nodes.py 53.7 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
comfyanonymous's avatar
comfyanonymous committed
10

11
from PIL import Image, ImageOps
comfyanonymous's avatar
comfyanonymous committed
12
13
from PIL.PngImagePlugin import PngInfo
import numpy as np
14
import safetensors.torch
comfyanonymous's avatar
comfyanonymous committed
15

comfyanonymous's avatar
comfyanonymous committed
16
sys.path.insert(0, os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy"))
comfyanonymous's avatar
comfyanonymous committed
17
18


19
import comfy.diffusers_load
comfyanonymous's avatar
comfyanonymous committed
20
import comfy.samplers
21
import comfy.sample
comfyanonymous's avatar
comfyanonymous committed
22
import comfy.sd
comfyanonymous's avatar
comfyanonymous committed
23
24
import comfy.utils

25
import comfy.clip_vision
26

27
import comfy.model_management
28
import importlib
comfyanonymous's avatar
comfyanonymous committed
29

30
import folder_paths
31
import latent_preview
space-nuko's avatar
space-nuko committed
32

33
def before_node_execution():
34
    comfy.model_management.throw_exception_if_processing_interrupted()
35

36
def interrupt_processing(value=True):
37
    comfy.model_management.interrupt_current_processing(value)
38

39
40
MAX_RESOLUTION=8192

comfyanonymous's avatar
comfyanonymous committed
41
42
43
class CLIPTextEncode:
    @classmethod
    def INPUT_TYPES(s):
44
        return {"required": {"text": ("STRING", {"multiline": True}), "clip": ("CLIP", )}}
comfyanonymous's avatar
comfyanonymous committed
45
46
47
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "encode"

48
49
    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
50
    def encode(self, clip, text):
51
52
53
        tokens = clip.tokenize(text)
        cond, pooled = clip.encode_from_tokens(tokens, return_pooled=True)
        return ([[cond, {"pooled_output": pooled}]], )
comfyanonymous's avatar
comfyanonymous committed
54
55
56
57
58
59
60
61

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

62
63
    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
64
65
66
    def combine(self, conditioning_1, conditioning_2):
        return (conditioning_1 + conditioning_2, )

FizzleDorf's avatar
FizzleDorf committed
67
68
69
class ConditioningAverage :
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
70
71
        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
72
73
74
75
76
77
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "addWeighted"

    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
78
    def addWeighted(self, conditioning_to, conditioning_from, conditioning_to_strength):
FizzleDorf's avatar
FizzleDorf committed
79
        out = []
comfyanonymous's avatar
comfyanonymous committed
80
81
82
83
84
85
86
87
88
89
90
91
92
93

        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]

        for i in range(len(conditioning_to)):
            t1 = conditioning_to[i][0]
            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))
            n = [tw, conditioning_to[i][1].copy()]
FizzleDorf's avatar
FizzleDorf committed
94
95
96
            out.append(n)
        return (out, )

comfyanonymous's avatar
comfyanonymous committed
97
98
99
100
class ConditioningSetArea:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
101
102
103
104
                              "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
105
106
107
108
109
                              "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

110
111
    CATEGORY = "conditioning"

112
    def append(self, conditioning, width, height, x, y, strength):
comfyanonymous's avatar
comfyanonymous committed
113
114
115
116
117
        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
118
            n[1]['set_area_to_bounds'] = False
comfyanonymous's avatar
comfyanonymous committed
119
            c.append(n)
comfyanonymous's avatar
comfyanonymous committed
120
        return (c, )
comfyanonymous's avatar
comfyanonymous committed
121

Jacob Segal's avatar
Jacob Segal committed
122
123
124
125
126
127
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}),
128
                              "set_cond_area": (["default", "mask bounds"],),
Jacob Segal's avatar
Jacob Segal committed
129
130
131
132
133
134
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

    CATEGORY = "conditioning"

135
    def append(self, conditioning, mask, set_cond_area, strength):
Jacob Segal's avatar
Jacob Segal committed
136
        c = []
137
138
139
        set_area_to_bounds = False
        if set_cond_area != "default":
            set_area_to_bounds = True
Jacob Segal's avatar
Jacob Segal committed
140
141
142
143
144
145
        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
146
            n[1]['set_area_to_bounds'] = set_area_to_bounds
147
            n[1]['mask_strength'] = strength
Jacob Segal's avatar
Jacob Segal committed
148
149
150
            c.append(n)
        return (c, )

comfyanonymous's avatar
comfyanonymous committed
151
152
153
154
155
156
157
class VAEDecode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "decode"

158
159
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
160
    def decode(self, vae, samples):
161
        return (vae.decode(samples["samples"]), )
comfyanonymous's avatar
comfyanonymous committed
162

163
164
165
166
167
168
169
170
171
172
173
174
class VAEDecodeTiled:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "decode"

    CATEGORY = "_for_testing"

    def decode(self, vae, samples):
        return (vae.decode_tiled(samples["samples"]), )

comfyanonymous's avatar
comfyanonymous committed
175
176
177
178
179
180
181
class VAEEncode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "pixels": ("IMAGE", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

182
183
    CATEGORY = "latent"

184
185
186
187
    @staticmethod
    def vae_encode_crop_pixels(pixels):
        x = (pixels.shape[1] // 8) * 8
        y = (pixels.shape[2] // 8) * 8
188
        if pixels.shape[1] != x or pixels.shape[2] != y:
189
190
191
192
            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
193

