"include/composable_kernel/utility/config_nvidia.hpp.in" did not exist on "121693b3d3b3148010f0756c5ab4741476620aba"
nodes.py 66.2 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
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, )

Jacob Segal's avatar
Jacob Segal committed
187
188
189
190
191
192
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}),
193
                              "set_cond_area": (["default", "mask bounds"],),
Jacob Segal's avatar
Jacob Segal committed
194
195
196
197
198
199
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

    CATEGORY = "conditioning"

200
    def append(self, conditioning, mask, set_cond_area, strength):
Jacob Segal's avatar
Jacob Segal committed
201
        c = []
202
203
204
        set_area_to_bounds = False
        if set_cond_area != "default":
            set_area_to_bounds = True
Jacob Segal's avatar
Jacob Segal committed
205
206
207
208
209
210
        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
211
            n[1]['set_area_to_bounds'] = set_area_to_bounds
212
            n[1]['mask_strength'] = strength
Jacob Segal's avatar
Jacob Segal committed
213
214
215
            c.append(n)
        return (c, )

216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
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, )

235
236
237
238
class ConditioningSetTimestepRange:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
239
240
                             "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})
241
242
243
244
245
246
247
248
249
250
                             }}
    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()
251
252
            d['start_percent'] = 1.0 - start
            d['end_percent'] = 1.0 - end
253
254
255
256
            n = [t[0], d]
            c.append(n)
        return (c, )

comfyanonymous's avatar
comfyanonymous committed
257
258
259
260
261
262
263
class VAEDecode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "decode"

264
265
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
266
    def decode(self, vae, samples):
267
        return (vae.decode(samples["samples"]), )
comfyanonymous's avatar
comfyanonymous committed
268

269
270
271
class VAEDecodeTiled:
    @classmethod
    def INPUT_TYPES(s):
272
        return {"required": {"samples": ("LATENT", ), "vae": ("VAE", ),
comfyanonymous's avatar
comfyanonymous committed
273
                             "tile_size": ("INT", {"default": 512, "min": 320, "max": 4096, "step": 64})
274
                            }}
275
276
277
278
279
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "decode"

    CATEGORY = "_for_testing"

280
    def decode(self, vae, samples, tile_size):
281
        return (vae.decode_tiled(samples["samples"], tile_x=tile_size // 8, tile_y=tile_size // 8, ), )
282

comfyanonymous's avatar
comfyanonymous committed
283
284
285
286
287
288
289
class VAEEncode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "pixels": ("IMAGE", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

290
291
    CATEGORY = "latent"

292
293
294
295
    @staticmethod
    def vae_encode_crop_pixels(pixels):
        x = (pixels.shape[1] // 8) * 8
        y = (pixels.shape[2] // 8) * 8
296
        if pixels.shape[1] != x or pixels.shape[2] != y:
297
298
299
300
            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
301

302
303
304
    def encode(self, vae, pixels):
        pixels = self.vae_encode_crop_pixels(pixels)
        t = vae.encode(pixels[:,:,:,:3])
305
        return ({"samples":t}, )
comfyanonymous's avatar
comfyanonymous committed
306

comfyanonymous's avatar
comfyanonymous committed
307
308
309
class VAEEncodeTiled:
    @classmethod
    def INPUT_TYPES(s):
310
        return {"required": {"pixels": ("IMAGE", ), "vae": ("VAE", ),
311
                             "tile_size": ("INT", {"default": 512, "min": 320, "max": 4096, "step": 64})
312
                            }}
comfyanonymous's avatar
comfyanonymous committed
313
314
315
316
317
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

    CATEGORY = "_for_testing"

318
    def encode(self, vae, pixels, tile_size):
319
        pixels = VAEEncode.vae_encode_crop_pixels(pixels)
320
        t = vae.encode_tiled(pixels[:,:,:,:3], tile_x=tile_size, tile_y=tile_size, )
comfyanonymous's avatar
comfyanonymous committed
321
        return ({"samples":t}, )
322

323
324
325
class VAEEncodeForInpaint:
    @classmethod
    def INPUT_TYPES(s):
326
        return {"required": { "pixels": ("IMAGE", ), "vae": ("VAE", ), "mask": ("MASK", ), "grow_mask_by": ("INT", {"default": 6, "min": 0, "max": 64, "step": 1}),}}
327
328
329
330
331
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

    CATEGORY = "latent/inpaint"

332
    def encode(self, vae, pixels, mask, grow_mask_by=6):
333
334
        x = (pixels.shape[1] // 8) * 8
        y = (pixels.shape[2] // 8) * 8
335
        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(pixels.shape[1], pixels.shape[2]), mode="bilinear")
336

337
        pixels = pixels.clone()
338
        if pixels.shape[1] != x or pixels.shape[2] != y:
339
340
341
342
            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]
343

344
        #grow mask by a few pixels to keep things seamless in latent space
345
346
347
348
349
350
351
352
        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)

353
        m = (1.0 - mask.round()).squeeze(1)
354
355
        for i in range(3):
            pixels[:,:,:,i] -= 0.5
356
            pixels[:,:,:,i] *= m
357
358
359
            pixels[:,:,:,i] += 0.5
        t = vae.encode(pixels)

360
        return ({"samples":t, "noise_mask": (mask_erosion[:,:,:x,:y].round())}, )
comfyanonymous's avatar
comfyanonymous committed
361

Dr.Lt.Data's avatar
Dr.Lt.Data committed
362
363
class SaveLatent:
    def __init__(self):
364
        self.output_dir = folder_paths.get_output_directory()
Dr.Lt.Data's avatar
Dr.Lt.Data committed
365
366
367
368

