"

comfyanonymous's avatar
comfyanonymous committed
992
    CATEGORY = "loaders"
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013

    def load_gligen(self, gligen_name):
        gligen_path = folder_paths.get_full_path("gligen", gligen_name)
        gligen = comfy.sd.load_gligen(gligen_path)
        return (gligen,)

class GLIGENTextBoxApply:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning_to": ("CONDITIONING", ),
                              "clip": ("CLIP", ),
                              "gligen_textbox_model": ("GLIGEN", ),
                              "text": ("STRING", {"multiline": True}),
                              "width": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 64, "min": 8, "max": MAX_RESOLUTION, "step": 8}),
                              "x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                              "y": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

comfyanonymous's avatar
comfyanonymous committed
1014
    CATEGORY = "conditioning/gligen"
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028

    def append(self, conditioning_to, clip, gligen_textbox_model, text, width, height, x, y):
        c = []
        cond, cond_pooled = clip.encode_from_tokens(clip.tokenize(text), return_pooled=True)
        for t in conditioning_to:
            n = [t[0], t[1].copy()]
            position_params = [(cond_pooled, height // 8, width // 8, y // 8, x // 8)]
            prev = []
            if "gligen" in n[1]:
                prev = n[1]['gligen'][2]

            n[1]['gligen'] = ("position", gligen_textbox_model, prev + position_params)
            c.append(n)
        return (c, )
1029

comfyanonymous's avatar
comfyanonymous committed
1030
class EmptyLatentImage:
1031
1032
    def __init__(self):
        self.device = comfy.model_management.intermediate_device()
comfyanonymous's avatar
comfyanonymous committed
1033
1034
1035

    @classmethod
    def INPUT_TYPES(s):
1036
1037
        return {"required": { "width": ("INT", {"default": 512, "min": 16, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 512, "min": 16, "max": MAX_RESOLUTION, "step": 8}),
comfyanonymous's avatar
comfyanonymous committed
1038
                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096})}}
comfyanonymous's avatar
comfyanonymous committed
1039
1040
1041
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "generate"

1042
1043
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
1044
    def generate(self, width, height, batch_size=1):
1045
        latent = torch.zeros([batch_size, 4, height // 8, width // 8], device=self.device)
1046
        return ({"samples":latent}, )
comfyanonymous's avatar
comfyanonymous committed
1047

comfyanonymous's avatar
comfyanonymous committed
1048

1049
1050
1051
1052
1053
class LatentFromBatch:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "batch_index": ("INT", {"default": 0, "min": 0, "max": 63}),
1054
                              "length": ("INT", {"default": 1, "min": 1, "max": 64}),
1055
1056
                              }}
    RETURN_TYPES = ("LATENT",)
1057
    FUNCTION = "frombatch"
1058

1059
    CATEGORY = "latent/batch"
1060

1061
    def frombatch(self, samples, batch_index, length):
1062
1063
1064
        s = samples.copy()
        s_in = samples["samples"]
        batch_index = min(s_in.shape[0] - 1, batch_index)
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
        length = min(s_in.shape[0] - batch_index, length)
        s["samples"] = s_in[batch_index:batch_index + length].clone()
        if "noise_mask" in samples:
            masks = samples["noise_mask"]
            if masks.shape[0] == 1:
                s["noise_mask"] = masks.clone()
            else:
                if masks.shape[0] < s_in.shape[0]:
                    masks = masks.repeat(math.ceil(s_in.shape[0] / masks.shape[0]), 1, 1, 1)[:s_in.shape[0]]
                s["noise_mask"] = masks[batch_index:batch_index + length].clone()
        if "batch_index" not in s:
            s["batch_index"] = [x for x in range(batch_index, batch_index+length)]
        else:
            s["batch_index"] = samples["batch_index"][batch_index:batch_index + length]
        return (s,)
    
class RepeatLatentBatch:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "amount": ("INT", {"default": 1, "min": 1, "max": 64}),
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "repeat"

    CATEGORY = "latent/batch"

    def repeat(self, samples, amount):
        s = samples.copy()
        s_in = samples["samples"]
        
        s["samples"] = s_in.repeat((amount, 1,1,1))
        if "noise_mask" in samples and samples["noise_mask"].shape[0] > 1:
            masks = samples["noise_mask"]
            if masks.shape[0] < s_in.shape[0]:
                masks = masks.repeat(math.ceil(s_in.shape[0] / masks.shape[0]), 1, 1, 1)[:s_in.shape[0]]
            s["noise_mask"] = samples["noise_mask"].repeat((amount, 1,1,1))
        if "batch_index" in s:
            offset = max(s["batch_index"]) - min(s["batch_index"]) + 1
            s["batch_index"] = s["batch_index"] + [x + (i * offset) for i in range(1, amount) for x in s["batch_index"]]
1105
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
1106

comfyanonymous's avatar
comfyanonymous committed
1107
class LatentUpscale:
comfyanonymous's avatar
comfyanonymous committed
1108
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "bislerp"]
1109
    crop_methods = ["disabled", "center"]
comfyanonymous's avatar
comfyanonymous committed
1110
1111
1112
1113

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",), "upscale_method": (s.upscale_methods,),
1114
1115
                              "width": ("INT", {"default": 512, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 512, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
1116
                              "crop": (s.crop_methods,)}}
comfyanonymous's avatar
comfyanonymous committed
1117
1118
1119
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "upscale"

1120
1121
    CATEGORY = "latent"