194
195
196
    def encode(self, vae, pixels):
        pixels = self.vae_encode_crop_pixels(pixels)
        t = vae.encode(pixels[:,:,:,:3])
197
        return ({"samples":t}, )
comfyanonymous's avatar
comfyanonymous committed
198

comfyanonymous's avatar
comfyanonymous committed
199
200
201
202
203
204
205
206
207
208
class VAEEncodeTiled:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "pixels": ("IMAGE", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

    CATEGORY = "_for_testing"

    def encode(self, vae, pixels):
209
        pixels = VAEEncode.vae_encode_crop_pixels(pixels)
comfyanonymous's avatar
comfyanonymous committed
210
211
        t = vae.encode_tiled(pixels[:,:,:,:3])
        return ({"samples":t}, )
212

213
214
215
class VAEEncodeForInpaint:
    @classmethod
    def INPUT_TYPES(s):
216
        return {"required": { "pixels": ("IMAGE", ), "vae": ("VAE", ), "mask": ("MASK", ), "grow_mask_by": ("INT", {"default": 6, "min": 0, "max": 64, "step": 1}),}}
217
218
219
220
221
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

    CATEGORY = "latent/inpaint"

222
    def encode(self, vae, pixels, mask, grow_mask_by=6):
223
224
        x = (pixels.shape[1] // 8) * 8
        y = (pixels.shape[2] // 8) * 8
225
        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(pixels.shape[1], pixels.shape[2]), mode="bilinear")
226

227
        pixels = pixels.clone()
228
        if pixels.shape[1] != x or pixels.shape[2] != y:
229
230
231
232
            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]
233

234
        #grow mask by a few pixels to keep things seamless in latent space
235
236
237
238
239
240
241
242
        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)

243
        m = (1.0 - mask.round()).squeeze(1)
244
245
        for i in range(3):
            pixels[:,:,:,i] -= 0.5
246
            pixels[:,:,:,i] *= m
247
248
249
            pixels[:,:,:,i] += 0.5
        t = vae.encode(pixels)

250
        return ({"samples":t, "noise_mask": (mask_erosion[:,:,:x,:y].round())}, )
comfyanonymous's avatar
comfyanonymous committed
251

Dr.Lt.Data's avatar
Dr.Lt.Data committed
252
253
class SaveLatent:
    def __init__(self):
254
        self.output_dir = folder_paths.get_output_directory()
Dr.Lt.Data's avatar
Dr.Lt.Data committed
255
256
257
258

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT", ),
259
                              "filename_prefix": ("STRING", {"default": "latents/ComfyUI"})},
Dr.Lt.Data's avatar
Dr.Lt.Data committed
260
261
262
263
264
265
266
267
268
269
                "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):
270
        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
271
272
273
274
275
276

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

277
        metadata = {"prompt": prompt_info}
Dr.Lt.Data's avatar
Dr.Lt.Data committed
278
279
280
281
282
283
284
        if extra_pnginfo is not None:
            for x in extra_pnginfo:
                metadata[x] = json.dumps(extra_pnginfo[x])

        file = f"{filename}_{counter:05}_.latent"
        file = os.path.join(full_output_folder, file)

285
286
        output = {}
        output["latent_tensor"] = samples["samples"]
287
        output["latent_format_version_0"] = torch.tensor([])
288
289

        safetensors.torch.save_file(output, file, metadata=metadata)
Dr.Lt.Data's avatar
Dr.Lt.Data committed
290
291
292
293
294
295
296

        return {}


class LoadLatent:
    @classmethod
    def INPUT_TYPES(s):
297
298
        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
299
300
301
302
303
304
305
306
        return {"required": {"latent": [sorted(files), ]}, }

    CATEGORY = "_for_testing"

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

    def load(self, latent):
307
308
        latent_path = folder_paths.get_annotated_filepath(latent)
        latent = safetensors.torch.load_file(latent_path, device="cpu")
309
310
311
312
        multiplier = 1.0
        if "latent_format_version_0" not in latent:
            multiplier = 1.0 / 0.18215
        samples = {"samples": latent["latent_tensor"].float() * multiplier}
313
        return (samples, )
Dr.Lt.Data's avatar
Dr.Lt.Data committed
314

315
316
317
318
319
320
321
322
323
324
325
326
327
328
    @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
329

comfyanonymous's avatar
comfyanonymous committed
330
331
332
class CheckpointLoader:
    @classmethod
    def INPUT_TYPES(s):
333
334
        return {"required": { "config_name": (folder_paths.get_filename_list("configs"), ),
                              "ckpt_name": (folder_paths.get_filename_list("checkpoints"), )}}
comfyanonymous's avatar
comfyanonymous committed
335
336
337
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

338
    CATEGORY = "advanced/loaders"
339

comfyanonymous's avatar
comfyanonymous committed
340
    def load_checkpoint(self, config_name, ckpt_name, output_vae=True, output_clip=True):
341
342
        config_path = folder_paths.get_full_path("configs", config_name)
        ckpt_path = folder_paths.get_full_path("checkpoints", ckpt_name)
343
        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
344

345
346
347
class CheckpointLoaderSimple:
    @classmethod
    def INPUT_TYPES(s):
348
        return {"required": { "ckpt_name": (folder_paths.get_filename_list("checkpoints"), ),
349
350
351
352
                             }}
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

353
    CATEGORY = "loaders"
354

355
    def load_checkpoint(self, ckpt_name, output_vae=True, output_clip=True):
356
        ckpt_path = folder_paths.get_full_path("checkpoints", ckpt_name)
357
        out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
358
359
        return out

sALTaccount's avatar
sALTaccount committed
360
361
362
class DiffusersLoader:
    @classmethod
    def INPUT_TYPES(cls):
363
        paths = []
sALTaccount's avatar
sALTaccount committed
364
        for search_path in folder_paths.get_folder_paths("diffusers"):
365
            if os.path.exists(search_path):
366
367
368
369
                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))