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT", ),
369
                              "filename_prefix": ("STRING", {"default": "latents/ComfyUI"})},
Dr.Lt.Data's avatar
Dr.Lt.Data committed
370
371
372
373
374
375
376
377
378
379
                "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):
380
        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
381
382
383
384
385
386

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

387
388
389
390
391
392
        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
393
394

        file = f"{filename}_{counter:05}_.latent"
395
396
397
398
399
400
401
402

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

Dr.Lt.Data's avatar
Dr.Lt.Data committed
403
404
        file = os.path.join(full_output_folder, file)

405
406
        output = {}
        output["latent_tensor"] = samples["samples"]
407
        output["latent_format_version_0"] = torch.tensor([])
408

409
        comfy.utils.save_torch_file(output, file, metadata=metadata)
410
        return { "ui": { "latents": results } }
Dr.Lt.Data's avatar
Dr.Lt.Data committed
411
412
413
414
415


class LoadLatent:
    @classmethod
    def INPUT_TYPES(s):
416
417
        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
418
419
420
421
422
423
424
425
        return {"required": {"latent": [sorted(files), ]}, }

    CATEGORY = "_for_testing"

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

    def load(self, latent):
426
427
        latent_path = folder_paths.get_annotated_filepath(latent)
        latent = safetensors.torch.load_file(latent_path, device="cpu")
428
429
430
431
        multiplier = 1.0
        if "latent_format_version_0" not in latent:
            multiplier = 1.0 / 0.18215
        samples = {"samples": latent["latent_tensor"].float() * multiplier}
432
        return (samples, )
Dr.Lt.Data's avatar
Dr.Lt.Data committed
433

434
435
436
437
438
439
440
441
442
443
444
445
446
447
    @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
448

comfyanonymous's avatar
comfyanonymous committed
449
450
451
class CheckpointLoader:
    @classmethod
    def INPUT_TYPES(s):
452
453
        return {"required": { "config_name": (folder_paths.get_filename_list("configs"), ),
                              "ckpt_name": (folder_paths.get_filename_list("checkpoints"), )}}
comfyanonymous's avatar
comfyanonymous committed
454
455
456
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

457
    CATEGORY = "advanced/loaders"
458

comfyanonymous's avatar
comfyanonymous committed
459
    def load_checkpoint(self, config_name, ckpt_name, output_vae=True, output_clip=True):
460
461
        config_path = folder_paths.get_full_path("configs", config_name)
        ckpt_path = folder_paths.get_full_path("checkpoints", ckpt_name)
462
        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
463

464
465
466
class CheckpointLoaderSimple:
    @classmethod
    def INPUT_TYPES(s):
467
        return {"required": { "ckpt_name": (folder_paths.get_filename_list("checkpoints"), ),
468
469
470
471
                             }}
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

472
    CATEGORY = "loaders"
473

474
    def load_checkpoint(self, ckpt_name, output_vae=True, output_clip=True):
475
        ckpt_path = folder_paths.get_full_path("checkpoints", ckpt_name)
476
        out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
477
        return out[:3]
478

sALTaccount's avatar
sALTaccount committed
479
480
481
class DiffusersLoader:
    @classmethod
    def INPUT_TYPES(cls):
482
        paths = []
sALTaccount's avatar
sALTaccount committed
483
        for search_path in folder_paths.get_folder_paths("diffusers"):
484
            if os.path.exists(search_path):
485
486
487
488
                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))

489
        return {"required": {"model_path": (paths,), }}
sALTaccount's avatar
sALTaccount committed
490
491
492
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

493
    CATEGORY = "advanced/loaders/deprecated"
sALTaccount's avatar
sALTaccount committed
494
495

    def load_checkpoint(self, model_path, output_vae=True, output_clip=True):
sALTaccount's avatar
sALTaccount committed
496
497
        for search_path in folder_paths.get_folder_paths("diffusers"):
            if os.path.exists(search_path):
498
499
500
                path = os.path.join(search_path, model_path)
                if os.path.exists(path):
                    model_path = path
sALTaccount's avatar
sALTaccount committed
501
                    break
502

503
        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
504
505


506
507
508
509
510
511
512
513
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"

514
    CATEGORY = "loaders"
515
516
517
518
519
520

    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
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
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,)

537
class LoraLoader:
538
539
540
    def __init__(self):
        self.loaded_lora = None

541
542
543
544
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
                              "clip": ("CLIP", ),
545
                              "lora_name": (folder_paths.get_filename_list("loras"), ),
546
547
                              "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}),
548
549
550
551
552
553
554
                              }}
    RETURN_TYPES = ("MODEL", "CLIP")
    FUNCTION = "load_lora"

    CATEGORY = "loaders"

    def load_lora(self, model, clip, lora_name, strength_model, strength_clip):
555
556
557
        if strength_model == 0 and strength_clip == 0:
            return (model, clip)

558
        lora_path = folder_paths.get_full_path("loras", lora_name)
559
560
561
562
563
        lora = None
        if self.loaded_lora is not None:
            if self.loaded_lora[0] == lora_path:
                lora = self.loaded_lora[1]
            else:
564
565
566
                temp = self.loaded_lora
                self.loaded_lora = None
                del temp
567
568
569
570
571
572

        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)
573
574
        return (model_lora, clip_lora)

comfyanonymous's avatar
comfyanonymous committed
575
576
577
class VAELoader:
    @classmethod
    def INPUT_TYPES(s):
578
        return {"required": { "vae_name": (folder_paths.get_filename_list("vae"), )}}
comfyanonymous's avatar
comfyanonymous committed
579
580
581
    RETURN_TYPES = ("VAE",)
    FUNCTION = "load_vae"