1122
    def upscale(self, samples, upscale_method, width, height, crop):
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
        if width == 0 and height == 0:
            s = samples
        else:
            s = samples.copy()

            if width == 0:
                height = max(64, height)
                width = max(64, round(samples["samples"].shape[3] * height / samples["samples"].shape[2]))
            elif height == 0:
                width = max(64, width)
                height = max(64, round(samples["samples"].shape[2] * width / samples["samples"].shape[3]))
            else:
                width = max(64, width)
                height = max(64, height)

            s["samples"] = comfy.utils.common_upscale(samples["samples"], width // 8, height // 8, upscale_method, crop)
comfyanonymous's avatar
comfyanonymous committed
1139
1140
        return (s,)

comfyanonymous's avatar
comfyanonymous committed
1141
class LatentUpscaleBy:
comfyanonymous's avatar
comfyanonymous committed
1142
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "bislerp"]
comfyanonymous's avatar
comfyanonymous committed
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",), "upscale_method": (s.upscale_methods,),
                              "scale_by": ("FLOAT", {"default": 1.5, "min": 0.01, "max": 8.0, "step": 0.01}),}}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "upscale"

    CATEGORY = "latent"

    def upscale(self, samples, upscale_method, scale_by):
        s = samples.copy()
        width = round(samples["samples"].shape[3] * scale_by)
        height = round(samples["samples"].shape[2] * scale_by)
        s["samples"] = comfy.utils.common_upscale(samples["samples"], width, height, upscale_method, "disabled")
        return (s,)

comfyanonymous's avatar
comfyanonymous committed
1160
1161
1162
1163
1164
1165
1166
1167
1168
class LatentRotate:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "rotation": (["none", "90 degrees", "180 degrees", "270 degrees"],),
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "rotate"

comfyanonymous's avatar
comfyanonymous committed
1169
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
1170
1171

    def rotate(self, samples, rotation):
1172
        s = samples.copy()
comfyanonymous's avatar
comfyanonymous committed
1173
1174
1175
1176
1177
1178
1179
1180
        rotate_by = 0
        if rotation.startswith("90"):
            rotate_by = 1
        elif rotation.startswith("180"):
            rotate_by = 2
        elif rotation.startswith("270"):
            rotate_by = 3

1181
        s["samples"] = torch.rot90(samples["samples"], k=rotate_by, dims=[3, 2])
comfyanonymous's avatar
comfyanonymous committed
1182
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192

class LatentFlip:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "flip_method": (["x-axis: vertically", "y-axis: horizontally"],),
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "flip"

comfyanonymous's avatar
comfyanonymous committed
1193
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
1194
1195

    def flip(self, samples, flip_method):
1196
        s = samples.copy()
comfyanonymous's avatar
comfyanonymous committed
1197
        if flip_method.startswith("x"):
1198
            s["samples"] = torch.flip(samples["samples"], dims=[2])
comfyanonymous's avatar
comfyanonymous committed
1199
        elif flip_method.startswith("y"):
1200
            s["samples"] = torch.flip(samples["samples"], dims=[3])
comfyanonymous's avatar
comfyanonymous committed
1201
1202

        return (s,)
comfyanonymous's avatar
comfyanonymous committed
1203
1204
1205
1206

class LatentComposite:
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
1207
1208
1209
1210
1211
1212
        return {"required": { "samples_to": ("LATENT",),
                              "samples_from": ("LATENT",),
                              "x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                              "y": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                              "feather": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                              }}
comfyanonymous's avatar
comfyanonymous committed
1213
1214
1215
1216
1217
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "composite"

    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
1218
1219
1220
    def composite(self, samples_to, samples_from, x, y, composite_method="normal", feather=0):
        x =  x // 8
        y = y // 8
1221
        feather = feather // 8
comfyanonymous's avatar
comfyanonymous committed
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
        samples_out = samples_to.copy()
        s = samples_to["samples"].clone()
        samples_to = samples_to["samples"]
        samples_from = samples_from["samples"]
        if feather == 0:
            s[:,:,y:y+samples_from.shape[2],x:x+samples_from.shape[3]] = samples_from[:,:,:samples_to.shape[2] - y, :samples_to.shape[3] - x]
        else:
            samples_from = samples_from[:,:,:samples_to.shape[2] - y, :samples_to.shape[3] - x]
            mask = torch.ones_like(samples_from)
            for t in range(feather):
                if y != 0:
                    mask[:,:,t:1+t,:] *= ((1.0/feather) * (t + 1))

                if y + samples_from.shape[2] < samples_to.shape[2]:
                    mask[:,:,mask.shape[2] -1 -t: mask.shape[2]-t,:] *= ((1.0/feather) * (t + 1))
                if x != 0:
                    mask[:,:,:,t:1+t] *= ((1.0/feather) * (t + 1))
                if x + samples_from.shape[3] < samples_to.shape[3]:
                    mask[:,:,:,mask.shape[3]- 1 - t: mask.shape[3]- t] *= ((1.0/feather) * (t + 1))
            rev_mask = torch.ones_like(mask) - mask
            s[:,:,y:y+samples_from.shape[2],x:x+samples_from.shape[3]] = samples_from[:,:,:samples_to.shape[2] - y, :samples_to.shape[3] - x] * mask + s[:,:,y:y+samples_from.shape[2],x:x+samples_from.shape[3]] * rev_mask
        samples_out["samples"] = s
        return (samples_out,)
comfyanonymous's avatar
comfyanonymous committed
1245

1246
1247
1248
1249
class LatentBlend:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {
1250
1251
            "samples1": ("LATENT",),
            "samples2": ("LATENT",),
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
            "blend_factor": ("FLOAT", {
                "default": 0.5,
                "min": 0,
                "max": 1,
                "step": 0.01
            }),
        }}

    RETURN_TYPES = ("LATENT",)
    FUNCTION = "blend"

    CATEGORY = "_for_testing"

1265
    def blend(self, samples1, samples2, blend_factor:float, blend_mode: str="normal"):
1266

1267
1268
1269
        samples_out = samples1.copy()
        samples1 = samples1["samples"]
        samples2 = samples2["samples"]
1270

1271
1272
1273
1274
        if samples1.shape != samples2.shape:
            samples2.permute(0, 3, 1, 2)
            samples2 = comfy.utils.common_upscale(samples2, samples1.shape[3], samples1.shape[2], 'bicubic', crop='center')
            samples2.permute(0, 2, 3, 1)
1275