370
        return {"required": {"model_path": (paths,), }}
sALTaccount's avatar
sALTaccount committed
371
372
373
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

374
    CATEGORY = "advanced/loaders"
sALTaccount's avatar
sALTaccount committed
375
376

    def load_checkpoint(self, model_path, output_vae=True, output_clip=True):
sALTaccount's avatar
sALTaccount committed
377
378
        for search_path in folder_paths.get_folder_paths("diffusers"):
            if os.path.exists(search_path):
379
380
381
                path = os.path.join(search_path, model_path)
                if os.path.exists(path):
                    model_path = path
sALTaccount's avatar
sALTaccount committed
382
                    break
383

384
        return comfy.diffusers_load.load_diffusers(model_path, fp16=comfy.model_management.should_use_fp16(), output_vae=output_vae, output_clip=output_clip, embedding_directory=folder_paths.get_folder_paths("embeddings"))
sALTaccount's avatar
sALTaccount committed
385
386


387
388
389
390
391
392
393
394
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"

395
    CATEGORY = "loaders"
396
397
398
399
400
401

    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
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
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,)

418
419
420
421
422
class LoraLoader:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
                              "clip": ("CLIP", ),
423
                              "lora_name": (folder_paths.get_filename_list("loras"), ),
424
425
                              "strength_model": ("FLOAT", {"default": 1.0, "min": -10.0, "max": 10.0, "step": 0.01}),
                              "strength_clip": ("FLOAT", {"default": 1.0, "min": -10.0, "max": 10.0, "step": 0.01}),
426
427
428
429
430
431
432
                              }}
    RETURN_TYPES = ("MODEL", "CLIP")
    FUNCTION = "load_lora"

    CATEGORY = "loaders"

    def load_lora(self, model, clip, lora_name, strength_model, strength_clip):
433
434
435
        if strength_model == 0 and strength_clip == 0:
            return (model, clip)

436
        lora_path = folder_paths.get_full_path("loras", lora_name)
437
438
439
        model_lora, clip_lora = comfy.sd.load_lora_for_models(model, clip, lora_path, strength_model, strength_clip)
        return (model_lora, clip_lora)

comfyanonymous's avatar
comfyanonymous committed
440
441
442
class VAELoader:
    @classmethod
    def INPUT_TYPES(s):
443
        return {"required": { "vae_name": (folder_paths.get_filename_list("vae"), )}}
comfyanonymous's avatar
comfyanonymous committed
444
445
446
    RETURN_TYPES = ("VAE",)
    FUNCTION = "load_vae"

447
448
    CATEGORY = "loaders"

comfyanonymous's avatar
comfyanonymous committed
449
450
    #TODO: scale factor?
    def load_vae(self, vae_name):
451
        vae_path = folder_paths.get_full_path("vae", vae_name)
comfyanonymous's avatar
comfyanonymous committed
452
453
454
        vae = comfy.sd.VAE(ckpt_path=vae_path)
        return (vae,)

comfyanonymous's avatar
comfyanonymous committed
455
456
457
class ControlNetLoader:
    @classmethod
    def INPUT_TYPES(s):
458
        return {"required": { "control_net_name": (folder_paths.get_filename_list("controlnet"), )}}
comfyanonymous's avatar
comfyanonymous committed
459
460
461
462
463
464
465

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

    CATEGORY = "loaders"

    def load_controlnet(self, control_net_name):
466
        controlnet_path = folder_paths.get_full_path("controlnet", control_net_name)
comfyanonymous's avatar
comfyanonymous committed
467
468
469
        controlnet = comfy.sd.load_controlnet(controlnet_path)
        return (controlnet,)

470
471
472
473
class DiffControlNetLoader:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
474
                              "control_net_name": (folder_paths.get_filename_list("controlnet"), )}}
475
476
477
478
479
480
481

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

    CATEGORY = "loaders"

    def load_controlnet(self, model, control_net_name):
482
        controlnet_path = folder_paths.get_full_path("controlnet", control_net_name)
483
484
485
        controlnet = comfy.sd.load_controlnet(controlnet_path, model)
        return (controlnet,)

comfyanonymous's avatar
comfyanonymous committed
486
487
488
489

class ControlNetApply:
    @classmethod
    def INPUT_TYPES(s):
490
491
492
493
494
        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
495
496
497
498
499
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_controlnet"

    CATEGORY = "conditioning"

500
    def apply_controlnet(self, conditioning, control_net, image, strength):
501
502
503
        if strength == 0:
            return (conditioning, )

comfyanonymous's avatar
comfyanonymous committed
504
505
506
507
        c = []
        control_hint = image.movedim(-1,1)
        for t in conditioning:
            n = [t[0], t[1].copy()]
comfyanonymous's avatar
comfyanonymous committed
508
509
510
511
            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
comfyanonymous's avatar
comfyanonymous committed
512
513
514
            c.append(n)
        return (c, )

515
516
517
class CLIPLoader:
    @classmethod
    def INPUT_TYPES(s):
518
        return {"required": { "clip_name": (folder_paths.get_filename_list("clip"), ),
519
520
521
522
523
524
                             }}
    RETURN_TYPES = ("CLIP",)
    FUNCTION = "load_clip"

    CATEGORY = "loaders"