582
583
    CATEGORY = "loaders"

comfyanonymous's avatar
comfyanonymous committed
584
585
    #TODO: scale factor?
    def load_vae(self, vae_name):
586
        vae_path = folder_paths.get_full_path("vae", vae_name)
comfyanonymous's avatar
comfyanonymous committed
587
588
589
        vae = comfy.sd.VAE(ckpt_path=vae_path)
        return (vae,)

comfyanonymous's avatar
comfyanonymous committed
590
591
592
class ControlNetLoader:
    @classmethod
    def INPUT_TYPES(s):
593
        return {"required": { "control_net_name": (folder_paths.get_filename_list("controlnet"), )}}
comfyanonymous's avatar
comfyanonymous committed
594
595
596
597
598
599
600

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

    CATEGORY = "loaders"

    def load_controlnet(self, control_net_name):
601
        controlnet_path = folder_paths.get_full_path("controlnet", control_net_name)
602
        controlnet = comfy.controlnet.load_controlnet(controlnet_path)
comfyanonymous's avatar
comfyanonymous committed
603
604
        return (controlnet,)

605
606
607
608
class DiffControlNetLoader:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
609
                              "control_net_name": (folder_paths.get_filename_list("controlnet"), )}}
610
611
612
613
614
615
616

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

    CATEGORY = "loaders"

    def load_controlnet(self, model, control_net_name):
617
        controlnet_path = folder_paths.get_full_path("controlnet", control_net_name)
618
        controlnet = comfy.controlnet.load_controlnet(controlnet_path, model)
619
620
        return (controlnet,)

comfyanonymous's avatar
comfyanonymous committed
621
622
623
624

class ControlNetApply:
    @classmethod
    def INPUT_TYPES(s):
625
626
627
628
629
        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
630
631
632
633
634
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_controlnet"

    CATEGORY = "conditioning"

635
    def apply_controlnet(self, conditioning, control_net, image, strength):
636
637
638
        if strength == 0:
            return (conditioning, )

comfyanonymous's avatar
comfyanonymous committed
639
640
641
642
        c = []
        control_hint = image.movedim(-1,1)
        for t in conditioning:
            n = [t[0], t[1].copy()]
comfyanonymous's avatar
comfyanonymous committed
643
644
645
646
            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
647
            n[1]['control_apply_to_uncond'] = True
comfyanonymous's avatar
comfyanonymous committed
648
649
650
            c.append(n)
        return (c, )

651
652
653
654
655
656
657
658
659

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}),
660
661
                             "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})
662
663
664
665
666
667
668
669
                             }}

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

    CATEGORY = "conditioning"

670
    def apply_controlnet(self, positive, negative, control_net, image, strength, start_percent, end_percent):
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
        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:
687
                    c_net = control_net.copy().set_cond_hint(control_hint, strength, (1.0 - start_percent, 1.0 - end_percent))
688
689
690
691
692
693
694
695
696
697
698
                    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])


699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
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,)

714
715
716
class CLIPLoader:
    @classmethod
    def INPUT_TYPES(s):
717
        return {"required": { "clip_name": (folder_paths.get_filename_list("clip"), ),
718
719
720
721
                             }}
    RETURN_TYPES = ("CLIP",)
    FUNCTION = "load_clip"

722
    CATEGORY = "advanced/loaders"
723

724
    def load_clip(self, clip_name):
725
        clip_path = folder_paths.get_full_path("clip", clip_name)
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
        clip = comfy.sd.load_clip(ckpt_paths=[clip_path], embedding_directory=folder_paths.get_folder_paths("embeddings"))
        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"))
743
744
        return (clip,)

745
746
747
class CLIPVisionLoader:
    @classmethod
    def INPUT_TYPES(s):
748
        return {"required": { "clip_name": (folder_paths.get_filename_list("clip_vision"), ),
749
750
751
752
753
754
755
                             }}
    RETURN_TYPES = ("CLIP_VISION",)
    FUNCTION = "load_clip"

    CATEGORY = "loaders"

    def load_clip(self, clip_name):
756
        clip_path = folder_paths.get_full_path("clip_vision", clip_name)
757
        clip_vision = comfy.clip_vision.load(clip_path)
758
759
760
761
762
763
764
765
        return (clip_vision,)

class CLIPVisionEncode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "clip_vision": ("CLIP_VISION",),
                              "image": ("IMAGE",)
                             }}
comfyanonymous's avatar
comfyanonymous committed
766
    RETURN_TYPES = ("CLIP_VISION_OUTPUT",)
767
768
    FUNCTION = "encode"

769
    CATEGORY = "conditioning"
770
771
772
773
774
775
776
777

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

class StyleModelLoader:
    @classmethod
    def INPUT_TYPES(s):
778
        return {"required": { "style_model_name": (folder_paths.get_filename_list("style_models"), )}}
779
780
781
782
783
784
785

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

    CATEGORY = "loaders"

    def load_style_model(self, style_model_name):
786
        style_model_path = folder_paths.get_full_path("style_models", style_model_name)
787
788
789
790
791
792
793
        style_model = comfy.sd.load_style_model(style_model_path)
        return (style_model,)


class StyleModelApply:
    @classmethod
    def INPUT_TYPES(s):
794
795
796
        return {"required": {"conditioning": ("CONDITIONING", ),
                             "style_model": ("STYLE_MODEL", ),
                             "clip_vision_output": ("CLIP_VISION_OUTPUT", ),
797
798
799
800
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_stylemodel"

comfyanonymous's avatar
comfyanonymous committed
801
    CATEGORY = "conditioning/style_model"
802