1276
1277
        samples_blended = self.blend_mode(samples1, samples2, blend_mode)
        samples_blended = samples1 * blend_factor + samples_blended * (1 - blend_factor)
1278
1279
1280
1281
1282
1283
1284
1285
1286
        samples_out["samples"] = samples_blended
        return (samples_out,)

    def blend_mode(self, img1, img2, mode):
        if mode == "normal":
            return img2
        else:
            raise ValueError(f"Unsupported blend mode: {mode}")

comfyanonymous's avatar
comfyanonymous committed
1287
1288
1289
1290
class LatentCrop:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
1291
1292
                              "width": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
1293
1294
                              "x": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                              "y": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
comfyanonymous's avatar
comfyanonymous committed
1295
1296
1297
1298
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "crop"

comfyanonymous's avatar
comfyanonymous committed
1299
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
1300
1301

    def crop(self, samples, width, height, x, y):
1302
1303
        s = samples.copy()
        samples = samples['samples']
comfyanonymous's avatar
comfyanonymous committed
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
        x =  x // 8
        y = y // 8

        #enfonce minimum size of 64
        if x > (samples.shape[3] - 8):
            x = samples.shape[3] - 8
        if y > (samples.shape[2] - 8):
            y = samples.shape[2] - 8

        new_height = height // 8
        new_width = width // 8
        to_x = new_width + x
        to_y = new_height + y
1317
        s['samples'] = samples[:,:,y:to_y, x:to_x]
comfyanonymous's avatar
comfyanonymous committed
1318
1319
        return (s,)

1320
1321
1322
1323
1324
1325
1326
1327
1328
class SetLatentNoiseMask:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "mask": ("MASK",),
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "set_mask"

1329
    CATEGORY = "latent/inpaint"
1330
1331
1332

    def set_mask(self, samples, mask):
        s = samples.copy()
1333
        s["noise_mask"] = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1]))
1334
1335
        return (s,)

space-nuko's avatar
space-nuko committed
1336
def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent, denoise=1.0, disable_noise=False, start_step=None, last_step=None, force_full_denoise=False):
1337
    latent_image = latent["samples"]
comfyanonymous's avatar
comfyanonymous committed
1338
1339
1340
    if disable_noise:
        noise = torch.zeros(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, device="cpu")
    else:
1341
1342
        batch_inds = latent["batch_index"] if "batch_index" in latent else None
        noise = comfy.sample.prepare_noise(latent_image, seed, batch_inds)
comfyanonymous's avatar
comfyanonymous committed
1343

1344
    noise_mask = None
1345
    if "noise_mask" in latent:
1346
        noise_mask = latent["noise_mask"]
comfyanonymous's avatar
comfyanonymous committed
1347

1348
    callback = latent_preview.prepare_callback(model, steps)
1349
    disable_pbar = not comfy.utils.PROGRESS_BAR_ENABLED
1350
1351
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
                                  denoise=denoise, disable_noise=disable_noise, start_step=start_step, last_step=last_step,
comfyanonymous's avatar
comfyanonymous committed
1352
                                  force_full_denoise=force_full_denoise, noise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
1353
1354
1355
    out = latent.copy()
    out["samples"] = samples
    return (out, )
comfyanonymous's avatar
comfyanonymous committed
1356

comfyanonymous's avatar
comfyanonymous committed
1357
1358
1359
class KSampler:
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
1360
        return {"required":
comfyanonymous's avatar
comfyanonymous committed
1361
1362
1363
                    {"model": ("MODEL",),
                    "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
                    "steps": ("INT", {"default": 20, "min": 1, "max": 10000}),
1364
                    "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01}),
comfyanonymous's avatar
comfyanonymous committed
1365
1366
1367
1368
1369
1370
                    "sampler_name": (comfy.samplers.KSampler.SAMPLERS, ),
                    "scheduler": (comfy.samplers.KSampler.SCHEDULERS, ),
                    "positive": ("CONDITIONING", ),
                    "negative": ("CONDITIONING", ),
                    "latent_image": ("LATENT", ),
                    "denoise": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01}),
space-nuko's avatar
space-nuko committed
1371
1372
                     }
                }
comfyanonymous's avatar
comfyanonymous committed
1373
1374
1375
1376

    RETURN_TYPES = ("LATENT",)
    FUNCTION = "sample"

1377
1378
    CATEGORY = "sampling"

space-nuko's avatar
space-nuko committed
1379
1380
    def sample(self, model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=1.0):
        return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
comfyanonymous's avatar
comfyanonymous committed
1381

comfyanonymous's avatar
comfyanonymous committed
1382
1383
1384
1385
1386
1387
1388
1389
class KSamplerAdvanced:
    @classmethod
    def INPUT_TYPES(s):
        return {"required":
                    {"model": ("MODEL",),
                    "add_noise": (["enable", "disable"], ),
                    "noise_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
                    "steps": ("INT", {"default": 20, "min": 1, "max": 10000}),
1390
                    "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01}),
comfyanonymous's avatar
comfyanonymous committed
1391
1392
1393
1394
1395
1396
1397
1398
                    "sampler_name": (comfy.samplers.KSampler.SAMPLERS, ),
                    "scheduler": (comfy.samplers.KSampler.SCHEDULERS, ),
                    "positive": ("CONDITIONING", ),
                    "negative": ("CONDITIONING", ),
                    "latent_image": ("LATENT", ),
                    "start_at_step": ("INT", {"default": 0, "min": 0, "max": 10000}),
                    "end_at_step": ("INT", {"default": 10000, "min": 0, "max": 10000}),
                    "return_with_leftover_noise": (["disable", "enable"], ),
space-nuko's avatar
space-nuko committed
1399
1400
                     }
                }
comfyanonymous's avatar
comfyanonymous committed
1401
1402
1403
1404
1405