525
    def load_clip(self, clip_name):
526
        clip_path = folder_paths.get_full_path("clip", clip_name)
comfyanonymous's avatar
comfyanonymous committed
527
        clip = comfy.sd.load_clip(ckpt_path=clip_path, embedding_directory=folder_paths.get_folder_paths("embeddings"))
528
529
        return (clip,)

530
531
532
class CLIPVisionLoader:
    @classmethod
    def INPUT_TYPES(s):
533
        return {"required": { "clip_name": (folder_paths.get_filename_list("clip_vision"), ),
534
535
536
537
538
539
540
                             }}
    RETURN_TYPES = ("CLIP_VISION",)
    FUNCTION = "load_clip"

    CATEGORY = "loaders"

    def load_clip(self, clip_name):
541
        clip_path = folder_paths.get_full_path("clip_vision", clip_name)
542
        clip_vision = comfy.clip_vision.load(clip_path)
543
544
545
546
547
548
549
550
        return (clip_vision,)

class CLIPVisionEncode:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "clip_vision": ("CLIP_VISION",),
                              "image": ("IMAGE",)
                             }}
comfyanonymous's avatar
comfyanonymous committed
551
    RETURN_TYPES = ("CLIP_VISION_OUTPUT",)
552
553
    FUNCTION = "encode"

554
    CATEGORY = "conditioning"
555
556
557
558
559
560
561
562

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

class StyleModelLoader:
    @classmethod
    def INPUT_TYPES(s):
563
        return {"required": { "style_model_name": (folder_paths.get_filename_list("style_models"), )}}
564
565
566
567
568
569
570

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

    CATEGORY = "loaders"

    def load_style_model(self, style_model_name):
571
        style_model_path = folder_paths.get_full_path("style_models", style_model_name)
572
573
574
575
576
577
578
        style_model = comfy.sd.load_style_model(style_model_path)
        return (style_model,)


class StyleModelApply:
    @classmethod
    def INPUT_TYPES(s):
579
580
581
        return {"required": {"conditioning": ("CONDITIONING", ),
                             "style_model": ("STYLE_MODEL", ),
                             "clip_vision_output": ("CLIP_VISION_OUTPUT", ),
582
583
584
585
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_stylemodel"

comfyanonymous's avatar
comfyanonymous committed
586
    CATEGORY = "conditioning/style_model"
587

588
589
    def apply_stylemodel(self, clip_vision_output, style_model, conditioning):
        cond = style_model.get_cond(clip_vision_output)
590
        c = []
591
592
        for t in conditioning:
            n = [torch.cat((t[0], cond), dim=1), t[1].copy()]
593
594
595
            c.append(n)
        return (c, )

596
597
598
599
600
601
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}),
602
                             "noise_augmentation": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.01}),
603
604
605
606
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "apply_adm"

607
    CATEGORY = "conditioning"
608

609
    def apply_adm(self, conditioning, clip_vision_output, strength, noise_augmentation):
610
611
612
        if strength == 0:
            return (conditioning, )

613
614
615
        c = []
        for t in conditioning:
            o = t[1].copy()
616
617
618
            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]
619
            else:
620
                o["unclip_conditioning"] = [x]
621
622
623
624
            n = [t[0], o]
            c.append(n)
        return (c, )

625
626
627
628
629
630
631
632
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
633
    CATEGORY = "loaders"
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654

    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
655
    CATEGORY = "conditioning/gligen"
656
657
658
659
660
661
662
663
664
665
666
667
668
669

    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, )
670

comfyanonymous's avatar
comfyanonymous committed
671
672
673
674
675
676
class EmptyLatentImage:
    def __init__(self, device="cpu"):
        self.device = device

    @classmethod
    def INPUT_TYPES(s):
677
678
        return {"required": { "width": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
comfyanonymous's avatar
comfyanonymous committed
679
680
681
682
                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 64})}}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "generate"

683
684
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
685
686
    def generate(self, width, height, batch_size=1):
        latent = torch.zeros([batch_size, 4, height // 8, width // 8])
687
        return ({"samples":latent}, )
comfyanonymous's avatar
comfyanonymous committed
688

comfyanonymous's avatar
comfyanonymous committed
689

690
691
692
693
694
class LatentFromBatch:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "batch_index": ("INT", {"default": 0, "min": 0, "max": 63}),
695
                              "length": ("INT", {"default": 1, "min": 1, "max": 64}),
696
697
                              }}
    RETURN_TYPES = ("LATENT",)
698
    FUNCTION = "frombatch"
699

700
    CATEGORY = "latent/batch"
701

702
    def frombatch(self, samples, batch_index, length):
703
704
705
        s = samples.copy()
        s_in = samples["samples"]
        batch_index = min(s_in.shape[0] - 1, batch_index)
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
        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"]]
746
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
747

comfyanonymous's avatar
comfyanonymous committed
748
class LatentUpscale:
comfyanonymous's avatar
comfyanonymous committed
749
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "bislerp"]
750
    crop_methods = ["disabled", "center"]
comfyanonymous's avatar
comfyanonymous committed
751
752
753
754

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",), "upscale_method": (s.upscale_methods,),
755
756
                              "width": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
757
                              "crop": (s.crop_methods,)}}
comfyanonymous's avatar
comfyanonymous committed
758
759
760
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "upscale"

761
762
    CATEGORY = "latent"

763
    def upscale(self, samples, upscale_method, width, height, crop):
764
        s = samples.copy()
comfyanonymous's avatar
comfyanonymous committed
765
        s["samples"] = comfy.utils.common_upscale(samples["samples"], width // 8, height // 8, upscale_method, crop)
comfyanonymous's avatar
comfyanonymous committed
766
767
        return (s,)

comfyanonymous's avatar
comfyanonymous committed
768
class LatentUpscaleBy:
comfyanonymous's avatar
comfyanonymous committed
769
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "bislerp"]
comfyanonymous's avatar
comfyanonymous committed
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786