803
    def apply_stylemodel(self, clip_vision_output, style_model, conditioning):
804
        cond = style_model.get_cond(clip_vision_output).flatten(start_dim=0, end_dim=1).unsqueeze(dim=0)
805
        c = []
806
807
        for t in conditioning:
            n = [torch.cat((t[0], cond), dim=1), t[1].copy()]
808
809
810
            c.append(n)
        return (c, )

811
812
813
814
815
816
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}),
817
                             "noise_augmentation": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.01}),
818
819
820
821
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_adm"

822
    CATEGORY = "conditioning"
823

824
    def apply_adm(self, conditioning, clip_vision_output, strength, noise_augmentation):
825
826
827
        if strength == 0:
            return (conditioning, )

828
829
830
        c = []
        for t in conditioning:
            o = t[1].copy()
831
832
833
            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]
834
            else:
835
                o["unclip_conditioning"] = [x]
836
837
838
839
            n = [t[0], o]
            c.append(n)
        return (c, )

840
841
842
843
844
845
846
847
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
848
    CATEGORY = "loaders"
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869

    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
870
    CATEGORY = "conditioning/gligen"
871
872
873
874
875
876
877
878
879
880
881
882
883
884

    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, )
885

comfyanonymous's avatar
comfyanonymous committed
886
887
888
889
890
891
class EmptyLatentImage:
    def __init__(self, device="cpu"):
        self.device = device

    @classmethod
    def INPUT_TYPES(s):
892
893
        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
894
                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096})}}
comfyanonymous's avatar
comfyanonymous committed
895
896
897
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "generate"

898
899
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
900
901
    def generate(self, width, height, batch_size=1):
        latent = torch.zeros([batch_size, 4, height // 8, width // 8])
902
        return ({"samples":latent}, )
comfyanonymous's avatar
comfyanonymous committed
903

comfyanonymous's avatar
comfyanonymous committed
904

905
906
907
908
909
class LatentFromBatch:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "batch_index": ("INT", {"default": 0, "min": 0, "max": 63}),
910
                              "length": ("INT", {"default": 1, "min": 1, "max": 64}),
911
912
                              }}
    RETURN_TYPES = ("LATENT",)
913
    FUNCTION = "frombatch"
914

915
    CATEGORY = "latent/batch"
916

917
    def frombatch(self, samples, batch_index, length):
918
919
920
        s = samples.copy()
        s_in = samples["samples"]
        batch_index = min(s_in.shape[0] - 1, batch_index)
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
        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"]]
961
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
962

comfyanonymous's avatar
comfyanonymous committed
963
class LatentUpscale:
comfyanonymous's avatar
comfyanonymous committed
964
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "bislerp"]
965
    crop_methods = ["disabled", "center"]
comfyanonymous's avatar
comfyanonymous committed
966
967
968
969

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",), "upscale_method": (s.upscale_methods,),
970
971
                              "width": ("INT", {"default": 512, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 512, "min": 0, "max": MAX_RESOLUTION, "step": 8}),
972
                              "crop": (s.crop_methods,)}}
comfyanonymous's avatar
comfyanonymous committed
973
974
975
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "upscale"

976
977
    CATEGORY = "latent"

978
    def upscale(self, samples, upscale_method, width, height, crop):
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
        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
995
996
        return (s,)

comfyanonymous's avatar
comfyanonymous committed
997
class LatentUpscaleBy:
comfyanonymous's avatar
comfyanonymous committed
998
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "bislerp"]
comfyanonymous's avatar
comfyanonymous committed
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015

    @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
1016
1017
1018
1019
1020
1021
1022
1023
1024
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
1025
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
1026
1027

    def rotate(self, samples, rotation):
1028
        s = samples.copy()
comfyanonymous's avatar
comfyanonymous committed
1029
1030
1031
1032
1033
1034
1035
1036
        rotate_by = 0
        if rotation.startswith("90"):
            rotate_by = 1
        elif rotation.startswith("180"):
            rotate_by = 2
        elif rotation.startswith("270"):
            rotate_by = 3

1037
        s["samples"] = torch.rot90(samples["samples"], k=rotate_by, dims=[3, 2])
comfyanonymous's avatar
comfyanonymous committed
1038
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048

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
1049
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
1050
1051

    def flip(self, samples, flip_method):
1052
        s = samples.copy()
comfyanonymous's avatar
comfyanonymous committed
1053
        if flip_method.startswith("x"):
1054
            s["samples"] = torch.flip(samples["samples"], dims=[2])
comfyanonymous's avatar
comfyanonymous committed
1055
        elif flip_method.startswith("y"):
1056
            s["samples"] = torch.flip(samples["samples"], dims=[3])
comfyanonymous's avatar
comfyanonymous committed
1057
1058

        return (s,)
comfyanonymous's avatar
comfyanonymous committed
1059
1060
1061
1062

class LatentComposite:
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
1063
1064
1065
1066
1067
1068
        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
1069
1070
1071
1072
1073
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "composite"

    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
1074
1075
1076
    def composite(self, samples_to, samples_from, x, y, composite_method="normal", feather=0):
        x =  x // 8
        y = y // 8
1077
        feather = feather // 8
comfyanonymous's avatar
comfyanonymous committed
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
        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
1101

1102
1103
1104
1105
class LatentBlend:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {
1106
1107
            "samples1": ("LATENT",),
            "samples2": ("LATENT",),
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
            "blend_factor": ("FLOAT", {
                "default": 0.5,
                "min": 0,
                "max": 1,
                "step": 0.01
            }),
        }}

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

    CATEGORY = "_for_testing"

1121
    def blend(self, samples1, samples2, blend_factor:float, blend_mode: str="normal"):
1122

1123
1124
1125
        samples_out = samples1.copy()
        samples1 = samples1["samples"]
        samples2 = samples2["samples"]
1126