    RETURN_TYPES = ("LATENT",)
    FUNCTION = "sample"

    CATEGORY = "sampling"
comfyanonymous's avatar
comfyanonymous committed
1406

space-nuko's avatar
space-nuko committed
1407
    def sample(self, model, add_noise, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, start_at_step, end_at_step, return_with_leftover_noise, denoise=1.0):
comfyanonymous's avatar
comfyanonymous committed
1408
1409
1410
1411
1412
1413
        force_full_denoise = True
        if return_with_leftover_noise == "enable":
            force_full_denoise = False
        disable_noise = False
        if add_noise == "disable":
            disable_noise = True
space-nuko's avatar
space-nuko committed
1414
        return common_ksampler(model, noise_seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise, disable_noise=disable_noise, start_step=start_at_step, last_step=end_at_step, force_full_denoise=force_full_denoise)
comfyanonymous's avatar
comfyanonymous committed
1415
1416
1417

class SaveImage:
    def __init__(self):
1418
        self.output_dir = folder_paths.get_output_directory()
m957ymj75urz's avatar
m957ymj75urz committed
1419
        self.type = "output"
1420
        self.prefix_append = ""
1421
        self.compress_level = 4
comfyanonymous's avatar
comfyanonymous committed
1422
1423
1424
1425

    @classmethod
    def INPUT_TYPES(s):
        return {"required": 
1426
                    {"images": ("IMAGE", ),
pythongosssss's avatar
tidy  
pythongosssss committed
1427
                     "filename_prefix": ("STRING", {"default": "ComfyUI"})},
pythongosssss's avatar
pythongosssss committed
1428
                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
comfyanonymous's avatar
comfyanonymous committed
1429
1430
1431
1432
1433
1434
1435
                }

    RETURN_TYPES = ()
    FUNCTION = "save_images"

    OUTPUT_NODE = True

1436
1437
    CATEGORY = "image"

pythongosssss's avatar
tidy  
pythongosssss committed
1438
    def save_images(self, images, filename_prefix="ComfyUI", prompt=None, extra_pnginfo=None):
1439
        filename_prefix += self.prefix_append
1440
        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir, images[0].shape[1], images[0].shape[0])
m957ymj75urz's avatar
m957ymj75urz committed
1441
        results = list()
1442
        for (batch_number, image) in enumerate(images):
comfyanonymous's avatar
comfyanonymous committed
1443
            i = 255. * image.cpu().numpy()
1444
            img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
1445
1446
1447
1448
1449
1450
1451
1452
            metadata = None
            if not args.disable_metadata:
                metadata = PngInfo()
                if prompt is not None:
                    metadata.add_text("prompt", json.dumps(prompt))
                if extra_pnginfo is not None:
                    for x in extra_pnginfo:
                        metadata.add_text(x, json.dumps(extra_pnginfo[x]))
1453

1454
1455
            filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
            file = f"{filename_with_batch_num}_{counter:05}_.png"
1456
            img.save(os.path.join(full_output_folder, file), pnginfo=metadata, compress_level=self.compress_level)
m957ymj75urz's avatar
m957ymj75urz committed
1457
1458
1459
1460
            results.append({
                "filename": file,
                "subfolder": subfolder,
                "type": self.type
Gavroche CryptoRUSH's avatar
Gavroche CryptoRUSH committed
1461
            })
1462
            counter += 1
comfyanonymous's avatar
comfyanonymous committed
1463

m957ymj75urz's avatar
m957ymj75urz committed
1464
        return { "ui": { "images": results } }
comfyanonymous's avatar
comfyanonymous committed
1465

pythongosssss's avatar
pythongosssss committed
1466
1467
class PreviewImage(SaveImage):
    def __init__(self):
1468
        self.output_dir = folder_paths.get_temp_directory()
m957ymj75urz's avatar
m957ymj75urz committed
1469
        self.type = "temp"
1470
        self.prefix_append = "_temp_" + ''.join(random.choice("abcdefghijklmnopqrstupvxyz") for x in range(5))
1471
        self.compress_level = 1
pythongosssss's avatar
pythongosssss committed
1472
1473
1474

    @classmethod
    def INPUT_TYPES(s):
1475
        return {"required":
pythongosssss's avatar
pythongosssss committed
1476
1477
1478
                    {"images": ("IMAGE", ), },
                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
                }
1479

1480
1481
1482
class LoadImage:
    @classmethod
    def INPUT_TYPES(s):
1483
        input_dir = folder_paths.get_input_directory()
comfyanonymous's avatar
comfyanonymous committed
1484
        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
1485
        return {"required":
1486
                    {"image": (sorted(files), {"image_upload": True})},
1487
                }
1488
1489

    CATEGORY = "image"
1490

1491
    RETURN_TYPES = ("IMAGE", "MASK")
1492
1493
    FUNCTION = "load_image"
    def load_image(self, image):
1494
        image_path = folder_paths.get_annotated_filepath(image)
1495
1496
1497
1498
1499
        img = Image.open(image_path)
        output_images = []
        output_masks = []
        for i in ImageSequence.Iterator(img):
            i = ImageOps.exif_transpose(i)
1500
1501
            if i.mode == 'I':
                i = i.point(lambda i: i * (1 / 255))
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
            image = i.convert("RGB")
            image = np.array(image).astype(np.float32) / 255.0
            image = torch.from_numpy(image)[None,]
            if 'A' in i.getbands():
                mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
                mask = 1. - torch.from_numpy(mask)
            else:
                mask = torch.zeros((64,64), dtype=torch.float32, device="cpu")
            output_images.append(image)
            output_masks.append(mask.unsqueeze(0))

        if len(output_images) > 1:
            output_image = torch.cat(output_images, dim=0)
            output_mask = torch.cat(output_masks, dim=0)
1516
        else:
1517
1518
1519
1520
            output_image = output_images[0]
            output_mask = output_masks[0]

        return (output_image, output_mask)
1521

1522
1523
    @classmethod
    def IS_CHANGED(s, image):
1524
        image_path = folder_paths.get_annotated_filepath(image)
1525
1526
1527
1528
        m = hashlib.sha256()
        with open(image_path, 'rb') as f:
            m.update(f.read())
        return m.digest().hex()
pythongosssss's avatar
pythongosssss committed
1529