    @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
787
788
789
790
791
792
793
794
795
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
796
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
797
798

    def rotate(self, samples, rotation):
799
        s = samples.copy()
comfyanonymous's avatar
comfyanonymous committed
800
801
802
803
804
805
806
807
        rotate_by = 0
        if rotation.startswith("90"):
            rotate_by = 1
        elif rotation.startswith("180"):
            rotate_by = 2
        elif rotation.startswith("270"):
            rotate_by = 3

808
        s["samples"] = torch.rot90(samples["samples"], k=rotate_by, dims=[3, 2])
comfyanonymous's avatar
comfyanonymous committed
809
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
810
811
812
813
814
815
816
817
818
819

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
820
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
821
822

    def flip(self, samples, flip_method):
823
        s = samples.copy()
comfyanonymous's avatar
comfyanonymous committed
824
        if flip_method.startswith("x"):
825
            s["samples"] = torch.flip(samples["samples"], dims=[2])
comfyanonymous's avatar
comfyanonymous committed
826
        elif flip_method.startswith("y"):
827
            s["samples"] = torch.flip(samples["samples"], dims=[3])
comfyanonymous's avatar
comfyanonymous committed
828
829

        return (s,)
comfyanonymous's avatar
comfyanonymous committed
830
831
832
833

class LatentComposite:
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
834
835
836
837
838
839
        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
840
841
842
843
844
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "composite"

    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
845
846
847
    def composite(self, samples_to, samples_from, x, y, composite_method="normal", feather=0):
        x =  x // 8
        y = y // 8
848
        feather = feather // 8
comfyanonymous's avatar
comfyanonymous committed
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
        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
872

comfyanonymous's avatar
comfyanonymous committed
873
874
875
876
class LatentCrop:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
877
878
                              "width": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
                              "height": ("INT", {"default": 512, "min": 64, "max": MAX_RESOLUTION, "step": 8}),
879
880
                              "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
881
882
883
884
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "crop"

comfyanonymous's avatar
comfyanonymous committed
885
    CATEGORY = "latent/transform"
comfyanonymous's avatar
comfyanonymous committed
886
887

    def crop(self, samples, width, height, x, y):
888
889
        s = samples.copy()
        samples = samples['samples']
comfyanonymous's avatar
comfyanonymous committed
890
891
892
893
894
895
896
897
898
899
900
901
902
        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
903
        s['samples'] = samples[:,:,y:to_y, x:to_x]
comfyanonymous's avatar
comfyanonymous committed
904
905
        return (s,)

906
907
908
909
910
911
912
913
914
class SetLatentNoiseMask:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "mask": ("MASK",),
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "set_mask"

915
    CATEGORY = "latent/inpaint"
916
917
918

    def set_mask(self, samples, mask):
        s = samples.copy()
919
        s["noise_mask"] = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1]))
920
921
        return (s,)

space-nuko's avatar
space-nuko committed
922

space-nuko's avatar
space-nuko committed
923
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):
924
    device = comfy.model_management.get_torch_device()
925
    latent_image = latent["samples"]
926

comfyanonymous's avatar
comfyanonymous committed
927
928
929
    if disable_noise:
        noise = torch.zeros(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, device="cpu")
    else:
930
931
        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
932

933
    noise_mask = None
934
    if "noise_mask" in latent:
935
        noise_mask = latent["noise_mask"]
comfyanonymous's avatar
comfyanonymous committed
936

space-nuko's avatar
space-nuko committed
937
938
939
940
    preview_format = "JPEG"
    if preview_format not in ["JPEG", "PNG"]:
        preview_format = "JPEG"

941
    previewer = latent_preview.get_previewer(device)
space-nuko's avatar
space-nuko committed
942

943
    pbar = comfy.utils.ProgressBar(steps)
944
    def callback(step, x0, x, total_steps):
space-nuko's avatar
space-nuko committed
945
        preview_bytes = None
946
        if previewer:
947
            preview_bytes = previewer.decode_latent_to_preview_image(preview_format, x0)
space-nuko's avatar
space-nuko committed
948
        pbar.update_absolute(step + 1, total_steps, preview_bytes)
949

950
951
    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,
952
                                  force_full_denoise=force_full_denoise, noise_mask=noise_mask, callback=callback)
953
954
955
    out = latent.copy()
    out["samples"] = samples
    return (out, )
comfyanonymous's avatar
comfyanonymous committed
956

comfyanonymous's avatar
comfyanonymous committed
957
958
959
class KSampler:
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
960
        return {"required":
comfyanonymous's avatar
comfyanonymous committed
961
962
963
964
965
966
967
968
969
970
                    {"model": ("MODEL",),
                    "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
                    "steps": ("INT", {"default": 20, "min": 1, "max": 10000}),
                    "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0}),
                    "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
971
972
                     }
                }
comfyanonymous's avatar
comfyanonymous committed
973
974
975
976

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

977
978
    CATEGORY = "sampling"

space-nuko's avatar
space-nuko committed
979
980
    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
981

comfyanonymous's avatar
comfyanonymous committed
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
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}),
                    "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0}),
                    "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
999
1000
                     }
                }
comfyanonymous's avatar
comfyanonymous committed
1001
1002
1003
1004
1005