1127
1128
1129
1130
        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)
1131

1132
1133
        samples_blended = self.blend_mode(samples1, samples2, blend_mode)
        samples_blended = samples1 * blend_factor + samples_blended * (1 - blend_factor)
1134
1135
1136
1137
1138
1139
1140
1141
1142
        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
1143
1144
1145
1146
class LatentCrop:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
1147
1148
                              "width": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
1149
1150
                              "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
1151
1152
1153
1154
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "crop"

comfyanonymous's avatar
comfyanonymous committed
1155
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
1156
1157

    def crop(self, samples, width, height, x, y):
1158
1159
        s = samples.copy()
        samples = samples['samples']
comfyanonymous's avatar
comfyanonymous committed
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
        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
1173
        s['samples'] = samples[:,:,y:to_y, x:to_x]
comfyanonymous's avatar
comfyanonymous committed
1174
1175
        return (s,)

1176
1177
1178
1179
1180
1181
1182
1183
1184
class SetLatentNoiseMask:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "mask": ("MASK",),
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "set_mask"

1185
    CATEGORY = "latent/inpaint"
1186
1187
1188

    def set_mask(self, samples, mask):
        s = samples.copy()
1189
        s["noise_mask"] = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1]))
1190
1191
        return (s,)

space-nuko's avatar
space-nuko committed
1192
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):
1193
    latent_image = latent["samples"]
comfyanonymous's avatar
comfyanonymous committed
1194
1195
1196
    if disable_noise:
        noise = torch.zeros(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, device="cpu")
    else:
1197
1198
        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
1199

1200
    noise_mask = None
1201
    if "noise_mask" in latent:
1202
        noise_mask = latent["noise_mask"]
comfyanonymous's avatar
comfyanonymous committed
1203

1204
    callback = latent_preview.prepare_callback(model, steps)
comfyanonymous's avatar
comfyanonymous committed
1205
    disable_pbar = False
1206
1207
    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
1208
                                  force_full_denoise=force_full_denoise, noise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
1209
1210
1211
    out = latent.copy()
    out["samples"] = samples
    return (out, )
comfyanonymous's avatar
comfyanonymous committed
1212

comfyanonymous's avatar
comfyanonymous committed
1213
1214
1215
class KSampler:
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
1216
        return {"required":
comfyanonymous's avatar
comfyanonymous committed
1217
1218
1219
                    {"model": ("MODEL",),
                    "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
                    "steps": ("INT", {"default": 20, "min": 1, "max": 10000}),
1220
                    "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.5, "round": 0.01}),
comfyanonymous's avatar
comfyanonymous committed
1221
1222
1223
1224
1225
1226
                    "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
1227
1228
                     }
                }
comfyanonymous's avatar
comfyanonymous committed
1229
1230
1231
1232

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

1233
1234
    CATEGORY = "sampling"

space-nuko's avatar
space-nuko committed
1235
1236
    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
1237

comfyanonymous's avatar
comfyanonymous committed
1238
1239
1240
1241
1242
1243
1244
1245
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}),
1246
                    "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.5, "round": 0.01}),
comfyanonymous's avatar
comfyanonymous committed
1247
1248
1249
1250
1251
1252
1253
1254
                    "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
1255
1256
                     }
                }
comfyanonymous's avatar
comfyanonymous committed
1257
1258
1259
1260
1261

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

    CATEGORY = "sampling"
comfyanonymous's avatar
comfyanonymous committed
1262

space-nuko's avatar
space-nuko committed
1263
    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
1264
1265
1266
1267
1268
1269
        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
1270
        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
1271
1272
1273

class SaveImage:
    def __init__(self):
1274
        self.output_dir = folder_paths.get_output_directory()
m957ymj75urz's avatar
m957ymj75urz committed
1275
        self.type = "output"
1276
        self.prefix_append = ""
comfyanonymous's avatar
comfyanonymous committed
1277
1278
1279
1280

    @classmethod
    def INPUT_TYPES(s):
        return {"required": 
1281
                    {"images": ("IMAGE", ),
pythongosssss's avatar
tidy  
pythongosssss committed
1282
                     "filename_prefix": ("STRING", {"default": "ComfyUI"})},
pythongosssss's avatar
pythongosssss committed
1283
                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
comfyanonymous's avatar
comfyanonymous committed
1284
1285
1286
1287
1288
1289
1290
                }

    RETURN_TYPES = ()
    FUNCTION = "save_images"

    OUTPUT_NODE = True

1291
1292
    CATEGORY = "image"

pythongosssss's avatar
tidy  
pythongosssss committed
1293
    def save_images(self, images, filename_prefix="ComfyUI", prompt=None, extra_pnginfo=None):
1294
        filename_prefix += self.prefix_append
1295
        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
1296
        results = list()
comfyanonymous's avatar
comfyanonymous committed
1297
1298
        for image in images:
            i = 255. * image.cpu().numpy()
1299
            img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
1300
1301
1302
1303
1304
1305
1306
1307
            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]))
1308

1309
            file = f"{filename}_{counter:05}_.png"
1310
            img.save(os.path.join(full_output_folder, file), pnginfo=metadata, compress_level=4)
m957ymj75urz's avatar
m957ymj75urz committed
1311
1312
1313
1314
            results.append({
                "filename": file,
                "subfolder": subfolder,
                "type": self.type
Gavroche CryptoRUSH's avatar
Gavroche CryptoRUSH committed
1315
            })
1316
            counter += 1
comfyanonymous's avatar
comfyanonymous committed
1317

m957ymj75urz's avatar
m957ymj75urz committed
1318
        return { "ui": { "images": results } }
comfyanonymous's avatar
comfyanonymous committed
1319

pythongosssss's avatar
pythongosssss committed
1320
1321
class PreviewImage(SaveImage):
    def __init__(self):
1322
        self.output_dir = folder_paths.get_temp_directory()
m957ymj75urz's avatar
m957ymj75urz committed
1323
        self.type = "temp"
1324
        self.prefix_append = "_temp_" + ''.join(random.choice("abcdefghijklmnopqrstupvxyz") for x in range(5))
pythongosssss's avatar
pythongosssss committed
1325
1326
1327