1530
1531
1532
1533
1534
1535
1536
    @classmethod
    def VALIDATE_INPUTS(s, image):
        if not folder_paths.exists_annotated_filepath(image):
            return "Invalid image file: {}".format(image)

        return True

1537
class LoadImageMask:
1538
    _color_channels = ["alpha", "red", "green", "blue"]
1539
1540
    @classmethod
    def INPUT_TYPES(s):
1541
        input_dir = folder_paths.get_input_directory()
comfyanonymous's avatar
comfyanonymous committed
1542
        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
1543
        return {"required":
1544
                    {"image": (sorted(files), {"image_upload": True}),
1545
                     "channel": (s._color_channels, ), }
1546
1547
                }

1548
    CATEGORY = "mask"
1549
1550
1551
1552

    RETURN_TYPES = ("MASK",)
    FUNCTION = "load_image"
    def load_image(self, image, channel):
1553
        image_path = folder_paths.get_annotated_filepath(image)
1554
        i = Image.open(image_path)
1555
        i = ImageOps.exif_transpose(i)
1556
        if i.getbands() != ("R", "G", "B", "A"):
1557
1558
            if i.mode == 'I':
                i = i.point(lambda i: i * (1 / 255))
1559
            i = i.convert("RGBA")
1560
1561
1562
1563
1564
1565
1566
1567
1568
        mask = None
        c = channel[0].upper()
        if c in i.getbands():
            mask = np.array(i.getchannel(c)).astype(np.float32) / 255.0
            mask = torch.from_numpy(mask)
            if c == 'A':
                mask = 1. - mask
        else:
            mask = torch.zeros((64,64), dtype=torch.float32, device="cpu")
1569
        return (mask.unsqueeze(0),)
1570
1571
1572

    @classmethod
    def IS_CHANGED(s, image, channel):
1573
        image_path = folder_paths.get_annotated_filepath(image)
1574
1575
1576
1577
        m = hashlib.sha256()
        with open(image_path, 'rb') as f:
            m.update(f.read())
        return m.digest().hex()
pythongosssss's avatar
pythongosssss committed
1578

1579
    @classmethod
1580
    def VALIDATE_INPUTS(s, image):
1581
1582
1583
1584
1585
        if not folder_paths.exists_annotated_filepath(image):
            return "Invalid image file: {}".format(image)

        return True

comfyanonymous's avatar
comfyanonymous committed
1586
class ImageScale:
1587
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "lanczos"]
comfyanonymous's avatar
comfyanonymous committed
1588
1589
1590
1591
1592
    crop_methods = ["disabled", "center"]

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "image": ("IMAGE",), "upscale_method": (s.upscale_methods,),
1593
1594
                              "width": ("INT", {"default": 512, "min": 0, "max": MAX_RESOLUTION, "step": 1}),
                              "height": ("INT", {"default": 512, "min": 0, "max": MAX_RESOLUTION, "step": 1}),
comfyanonymous's avatar
comfyanonymous committed
1595
1596
1597
1598
                              "crop": (s.crop_methods,)}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "upscale"

1599
    CATEGORY = "image/upscaling"
1600

comfyanonymous's avatar
comfyanonymous committed
1601
    def upscale(self, image, upscale_method, width, height, crop):
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
        if width == 0 and height == 0:
            s = image
        else:
            samples = image.movedim(-1,1)

            if width == 0:
                width = max(1, round(samples.shape[3] * height / samples.shape[2]))
            elif height == 0:
                height = max(1, round(samples.shape[2] * width / samples.shape[3]))

            s = comfy.utils.common_upscale(samples, width, height, upscale_method, crop)
            s = s.movedim(1,-1)
comfyanonymous's avatar
comfyanonymous committed
1614
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
1615

comfyanonymous's avatar
comfyanonymous committed
1616
class ImageScaleBy:
1617
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "lanczos"]
comfyanonymous's avatar
comfyanonymous committed
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "image": ("IMAGE",), "upscale_method": (s.upscale_methods,),
                              "scale_by": ("FLOAT", {"default": 1.0, "min": 0.01, "max": 8.0, "step": 0.01}),}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "upscale"

    CATEGORY = "image/upscaling"

    def upscale(self, image, upscale_method, scale_by):
        samples = image.movedim(-1,1)
        width = round(samples.shape[3] * scale_by)
        height = round(samples.shape[2] * scale_by)
        s = comfy.utils.common_upscale(samples, width, height, upscale_method, "disabled")
        s = s.movedim(1,-1)
        return (s,)

1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
class ImageInvert:

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "image": ("IMAGE",)}}

    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "invert"

    CATEGORY = "image"

    def invert(self, image):
        s = 1.0 - image
        return (s,)

1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
class ImageBatch:

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "image1": ("IMAGE",), "image2": ("IMAGE",)}}

    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "batch"

    CATEGORY = "image"

    def batch(self, image1, image2):
        if image1.shape[1:] != image2.shape[1:]:
            image2 = comfy.utils.common_upscale(image2.movedim(-1,1), image1.shape[2], image1.shape[1], "bilinear", "center").movedim(1,-1)
        s = torch.cat((image1, image2), dim=0)
        return (s,)
1667

comfyanonymous's avatar
comfyanonymous committed
1668
1669
1670
1671
1672
1673
1674
1675
class EmptyImage:
    def __init__(self, device="cpu"):
        self.device = device