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

    CATEGORY = "sampling"
comfyanonymous's avatar
comfyanonymous committed
1006

space-nuko's avatar
space-nuko committed
1007
    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
1008
1009
1010
1011
1012
1013
        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
1014
        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
1015
1016
1017

class SaveImage:
    def __init__(self):
1018
        self.output_dir = folder_paths.get_output_directory()
m957ymj75urz's avatar
m957ymj75urz committed
1019
        self.type = "output"
comfyanonymous's avatar
comfyanonymous committed
1020
1021
1022
1023

    @classmethod
    def INPUT_TYPES(s):
        return {"required": 
1024
                    {"images": ("IMAGE", ),
pythongosssss's avatar
tidy  
pythongosssss committed
1025
                     "filename_prefix": ("STRING", {"default": "ComfyUI"})},
pythongosssss's avatar
pythongosssss committed
1026
                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
comfyanonymous's avatar
comfyanonymous committed
1027
1028
1029
1030
1031
1032
1033
                }

    RETURN_TYPES = ()
    FUNCTION = "save_images"

    OUTPUT_NODE = True

1034
1035
    CATEGORY = "image"

pythongosssss's avatar
tidy  
pythongosssss committed
1036
    def save_images(self, images, filename_prefix="ComfyUI", prompt=None, extra_pnginfo=None):
1037
        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
1038
        results = list()
comfyanonymous's avatar
comfyanonymous committed
1039
1040
        for image in images:
            i = 255. * image.cpu().numpy()
1041
            img = Image.fromarray(np.clip(i, 0, 255).astype(np.uint8))
comfyanonymous's avatar
comfyanonymous committed
1042
1043
1044
1045
1046
1047
            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]))
1048

1049
            file = f"{filename}_{counter:05}_.png"
1050
            img.save(os.path.join(full_output_folder, file), pnginfo=metadata, compress_level=4)
m957ymj75urz's avatar
m957ymj75urz committed
1051
1052
1053
1054
            results.append({
                "filename": file,
                "subfolder": subfolder,
                "type": self.type
Gavroche CryptoRUSH's avatar
Gavroche CryptoRUSH committed
1055
            })
1056
            counter += 1
comfyanonymous's avatar
comfyanonymous committed
1057

m957ymj75urz's avatar
m957ymj75urz committed
1058
        return { "ui": { "images": results } }
comfyanonymous's avatar
comfyanonymous committed
1059

pythongosssss's avatar
pythongosssss committed
1060
1061
class PreviewImage(SaveImage):
    def __init__(self):
1062
        self.output_dir = folder_paths.get_temp_directory()
m957ymj75urz's avatar
m957ymj75urz committed
1063
        self.type = "temp"
pythongosssss's avatar
pythongosssss committed
1064
1065
1066

    @classmethod
    def INPUT_TYPES(s):
1067
        return {"required":
pythongosssss's avatar
pythongosssss committed
1068
1069
1070
                    {"images": ("IMAGE", ), },
                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
                }
1071

1072
1073
1074
class LoadImage:
    @classmethod
    def INPUT_TYPES(s):
1075
        input_dir = folder_paths.get_input_directory()
comfyanonymous's avatar
comfyanonymous committed
1076
        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
1077
        return {"required":
comfyanonymous's avatar
comfyanonymous committed
1078
                    {"image": (sorted(files), )},
1079
                }
1080
1081

    CATEGORY = "image"
1082

1083
    RETURN_TYPES = ("IMAGE", "MASK")
1084
1085
    FUNCTION = "load_image"
    def load_image(self, image):
1086
        image_path = folder_paths.get_annotated_filepath(image)
1087
        i = Image.open(image_path)
1088
        i = ImageOps.exif_transpose(i)
1089
        image = i.convert("RGB")
1090
        image = np.array(image).astype(np.float32) / 255.0
1091
        image = torch.from_numpy(image)[None,]
1092
1093
1094
1095
1096
1097
        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")
        return (image, mask)
1098

1099
1100
    @classmethod
    def IS_CHANGED(s, image):
1101
        image_path = folder_paths.get_annotated_filepath(image)
1102
1103
1104
1105
        m = hashlib.sha256()
        with open(image_path, 'rb') as f:
            m.update(f.read())
        return m.digest().hex()
pythongosssss's avatar
pythongosssss committed
1106

1107
1108
1109
1110
1111
1112
1113
    @classmethod
    def VALIDATE_INPUTS(s, image):
        if not folder_paths.exists_annotated_filepath(image):
            return "Invalid image file: {}".format(image)

        return True

1114
class LoadImageMask:
1115
    _color_channels = ["alpha", "red", "green", "blue"]
1116
1117
    @classmethod
    def INPUT_TYPES(s):
1118
        input_dir = folder_paths.get_input_directory()
comfyanonymous's avatar
comfyanonymous committed
1119
        files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
1120
        return {"required":
comfyanonymous's avatar
comfyanonymous committed
1121
                    {"image": (sorted(files), ),
1122
                     "channel": (s._color_channels, ), }
1123
1124
                }

1125
    CATEGORY = "mask"
1126
1127
1128
1129

    RETURN_TYPES = ("MASK",)
    FUNCTION = "load_image"
    def load_image(self, image, channel):
1130
        image_path = folder_paths.get_annotated_filepath(image)
1131
        i = Image.open(image_path)
1132
        i = ImageOps.exif_transpose(i)
1133
1134
        if i.getbands() != ("R", "G", "B", "A"):
            i = i.convert("RGBA")
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
        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")
        return (mask,)

    @classmethod
    def IS_CHANGED(s, image, channel):
1148
        image_path = folder_paths.get_annotated_filepath(image)
1149
1150
1151
1152
        m = hashlib.sha256()
        with open(image_path, 'rb') as f:
            m.update(f.read())
        return m.digest().hex()
pythongosssss's avatar
pythongosssss committed
1153