    @classmethod
    def INPUT_TYPES(s):
1328
        return {"required":
pythongosssss's avatar
pythongosssss committed
1329
1330
1331
                    {"images": ("IMAGE", ), },
                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
                }
1332

1333
1334
1335
class LoadImage:
    @classmethod
    def INPUT_TYPES(s):
1336
        input_dir = folder_paths.get_input_directory()
comfyanonymous's avatar
comfyanonymous committed
1337
        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
1338
        return {"required":
1339
                    {"image": (sorted(files), {"image_upload": True})},
1340
                }
1341
1342

    CATEGORY = "image"
1343

1344
    RETURN_TYPES = ("IMAGE", "MASK")
1345
1346
    FUNCTION = "load_image"
    def load_image(self, image):
1347
        image_path = folder_paths.get_annotated_filepath(image)
1348
        i = Image.open(image_path)
1349
        i = ImageOps.exif_transpose(i)
1350
        image = i.convert("RGB")
1351
        image = np.array(image).astype(np.float32) / 255.0
1352
        image = torch.from_numpy(image)[None,]
1353
1354
1355
1356
1357
        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")
1358
        return (image, mask.unsqueeze(0))
1359

1360
1361
    @classmethod
    def IS_CHANGED(s, image):
1362
        image_path = folder_paths.get_annotated_filepath(image)
1363
1364
1365
1366
        m = hashlib.sha256()
        with open(image_path, 'rb') as f:
            m.update(f.read())
        return m.digest().hex()
pythongosssss's avatar
pythongosssss committed
1367

1368
1369
1370
1371
1372
1373
1374
    @classmethod
    def VALIDATE_INPUTS(s, image):
        if not folder_paths.exists_annotated_filepath(image):
            return "Invalid image file: {}".format(image)

        return True

1375
class LoadImageMask:
1376
    _color_channels = ["alpha", "red", "green", "blue"]
1377
1378
    @classmethod
    def INPUT_TYPES(s):
1379
        input_dir = folder_paths.get_input_directory()
comfyanonymous's avatar
comfyanonymous committed
1380
        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
1381
        return {"required":
1382
                    {"image": (sorted(files), {"image_upload": True}),
1383
                     "channel": (s._color_channels, ), }
1384
1385
                }

1386
    CATEGORY = "mask"
1387
1388
1389
1390

    RETURN_TYPES = ("MASK",)
    FUNCTION = "load_image"
    def load_image(self, image, channel):
1391
        image_path = folder_paths.get_annotated_filepath(image)
1392
        i = Image.open(image_path)
1393
        i = ImageOps.exif_transpose(i)
1394
1395
        if i.getbands() != ("R", "G", "B", "A"):
            i = i.convert("RGBA")
1396
1397
1398
1399
1400
1401
1402
1403
1404
        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")
1405
        return (mask.unsqueeze(0),)
1406
1407
1408

    @classmethod
    def IS_CHANGED(s, image, channel):
1409
        image_path = folder_paths.get_annotated_filepath(image)
1410
1411
1412
1413
        m = hashlib.sha256()
        with open(image_path, 'rb') as f:
            m.update(f.read())
        return m.digest().hex()
pythongosssss's avatar
pythongosssss committed
1414

1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
    @classmethod
    def VALIDATE_INPUTS(s, image, channel):
        if not folder_paths.exists_annotated_filepath(image):
            return "Invalid image file: {}".format(image)

        if channel not in s._color_channels:
            return "Invalid color channel: {}".format(channel)

        return True

comfyanonymous's avatar
comfyanonymous committed
1425
class ImageScale:
1426
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "lanczos"]
comfyanonymous's avatar
comfyanonymous committed
1427
1428
1429
1430
1431
    crop_methods = ["disabled", "center"]

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "image": ("IMAGE",), "upscale_method": (s.upscale_methods,),
1432
1433
                              "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
1434
1435
1436
1437
                              "crop": (s.crop_methods,)}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "upscale"

1438
    CATEGORY = "image/upscaling"
1439

comfyanonymous's avatar
comfyanonymous committed
1440
    def upscale(self, image, upscale_method, width, height, crop):
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
        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
1453
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
1454

comfyanonymous's avatar
comfyanonymous committed
1455
class ImageScaleBy:
1456
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "lanczos"]
comfyanonymous's avatar
comfyanonymous committed
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474

    @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,)

1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
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,)

1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
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,)
1506

comfyanonymous's avatar
comfyanonymous committed
1507
1508
1509
1510
1511
1512
1513
1514
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
1515
                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
comfyanonymous's avatar
comfyanonymous committed
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
                              "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
1529
1530
1531
1532
1533
1534
1535
class ImagePadForOutpaint:

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "image": ("IMAGE",),
1536
1537
1538
1539
                "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}),
1540
                "feathering": ("INT", {"default": 40, "min": 0, "max": MAX_RESOLUTION, "step": 1}),
Guo Y.K's avatar
Guo Y.K committed
1541
1542
1543
1544
1545
1546
1547
1548
            }
        }

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

    CATEGORY = "image"