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "width": ("INT", {"default": 512, "min": 1, "max": MAX_RESOLUTION, "step": 1}),
                              "height": ("INT", {"default": 512, "min": 1, "max": MAX_RESOLUTION, "step": 1}),
comfyanonymous's avatar
comfyanonymous committed
1676
                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
comfyanonymous's avatar
comfyanonymous committed
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
                              "color": ("INT", {"default": 0, "min": 0, "max": 0xFFFFFF, "step": 1, "display": "color"}),
                              }}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "generate"

    CATEGORY = "image"

    def generate(self, width, height, batch_size=1, color=0):
        r = torch.full([batch_size, height, width, 1], ((color >> 16) & 0xFF) / 0xFF)
        g = torch.full([batch_size, height, width, 1], ((color >> 8) & 0xFF) / 0xFF)
        b = torch.full([batch_size, height, width, 1], ((color) & 0xFF) / 0xFF)
        return (torch.cat((r, g, b), dim=-1), )

Guo Y.K's avatar
Guo Y.K committed
1690
1691
1692
1693
1694
1695
1696
class ImagePadForOutpaint:

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "image": ("IMAGE",),
1697
1698
1699
1700
                "left": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                "top": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                "right": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                "bottom": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
1701
                "feathering": ("INT", {"default": 40, "min": 0, "max": MAX_RESOLUTION, "step": 1}),
Guo Y.K's avatar
Guo Y.K committed
1702
1703
1704
1705
1706
1707
1708
1709
            }
        }

    RETURN_TYPES = ("IMAGE", "MASK")
    FUNCTION = "expand_image"

    CATEGORY = "image"

1710
    def expand_image(self, image, left, top, right, bottom, feathering):
Guo Y.K's avatar
Guo Y.K committed
1711
1712
        d1, d2, d3, d4 = image.size()

1713
        new_image = torch.ones(
Guo Y.K's avatar
Guo Y.K committed
1714
1715
            (d1, d2 + top + bottom, d3 + left + right, d4),
            dtype=torch.float32,
1716
1717
        ) * 0.5

Guo Y.K's avatar
Guo Y.K committed
1718
1719
1720
1721
1722
1723
        new_image[:, top:top + d2, left:left + d3, :] = image

        mask = torch.ones(
            (d2 + top + bottom, d3 + left + right),
            dtype=torch.float32,
        )
1724

1725
1726
1727
1728
1729
        t = torch.zeros(
            (d2, d3),
            dtype=torch.float32
        )

1730
        if feathering > 0 and feathering * 2 < d2 and feathering * 2 < d3:
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749

            for i in range(d2):
                for j in range(d3):
                    dt = i if top != 0 else d2
                    db = d2 - i if bottom != 0 else d2

                    dl = j if left != 0 else d3
                    dr = d3 - j if right != 0 else d3

                    d = min(dt, db, dl, dr)

                    if d >= feathering:
                        continue

                    v = (feathering - d) / feathering

                    t[i, j] = v * v

        mask[top:top + d2, left:left + d3] = t
1750

Guo Y.K's avatar
Guo Y.K committed
1751
1752
1753
        return (new_image, mask)


comfyanonymous's avatar
comfyanonymous committed
1754
1755
NODE_CLASS_MAPPINGS = {
    "KSampler": KSampler,
1756
    "CheckpointLoaderSimple": CheckpointLoaderSimple,
comfyanonymous's avatar
comfyanonymous committed
1757
    "CLIPTextEncode": CLIPTextEncode,
comfyanonymous's avatar
comfyanonymous committed
1758
    "CLIPSetLastLayer": CLIPSetLastLayer,
comfyanonymous's avatar
comfyanonymous committed
1759
1760
    "VAEDecode": VAEDecode,
    "VAEEncode": VAEEncode,
1761
    "VAEEncodeForInpaint": VAEEncodeForInpaint,
comfyanonymous's avatar
comfyanonymous committed
1762
1763
1764
    "VAELoader": VAELoader,
    "EmptyLatentImage": EmptyLatentImage,
    "LatentUpscale": LatentUpscale,
comfyanonymous's avatar
comfyanonymous committed
1765
    "LatentUpscaleBy": LatentUpscaleBy,
1766
    "LatentFromBatch": LatentFromBatch,
1767
    "RepeatLatentBatch": RepeatLatentBatch,
comfyanonymous's avatar
comfyanonymous committed
1768
    "SaveImage": SaveImage,
pythongosssss's avatar
pythongosssss committed
1769
    "PreviewImage": PreviewImage,
comfyanonymous's avatar
comfyanonymous committed
1770
    "LoadImage": LoadImage,
1771
    "LoadImageMask": LoadImageMask,
comfyanonymous's avatar
comfyanonymous committed
1772
    "ImageScale": ImageScale,
comfyanonymous's avatar
comfyanonymous committed
1773
    "ImageScaleBy": ImageScaleBy,
1774
    "ImageInvert": ImageInvert,
1775
    "ImageBatch": ImageBatch,
Guo Y.K's avatar
Guo Y.K committed
1776
    "ImagePadForOutpaint": ImagePadForOutpaint,
comfyanonymous's avatar
comfyanonymous committed
1777
    "EmptyImage": EmptyImage,
comfyanonymous's avatar
comfyanonymous committed
1778
    "ConditioningAverage": ConditioningAverage ,
comfyanonymous's avatar
comfyanonymous committed
1779
    "ConditioningCombine": ConditioningCombine,
1780
    "ConditioningConcat": ConditioningConcat,
comfyanonymous's avatar
comfyanonymous committed
1781
    "ConditioningSetArea": ConditioningSetArea,
1782
    "ConditioningSetAreaPercentage": ConditioningSetAreaPercentage,
1783
    "ConditioningSetAreaStrength": ConditioningSetAreaStrength,
Jacob Segal's avatar
Jacob Segal committed
1784
    "ConditioningSetMask": ConditioningSetMask,
comfyanonymous's avatar
comfyanonymous committed
1785
    "KSamplerAdvanced": KSamplerAdvanced,
1786
    "SetLatentNoiseMask": SetLatentNoiseMask,
comfyanonymous's avatar
comfyanonymous committed
1787
    "LatentComposite": LatentComposite,
1788
    "LatentBlend": LatentBlend,
comfyanonymous's avatar
comfyanonymous committed
1789
    "LatentRotate": LatentRotate,
comfyanonymous's avatar
comfyanonymous committed
1790
    "LatentFlip": LatentFlip,
comfyanonymous's avatar
comfyanonymous committed
1791
    "LatentCrop": LatentCrop,
1792
    "LoraLoader": LoraLoader,
1793
    "CLIPLoader": CLIPLoader,
1794
    "UNETLoader": UNETLoader,
1795
    "DualCLIPLoader": DualCLIPLoader,
1796
    "CLIPVisionEncode": CLIPVisionEncode,
1797
    "StyleModelApply": StyleModelApply,
1798
    "unCLIPConditioning": unCLIPConditioning,
comfyanonymous's avatar
comfyanonymous committed
1799
    "ControlNetApply": ControlNetApply,
1800
    "ControlNetApplyAdvanced": ControlNetApplyAdvanced,
comfyanonymous's avatar
comfyanonymous committed
1801
    "ControlNetLoader": ControlNetLoader,
1802
    "DiffControlNetLoader": DiffControlNetLoader,
comfyanonymous's avatar
comfyanonymous committed
1803
1804
    "StyleModelLoader": StyleModelLoader,
    "CLIPVisionLoader": CLIPVisionLoader,
1805
    "VAEDecodeTiled": VAEDecodeTiled,
comfyanonymous's avatar
comfyanonymous committed
1806
    "VAEEncodeTiled": VAEEncodeTiled,
1807
    "unCLIPCheckpointLoader": unCLIPCheckpointLoader,
1808
1809
    "GLIGENLoader": GLIGENLoader,
    "GLIGENTextBoxApply": GLIGENTextBoxApply,
1810
    "InpaintModelConditioning": InpaintModelConditioning,
1811