1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
    @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
1164
class ImageScale:
comfyanonymous's avatar
comfyanonymous committed
1165
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic"]
comfyanonymous's avatar
comfyanonymous committed
1166
1167
1168
1169
1170
    crop_methods = ["disabled", "center"]

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "image": ("IMAGE",), "upscale_method": (s.upscale_methods,),
1171
1172
                              "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
1173
1174
1175
1176
                              "crop": (s.crop_methods,)}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "upscale"

1177
    CATEGORY = "image/upscaling"
1178

comfyanonymous's avatar
comfyanonymous committed
1179
1180
    def upscale(self, image, upscale_method, width, height, crop):
        samples = image.movedim(-1,1)
comfyanonymous's avatar
comfyanonymous committed
1181
        s = comfy.utils.common_upscale(samples, width, height, upscale_method, crop)
comfyanonymous's avatar
comfyanonymous committed
1182
1183
        s = s.movedim(1,-1)
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
1184

comfyanonymous's avatar
comfyanonymous committed
1185
class ImageScaleBy:
comfyanonymous's avatar
comfyanonymous committed
1186
    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic"]
comfyanonymous's avatar
comfyanonymous committed
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204

    @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,)

1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
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,)


Guo Y.K's avatar
Guo Y.K committed
1221
1222
1223
1224
1225
1226
1227
class ImagePadForOutpaint:

    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "image": ("IMAGE",),
1228
1229
1230
1231
                "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}),
1232
                "feathering": ("INT", {"default": 40, "min": 0, "max": MAX_RESOLUTION, "step": 1}),
Guo Y.K's avatar
Guo Y.K committed
1233
1234
1235
1236
1237
1238
1239
1240
            }
        }

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

    CATEGORY = "image"

1241
    def expand_image(self, image, left, top, right, bottom, feathering):
Guo Y.K's avatar
Guo Y.K committed
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
        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,
        )
1254

1255
1256
1257
1258
1259
        t = torch.zeros(
            (d2, d3),
            dtype=torch.float32
        )

1260
        if feathering > 0 and feathering * 2 < d2 and feathering * 2 < d3:
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279

            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
1280

Guo Y.K's avatar
Guo Y.K committed
1281
1282
1283
        return (new_image, mask)


comfyanonymous's avatar
comfyanonymous committed
1284
1285
NODE_CLASS_MAPPINGS = {
    "KSampler": KSampler,
1286
    "CheckpointLoaderSimple": CheckpointLoaderSimple,
comfyanonymous's avatar
comfyanonymous committed
1287
    "CLIPTextEncode": CLIPTextEncode,
comfyanonymous's avatar
comfyanonymous committed
1288
    "CLIPSetLastLayer": CLIPSetLastLayer,
comfyanonymous's avatar
comfyanonymous committed
1289
1290
    "VAEDecode": VAEDecode,
    "VAEEncode": VAEEncode,
1291
    "VAEEncodeForInpaint": VAEEncodeForInpaint,
comfyanonymous's avatar
comfyanonymous committed
1292
1293
1294
    "VAELoader": VAELoader,
    "EmptyLatentImage": EmptyLatentImage,
    "LatentUpscale": LatentUpscale,
comfyanonymous's avatar
comfyanonymous committed
1295
    "LatentUpscaleBy": LatentUpscaleBy,
1296
    "LatentFromBatch": LatentFromBatch,
1297
    "RepeatLatentBatch": RepeatLatentBatch,
comfyanonymous's avatar
comfyanonymous committed
1298
    "SaveImage": SaveImage,
pythongosssss's avatar
pythongosssss committed
1299
    "PreviewImage": PreviewImage,
comfyanonymous's avatar
comfyanonymous committed
1300
    "LoadImage": LoadImage,
1301
    "LoadImageMask": LoadImageMask,
comfyanonymous's avatar
comfyanonymous committed
1302
    "ImageScale": ImageScale,
comfyanonymous's avatar
comfyanonymous committed
1303
    "ImageScaleBy": ImageScaleBy,
1304
    "ImageInvert": ImageInvert,
Guo Y.K's avatar
Guo Y.K committed
1305
    "ImagePadForOutpaint": ImagePadForOutpaint,
FizzleDorf's avatar
FizzleDorf committed
1306
    "ConditioningAverage ": ConditioningAverage ,
comfyanonymous's avatar
comfyanonymous committed
1307
1308
    "ConditioningCombine": ConditioningCombine,
    "ConditioningSetArea": ConditioningSetArea,
Jacob Segal's avatar
Jacob Segal committed
1309
    "ConditioningSetMask": ConditioningSetMask,
comfyanonymous's avatar
comfyanonymous committed
1310
    "KSamplerAdvanced": KSamplerAdvanced,
1311
    "SetLatentNoiseMask": SetLatentNoiseMask,
comfyanonymous's avatar
comfyanonymous committed
1312
    "LatentComposite": LatentComposite,
comfyanonymous's avatar
comfyanonymous committed
1313
    "LatentRotate": LatentRotate,
comfyanonymous's avatar
comfyanonymous committed
1314
    "LatentFlip": LatentFlip,
comfyanonymous's avatar
comfyanonymous committed
1315
    "LatentCrop": LatentCrop,
1316
    "LoraLoader": LoraLoader,
1317
    "CLIPLoader": CLIPLoader,
1318
    "CLIPVisionEncode": CLIPVisionEncode,
1319
    "StyleModelApply": StyleModelApply,
1320
    "unCLIPConditioning": unCLIPConditioning,
comfyanonymous's avatar
comfyanonymous committed
1321
1322
    "ControlNetApply": ControlNetApply,
    "ControlNetLoader": ControlNetLoader,
1323
    "DiffControlNetLoader": DiffControlNetLoader,
comfyanonymous's avatar
comfyanonymous committed
1324
1325
    "StyleModelLoader": StyleModelLoader,
    "CLIPVisionLoader": CLIPVisionLoader,
1326
    "VAEDecodeTiled": VAEDecodeTiled,
comfyanonymous's avatar
comfyanonymous committed
1327
    "VAEEncodeTiled": VAEEncodeTiled,
1328
    "unCLIPCheckpointLoader": unCLIPCheckpointLoader,
1329
1330
1331
    "GLIGENLoader": GLIGENLoader,
    "GLIGENTextBoxApply": GLIGENTextBoxApply,