1549
    def expand_image(self, image, left, top, right, bottom, feathering):
Guo Y.K's avatar
Guo Y.K committed
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
        d1, d2, d3, d4 = image.size()

        new_image = torch.zeros(
            (d1, d2 + top + bottom, d3 + left + right, d4),
            dtype=torch.float32,
        )
        new_image[:, top:top + d2, left:left + d3, :] = image

        mask = torch.ones(
            (d2 + top + bottom, d3 + left + right),
            dtype=torch.float32,
        )
1562

1563
1564
1565
1566
1567
        t = torch.zeros(
            (d2, d3),
            dtype=torch.float32
        )

1568
        if feathering > 0 and feathering * 2 < d2 and feathering * 2 < d3:
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587

            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
1588

Guo Y.K's avatar
Guo Y.K committed
1589
1590
1591
        return (new_image, mask)


comfyanonymous's avatar
comfyanonymous committed
1592
1593
NODE_CLASS_MAPPINGS = {
    "KSampler": KSampler,
1594
    "CheckpointLoaderSimple": CheckpointLoaderSimple,
comfyanonymous's avatar
comfyanonymous committed
1595
    "CLIPTextEncode": CLIPTextEncode,
comfyanonymous's avatar
comfyanonymous committed
1596
    "CLIPSetLastLayer": CLIPSetLastLayer,
comfyanonymous's avatar
comfyanonymous committed
1597
1598
    "VAEDecode": VAEDecode,
    "VAEEncode": VAEEncode,
1599
    "VAEEncodeForInpaint": VAEEncodeForInpaint,
comfyanonymous's avatar
comfyanonymous committed
1600
1601
1602
    "VAELoader": VAELoader,
    "EmptyLatentImage": EmptyLatentImage,
    "LatentUpscale": LatentUpscale,
comfyanonymous's avatar
comfyanonymous committed
1603
    "LatentUpscaleBy": LatentUpscaleBy,
1604
    "LatentFromBatch": LatentFromBatch,
1605
    "RepeatLatentBatch": RepeatLatentBatch,
comfyanonymous's avatar
comfyanonymous committed
1606
    "SaveImage": SaveImage,
pythongosssss's avatar
pythongosssss committed
1607
    "PreviewImage": PreviewImage,
comfyanonymous's avatar
comfyanonymous committed
1608
    "LoadImage": LoadImage,
1609
    "LoadImageMask": LoadImageMask,
comfyanonymous's avatar
comfyanonymous committed
1610
    "ImageScale": ImageScale,
comfyanonymous's avatar
comfyanonymous committed
1611
    "ImageScaleBy": ImageScaleBy,
1612
    "ImageInvert": ImageInvert,
1613
    "ImageBatch": ImageBatch,
Guo Y.K's avatar
Guo Y.K committed
1614
    "ImagePadForOutpaint": ImagePadForOutpaint,
comfyanonymous's avatar
comfyanonymous committed
1615
    "EmptyImage": EmptyImage,
comfyanonymous's avatar
comfyanonymous committed
1616
    "ConditioningAverage": ConditioningAverage ,
comfyanonymous's avatar
comfyanonymous committed
1617
    "ConditioningCombine": ConditioningCombine,
1618
    "ConditioningConcat": ConditioningConcat,
comfyanonymous's avatar
comfyanonymous committed
1619
    "ConditioningSetArea": ConditioningSetArea,
1620
    "ConditioningSetAreaPercentage": ConditioningSetAreaPercentage,
Jacob Segal's avatar
Jacob Segal committed
1621
    "ConditioningSetMask": ConditioningSetMask,
comfyanonymous's avatar
comfyanonymous committed
1622
    "KSamplerAdvanced": KSamplerAdvanced,
1623
    "SetLatentNoiseMask": SetLatentNoiseMask,
comfyanonymous's avatar
comfyanonymous committed
1624
    "LatentComposite": LatentComposite,
1625
    "LatentBlend": LatentBlend,
comfyanonymous's avatar
comfyanonymous committed
1626
    "LatentRotate": LatentRotate,
comfyanonymous's avatar
comfyanonymous committed
1627
    "LatentFlip": LatentFlip,
comfyanonymous's avatar
comfyanonymous committed
1628
    "LatentCrop": LatentCrop,
1629
    "LoraLoader": LoraLoader,
1630
    "CLIPLoader": CLIPLoader,
1631
    "UNETLoader": UNETLoader,
1632
    "DualCLIPLoader": DualCLIPLoader,
1633
    "CLIPVisionEncode": CLIPVisionEncode,
1634
    "StyleModelApply": StyleModelApply,
1635
    "unCLIPConditioning": unCLIPConditioning,
comfyanonymous's avatar
comfyanonymous committed
1636
    "ControlNetApply": ControlNetApply,
1637
    "ControlNetApplyAdvanced": ControlNetApplyAdvanced,
comfyanonymous's avatar
comfyanonymous committed
1638
    "ControlNetLoader": ControlNetLoader,
1639
    "DiffControlNetLoader": DiffControlNetLoader,
comfyanonymous's avatar
comfyanonymous committed
1640
1641
    "StyleModelLoader": StyleModelLoader,
    "CLIPVisionLoader": CLIPVisionLoader,
1642
    "VAEDecodeTiled": VAEDecodeTiled,
comfyanonymous's avatar
comfyanonymous committed
1643
    "VAEEncodeTiled": VAEEncodeTiled,
1644
    "unCLIPCheckpointLoader": unCLIPCheckpointLoader,
1645
1646
1647
    "GLIGENLoader": GLIGENLoader,
    "GLIGENTextBoxApply": GLIGENTextBoxApply,

1648
    "CheckpointLoader": CheckpointLoader,
sALTaccount's avatar
sALTaccount committed
1649
    "DiffusersLoader": DiffusersLoader,
Dr.Lt.Data's avatar
Dr.Lt.Data committed
1650
1651