1812
    "CheckpointLoader": CheckpointLoader,
sALTaccount's avatar
sALTaccount committed
1813
    "DiffusersLoader": DiffusersLoader,
Dr.Lt.Data's avatar
Dr.Lt.Data committed
1814
1815

    "LoadLatent": LoadLatent,
1816
    "SaveLatent": SaveLatent,
1817
1818

    "ConditioningZeroOut": ConditioningZeroOut,
1819
    "ConditioningSetTimestepRange": ConditioningSetTimestepRange,
1820
    "LoraLoaderModelOnly": LoraLoaderModelOnly,
comfyanonymous's avatar
comfyanonymous committed
1821
1822
}

City's avatar
City committed
1823
1824
1825
1826
1827
NODE_DISPLAY_NAME_MAPPINGS = {
    # Sampling
    "KSampler": "KSampler",
    "KSamplerAdvanced": "KSampler (Advanced)",
    # Loaders
1828
    "CheckpointLoader": "Load Checkpoint With Config (DEPRECATED)",
comfyanonymous's avatar
Rename.  
comfyanonymous committed
1829
    "CheckpointLoaderSimple": "Load Checkpoint",
City's avatar
City committed
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
    "VAELoader": "Load VAE",
    "LoraLoader": "Load LoRA",
    "CLIPLoader": "Load CLIP",
    "ControlNetLoader": "Load ControlNet Model",
    "DiffControlNetLoader": "Load ControlNet Model (diff)",
    "StyleModelLoader": "Load Style Model",
    "CLIPVisionLoader": "Load CLIP Vision",
    "UpscaleModelLoader": "Load Upscale Model",
    # Conditioning
    "CLIPVisionEncode": "CLIP Vision Encode",
    "StyleModelApply": "Apply Style Model",
    "CLIPTextEncode": "CLIP Text Encode (Prompt)",
    "CLIPSetLastLayer": "CLIP Set Last Layer",
    "ConditioningCombine": "Conditioning (Combine)",
FizzleDorf's avatar
FizzleDorf committed
1844
    "ConditioningAverage ": "Conditioning (Average)",
1845
    "ConditioningConcat": "Conditioning (Concat)",
City's avatar
City committed
1846
    "ConditioningSetArea": "Conditioning (Set Area)",
1847
    "ConditioningSetAreaPercentage": "Conditioning (Set Area with Percentage)",
Jacob Segal's avatar
Jacob Segal committed
1848
    "ConditioningSetMask": "Conditioning (Set Mask)",
City's avatar
City committed
1849
    "ControlNetApply": "Apply ControlNet",
1850
    "ControlNetApplyAdvanced": "Apply ControlNet (Advanced)",
City's avatar
City committed
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
    # Latent
    "VAEEncodeForInpaint": "VAE Encode (for Inpainting)",
    "SetLatentNoiseMask": "Set Latent Noise Mask",
    "VAEDecode": "VAE Decode",
    "VAEEncode": "VAE Encode",
    "LatentRotate": "Rotate Latent",
    "LatentFlip": "Flip Latent",
    "LatentCrop": "Crop Latent",
    "EmptyLatentImage": "Empty Latent Image",
    "LatentUpscale": "Upscale Latent",
comfyanonymous's avatar
comfyanonymous committed
1861
    "LatentUpscaleBy": "Upscale Latent By",
City's avatar
City committed
1862
    "LatentComposite": "Latent Composite",
1863
    "LatentBlend": "Latent Blend",
1864
1865
    "LatentFromBatch" : "Latent From Batch",
    "RepeatLatentBatch": "Repeat Latent Batch",
City's avatar
City committed
1866
1867
1868
1869
1870
1871
    # Image
    "SaveImage": "Save Image",
    "PreviewImage": "Preview Image",
    "LoadImage": "Load Image",
    "LoadImageMask": "Load Image (as Mask)",
    "ImageScale": "Upscale Image",
comfyanonymous's avatar
comfyanonymous committed
1872
    "ImageScaleBy": "Upscale Image By",
City's avatar
City committed
1873
1874
1875
    "ImageUpscaleWithModel": "Upscale Image (using Model)",
    "ImageInvert": "Invert Image",
    "ImagePadForOutpaint": "Pad Image for Outpainting",
1876
    "ImageBatch": "Batch Images",
City's avatar
City committed
1877
1878
1879
1880
1881
    # _for_testing
    "VAEDecodeTiled": "VAE Decode (Tiled)",
    "VAEEncodeTiled": "VAE Encode (Tiled)",
}