1332
    "CheckpointLoader": CheckpointLoader,
sALTaccount's avatar
sALTaccount committed
1333
    "DiffusersLoader": DiffusersLoader,
Dr.Lt.Data's avatar
Dr.Lt.Data committed
1334
1335

    "LoadLatent": LoadLatent,
1336
    "SaveLatent": SaveLatent,
comfyanonymous's avatar
comfyanonymous committed
1337
1338
}

City's avatar
City committed
1339
1340
1341
1342
1343
NODE_DISPLAY_NAME_MAPPINGS = {
    # Sampling
    "KSampler": "KSampler",
    "KSamplerAdvanced": "KSampler (Advanced)",
    # Loaders
comfyanonymous's avatar
Rename.  
comfyanonymous committed
1344
1345
    "CheckpointLoader": "Load Checkpoint (With Config)",
    "CheckpointLoaderSimple": "Load Checkpoint",
City's avatar
City committed
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
    "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
1360
    "ConditioningAverage ": "Conditioning (Average)",
City's avatar
City committed
1361
    "ConditioningSetArea": "Conditioning (Set Area)",
Jacob Segal's avatar
Jacob Segal committed
1362
    "ConditioningSetMask": "Conditioning (Set Mask)",
City's avatar
City committed
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
    "ControlNetApply": "Apply ControlNet",
    # 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
1374
    "LatentUpscaleBy": "Upscale Latent By",
City's avatar
City committed
1375
    "LatentComposite": "Latent Composite",
1376
1377
    "LatentFromBatch" : "Latent From Batch",
    "RepeatLatentBatch": "Repeat Latent Batch",
City's avatar
City committed
1378
1379
1380
1381
1382
1383
    # Image
    "SaveImage": "Save Image",
    "PreviewImage": "Preview Image",
    "LoadImage": "Load Image",
    "LoadImageMask": "Load Image (as Mask)",
    "ImageScale": "Upscale Image",
comfyanonymous's avatar
comfyanonymous committed
1384
    "ImageScaleBy": "Upscale Image By",
City's avatar
City committed
1385
1386
1387
1388
1389
1390
1391
1392
    "ImageUpscaleWithModel": "Upscale Image (using Model)",
    "ImageInvert": "Invert Image",
    "ImagePadForOutpaint": "Pad Image for Outpainting",
    # _for_testing
    "VAEDecodeTiled": "VAE Decode (Tiled)",
    "VAEEncodeTiled": "VAE Encode (Tiled)",
}

1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
def load_custom_node(module_path):
    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)
        else:
            module_spec = importlib.util.spec_from_file_location(module_name, os.path.join(module_path, "__init__.py"))
        module = importlib.util.module_from_spec(module_spec)
        sys.modules[module_name] = module
        module_spec.loader.exec_module(module)
        if hasattr(module, "NODE_CLASS_MAPPINGS") and getattr(module, "NODE_CLASS_MAPPINGS") is not None:
            NODE_CLASS_MAPPINGS.update(module.NODE_CLASS_MAPPINGS)
1408
1409
            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)
1410
            return True
1411
1412
        else:
            print(f"Skip {module_path} module for custom nodes due to the lack of NODE_CLASS_MAPPINGS.")
1413
            return False
1414
1415
1416
    except Exception as e:
        print(traceback.format_exc())
        print(f"Cannot import {module_path} module for custom nodes:", e)
1417
        return False
1418

Hacker 17082006's avatar
Hacker 17082006 committed
1419
def load_custom_nodes():
1420
    node_paths = folder_paths.get_folder_paths("custom_nodes")
1421
    node_import_times = []
1422
1423
1424
1425
1426
1427
1428
1429
    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
1430
            if module_path.endswith(".disabled"): continue
1431
            time_before = time.perf_counter()
1432
            success = load_custom_node(module_path)
1433
            node_import_times.append((time.perf_counter() - time_before, module_path, success))
1434

1435
    if len(node_import_times) > 0:
comfyanonymous's avatar
comfyanonymous committed
1436
        print("\nImport times for custom nodes:")
1437
        for n in sorted(node_import_times):
1438
1439
1440
1441
1442
            if n[2]:
                import_message = ""
            else:
                import_message = " (IMPORT FAILED)"
            print("{:6.1f} seconds{}:".format(n[0], import_message), n[1])
1443
        print()
1444

1445
def init_custom_nodes():
1446
    load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_hypernetwork.py"))
1447
1448
    load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_upscale_model.py"))
    load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_post_processing.py"))
1449
    load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_mask.py"))
1450
    load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_rebatch.py"))
1451
    load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_model_merging.py"))
1452
    load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_tomesd.py"))
1453
    load_custom_nodes()