    "LoadLatent": LoadLatent,
1652
    "SaveLatent": SaveLatent,
1653
1654

    "ConditioningZeroOut": ConditioningZeroOut,
1655
    "ConditioningSetTimestepRange": ConditioningSetTimestepRange,
comfyanonymous's avatar
comfyanonymous committed
1656
1657
}

City's avatar
City committed
1658
1659
1660
1661
1662
NODE_DISPLAY_NAME_MAPPINGS = {
    # Sampling
    "KSampler": "KSampler",
    "KSamplerAdvanced": "KSampler (Advanced)",
    # Loaders
comfyanonymous's avatar
Rename.  
comfyanonymous committed
1663
1664
    "CheckpointLoader": "Load Checkpoint (With Config)",
    "CheckpointLoaderSimple": "Load Checkpoint",
City's avatar
City committed
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
    "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
1679
    "ConditioningAverage ": "Conditioning (Average)",
1680
    "ConditioningConcat": "Conditioning (Concat)",
City's avatar
City committed
1681
    "ConditioningSetArea": "Conditioning (Set Area)",
1682
    "ConditioningSetAreaPercentage": "Conditioning (Set Area with Percentage)",
Jacob Segal's avatar
Jacob Segal committed
1683
    "ConditioningSetMask": "Conditioning (Set Mask)",
City's avatar
City committed
1684
    "ControlNetApply": "Apply ControlNet",
1685
    "ControlNetApplyAdvanced": "Apply ControlNet (Advanced)",
City's avatar
City committed
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
    # 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
1696
    "LatentUpscaleBy": "Upscale Latent By",
City's avatar
City committed
1697
    "LatentComposite": "Latent Composite",
1698
    "LatentBlend": "Latent Blend",
1699
1700
    "LatentFromBatch" : "Latent From Batch",
    "RepeatLatentBatch": "Repeat Latent Batch",
City's avatar
City committed
1701
1702
1703
1704
1705
1706
    # Image
    "SaveImage": "Save Image",
    "PreviewImage": "Preview Image",
    "LoadImage": "Load Image",
    "LoadImageMask": "Load Image (as Mask)",
    "ImageScale": "Upscale Image",
comfyanonymous's avatar
comfyanonymous committed
1707
    "ImageScaleBy": "Upscale Image By",
City's avatar
City committed
1708
1709
1710
    "ImageUpscaleWithModel": "Upscale Image (using Model)",
    "ImageInvert": "Invert Image",
    "ImagePadForOutpaint": "Pad Image for Outpainting",
1711
    "ImageBatch": "Batch Images",
City's avatar
City committed
1712
1713
1714
1715
1716
    # _for_testing
    "VAEDecodeTiled": "VAE Decode (Tiled)",
    "VAEEncodeTiled": "VAE Encode (Tiled)",
}

1717
1718
EXTENSION_WEB_DIRS = {}

1719
def load_custom_node(module_path, ignore=set()):
1720
1721
1722
1723
1724
1725
1726
    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)
1727
            module_dir = os.path.split(module_path)[0]
1728
1729
        else:
            module_spec = importlib.util.spec_from_file_location(module_name, os.path.join(module_path, "__init__.py"))
1730
1731
            module_dir = module_path

1732
1733
1734
        module = importlib.util.module_from_spec(module_spec)
        sys.modules[module_name] = module
        module_spec.loader.exec_module(module)
1735
1736
1737
1738
1739
1740

        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

1741
        if hasattr(module, "NODE_CLASS_MAPPINGS") and getattr(module, "NODE_CLASS_MAPPINGS") is not None:
1742
1743
1744
            for name in module.NODE_CLASS_MAPPINGS:
                if name not in ignore:
                    NODE_CLASS_MAPPINGS[name] = module.NODE_CLASS_MAPPINGS[name]
1745
1746
            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)
1747
            return True
1748
1749
        else:
            print(f"Skip {module_path} module for custom nodes due to the lack of NODE_CLASS_MAPPINGS.")
1750
            return False
1751
1752
1753
    except Exception as e:
        print(traceback.format_exc())
        print(f"Cannot import {module_path} module for custom nodes:", e)
1754
        return False
1755

Hacker 17082006's avatar
Hacker 17082006 committed
1756
def load_custom_nodes():
1757
    base_node_names = set(NODE_CLASS_MAPPINGS.keys())
1758
    node_paths = folder_paths.get_folder_paths("custom_nodes")
1759
    node_import_times = []
1760
1761
1762
1763
1764
1765
1766
1767
    for custom_node_path in node_paths:
        possible_modules = os.listdir(custom_node_path)
        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
1768
            if module_path.endswith(".disabled"): continue
1769
            time_before = time.perf_counter()
1770
            success = load_custom_node(module_path, base_node_names)
1771
            node_import_times.append((time.perf_counter() - time_before, module_path, success))
1772

1773
    if len(node_import_times) > 0:
comfyanonymous's avatar
comfyanonymous committed
1774
        print("\nImport times for custom nodes:")
1775
        for n in sorted(node_import_times):
1776
1777
1778
1779
1780
            if n[2]:
                import_message = ""
            else:
                import_message = " (IMPORT FAILED)"
            print("{:6.1f} seconds{}:".format(n[0], import_message), n[1])
1781
        print()
1782

1783
def init_custom_nodes():
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
    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",
        "nodes_rebatch.py",
        "nodes_model_merging.py",
        "nodes_tomesd.py",
        "nodes_clip_sdxl.py",
        "nodes_canny.py",
        "nodes_freelunch.py",
        "nodes_custom_sampler.py"
    ]

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

1803
    load_custom_nodes()