1882
1883
EXTENSION_WEB_DIRS = {}

1884
def load_custom_node(module_path, ignore=set()):
1885
1886
1887
1888
1889
1890
1891
    module_name = os.path.basename(module_path)
    if os.path.isfile(module_path):
        sp = os.path.splitext(module_path)
        module_name = sp[0]
    try:
        if os.path.isfile(module_path):
            module_spec = importlib.util.spec_from_file_location(module_name, module_path)
1892
            module_dir = os.path.split(module_path)[0]
1893
1894
        else:
            module_spec = importlib.util.spec_from_file_location(module_name, os.path.join(module_path, "__init__.py"))
1895
1896
            module_dir = module_path

1897
1898
1899
        module = importlib.util.module_from_spec(module_spec)
        sys.modules[module_name] = module
        module_spec.loader.exec_module(module)
1900
1901
1902
1903
1904
1905

        if hasattr(module, "WEB_DIRECTORY") and getattr(module, "WEB_DIRECTORY") is not None:
            web_dir = os.path.abspath(os.path.join(module_dir, getattr(module, "WEB_DIRECTORY")))
            if os.path.isdir(web_dir):
                EXTENSION_WEB_DIRS[module_name] = web_dir

1906
        if hasattr(module, "NODE_CLASS_MAPPINGS") and getattr(module, "NODE_CLASS_MAPPINGS") is not None:
1907
1908
1909
            for name in module.NODE_CLASS_MAPPINGS:
                if name not in ignore:
                    NODE_CLASS_MAPPINGS[name] = module.NODE_CLASS_MAPPINGS[name]
1910
1911
            if hasattr(module, "NODE_DISPLAY_NAME_MAPPINGS") and getattr(module, "NODE_DISPLAY_NAME_MAPPINGS") is not None:
                NODE_DISPLAY_NAME_MAPPINGS.update(module.NODE_DISPLAY_NAME_MAPPINGS)
1912
            return True
1913
1914
        else:
            print(f"Skip {module_path} module for custom nodes due to the lack of NODE_CLASS_MAPPINGS.")
1915
            return False
1916
1917
1918
    except Exception as e:
        print(traceback.format_exc())
        print(f"Cannot import {module_path} module for custom nodes:", e)
1919
        return False
1920

Hacker 17082006's avatar
Hacker 17082006 committed
1921
def load_custom_nodes():
1922
    base_node_names = set(NODE_CLASS_MAPPINGS.keys())
1923
    node_paths = folder_paths.get_folder_paths("custom_nodes")
1924
    node_import_times = []
1925
    for custom_node_path in node_paths:
Enrico Fasoli's avatar
Enrico Fasoli committed
1926
        possible_modules = os.listdir(os.path.realpath(custom_node_path))
1927
1928
1929
1930
1931
1932
        if "__pycache__" in possible_modules:
            possible_modules.remove("__pycache__")

        for possible_module in possible_modules:
            module_path = os.path.join(custom_node_path, possible_module)
            if os.path.isfile(module_path) and os.path.splitext(module_path)[1] != ".py": continue
1933
            if module_path.endswith(".disabled"): continue
1934
            time_before = time.perf_counter()
1935
            success = load_custom_node(module_path, base_node_names)
1936
            node_import_times.append((time.perf_counter() - time_before, module_path, success))
1937

1938
    if len(node_import_times) > 0:
comfyanonymous's avatar
comfyanonymous committed
1939
        print("\nImport times for custom nodes:")
1940
        for n in sorted(node_import_times):
1941
1942
1943
1944
1945
            if n[2]:
                import_message = ""
            else:
                import_message = " (IMPORT FAILED)"
            print("{:6.1f} seconds{}:".format(n[0], import_message), n[1])
1946
        print()
1947

1948
def init_custom_nodes():
1949
1950
1951
1952
1953
1954
1955
    extras_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras")
    extras_files = [
        "nodes_latent.py",
        "nodes_hypernetwork.py",
        "nodes_upscale_model.py",
        "nodes_post_processing.py",
        "nodes_mask.py",
1956
        "nodes_compositing.py",
1957
1958
1959
1960
1961
1962
        "nodes_rebatch.py",
        "nodes_model_merging.py",
        "nodes_tomesd.py",
        "nodes_clip_sdxl.py",
        "nodes_canny.py",
        "nodes_freelunch.py",
1963
1964
        "nodes_custom_sampler.py",
        "nodes_hypertile.py",
1965
        "nodes_model_advanced.py",
1966
        "nodes_model_downscale.py",
comfyanonymous's avatar
comfyanonymous committed
1967
        "nodes_images.py",
1968
        "nodes_video_model.py",
1969
        "nodes_sag.py",
Hari's avatar
Hari committed
1970
        "nodes_perpneg.py",
1971
        "nodes_stable3d.py",
1972
        "nodes_sdupscale.py",
1973
        "nodes_photomaker.py",
1974
        "nodes_cond.py",
comfyanonymous's avatar
comfyanonymous committed
1975
        "nodes_stable_cascade.py",
1976
1977
1978
1979
1980
    ]

    for node_file in extras_files:
        load_custom_node(os.path.join(extras_dir, node_file))

1981
    load_custom_nodes()