nodes.py 12.8 KB
Newer Older
comfyanonymous's avatar
comfyanonymous committed
1
2
3
4
5
import torch

import os
import sys
import json
6
import hashlib
comfyanonymous's avatar
comfyanonymous committed
7
import copy
comfyanonymous's avatar
comfyanonymous committed
8
9
10
11
12
13
14
15
16
17
18
19

from PIL import Image
from PIL.PngImagePlugin import PngInfo
import numpy as np

sys.path.append(os.path.join(sys.path[0], "comfy"))


import comfy.samplers
import comfy.sd

supported_ckpt_extensions = ['.ckpt']
comfyanonymous's avatar
comfyanonymous committed
20
supported_pt_extensions = ['.ckpt', '.pt']
comfyanonymous's avatar
comfyanonymous committed
21
22
23
try:
    import safetensors.torch
    supported_ckpt_extensions += ['.safetensors']
comfyanonymous's avatar
comfyanonymous committed
24
    supported_pt_extensions += ['.safetensors']
comfyanonymous's avatar
comfyanonymous committed
25
26
27
28
29
30
31
32
33
except:
    print("Could not import safetensors, safetensors support disabled.")

def filter_files_extensions(files, extensions):
    return sorted(list(filter(lambda a: os.path.splitext(a)[-1].lower() in extensions, files)))

class CLIPTextEncode:
    @classmethod
    def INPUT_TYPES(s):
34
        return {"required": {"text": ("STRING", {"multiline": True}), "clip": ("CLIP", )}}
comfyanonymous's avatar
comfyanonymous committed
35
36
37
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "encode"

38
39
    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
40
    def encode(self, clip, text):
comfyanonymous's avatar
comfyanonymous committed
41
42
43
44
45
46
47
48
49
        return ([[clip.encode(text), {}]], )

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

50
51
    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
    def combine(self, conditioning_1, conditioning_2):
        return (conditioning_1 + conditioning_2, )

class ConditioningSetArea:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"conditioning": ("CONDITIONING", ),
                              "width": ("INT", {"default": 64, "min": 64, "max": 4096, "step": 64}),
                              "height": ("INT", {"default": 64, "min": 64, "max": 4096, "step": 64}),
                              "x": ("INT", {"default": 0, "min": 0, "max": 4096, "step": 64}),
                              "y": ("INT", {"default": 0, "min": 0, "max": 4096, "step": 64}),
                              "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
                             }}
    RETURN_TYPES = ("CONDITIONING",)
    FUNCTION = "append"

68
69
    CATEGORY = "conditioning"

comfyanonymous's avatar
comfyanonymous committed
70
71
72
73
74
75
76
77
    def append(self, conditioning, width, height, x, y, strength, min_sigma=0.0, max_sigma=99.0):
        c = copy.deepcopy(conditioning)
        for t in c:
            t[1]['area'] = (height // 8, width // 8, y // 8, x // 8)
            t[1]['strength'] = strength
            t[1]['min_sigma'] = min_sigma
            t[1]['max_sigma'] = max_sigma
        return (c, )
comfyanonymous's avatar
comfyanonymous committed
78
79
80
81
82
83
84
85
86
87
88

class VAEDecode:
    def __init__(self, device="cpu"):
        self.device = device

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "decode"

89
90
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
91
92
93
94
95
96
97
98
99
100
101
102
103
    def decode(self, vae, samples):
        return (vae.decode(samples), )

class VAEEncode:
    def __init__(self, device="cpu"):
        self.device = device

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "pixels": ("IMAGE", ), "vae": ("VAE", )}}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "encode"

104
105
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
106
    def encode(self, vae, pixels):
107
108
109
110
        x = (pixels.shape[1] // 64) * 64
        y = (pixels.shape[2] // 64) * 64
        if pixels.shape[1] != x or pixels.shape[2] != y:
            pixels = pixels[:,:x,:y,:]
comfyanonymous's avatar
comfyanonymous committed
111
112
113
114
115
116
117
118
119
120
121
122
123
124
        return (vae.encode(pixels), )

class CheckpointLoader:
    models_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "models")
    config_dir = os.path.join(models_dir, "configs")
    ckpt_dir = os.path.join(models_dir, "checkpoints")

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "config_name": (filter_files_extensions(os.listdir(s.config_dir), '.yaml'), ),
                              "ckpt_name": (filter_files_extensions(os.listdir(s.ckpt_dir), supported_ckpt_extensions), )}}
    RETURN_TYPES = ("MODEL", "CLIP", "VAE")
    FUNCTION = "load_checkpoint"

125
126
    CATEGORY = "loaders"

comfyanonymous's avatar
comfyanonymous committed
127
128
129
    def load_checkpoint(self, config_name, ckpt_name, output_vae=True, output_clip=True):
        config_path = os.path.join(self.config_dir, config_name)
        ckpt_path = os.path.join(self.ckpt_dir, ckpt_name)
130
131
        embedding_directory = os.path.join(self.models_dir, "embeddings")
        return comfy.sd.load_checkpoint(config_path, ckpt_path, output_vae=True, output_clip=True, embedding_directory=embedding_directory)
comfyanonymous's avatar
comfyanonymous committed
132
133
134
135
136
137

class VAELoader:
    models_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "models")
    vae_dir = os.path.join(models_dir, "vae")
    @classmethod
    def INPUT_TYPES(s):
comfyanonymous's avatar
comfyanonymous committed
138
        return {"required": { "vae_name": (filter_files_extensions(os.listdir(s.vae_dir), supported_pt_extensions), )}}
comfyanonymous's avatar
comfyanonymous committed
139
140
141
    RETURN_TYPES = ("VAE",)
    FUNCTION = "load_vae"

142
143
    CATEGORY = "loaders"

comfyanonymous's avatar
comfyanonymous committed
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
    #TODO: scale factor?
    def load_vae(self, vae_name):
        vae_path = os.path.join(self.vae_dir, vae_name)
        vae = comfy.sd.VAE(ckpt_path=vae_path)
        return (vae,)

class EmptyLatentImage:
    def __init__(self, device="cpu"):
        self.device = device

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "width": ("INT", {"default": 512, "min": 64, "max": 4096, "step": 64}),
                              "height": ("INT", {"default": 512, "min": 64, "max": 4096, "step": 64}),
                              "batch_size": ("INT", {"default": 1, "min": 1, "max": 64})}}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "generate"

162
163
    CATEGORY = "latent"

comfyanonymous's avatar
comfyanonymous committed
164
165
166
167
168
169
    def generate(self, width, height, batch_size=1):
        latent = torch.zeros([batch_size, 4, height // 8, width // 8])
        return (latent, )

class LatentUpscale:
    upscale_methods = ["nearest-exact", "bilinear", "area"]
170
    crop_methods = ["disabled", "center"]
comfyanonymous's avatar
comfyanonymous committed
171
172
173
174
175

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",), "upscale_method": (s.upscale_methods,),
                              "width": ("INT", {"default": 512, "min": 64, "max": 4096, "step": 64}),
176
177
                              "height": ("INT", {"default": 512, "min": 64, "max": 4096, "step": 64}),
                              "crop": (s.crop_methods,)}}
comfyanonymous's avatar
comfyanonymous committed
178
179
180
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "upscale"

181
182
    CATEGORY = "latent"

183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
    def upscale(self, samples, upscale_method, width, height, crop):
        if crop == "center":
            old_width = samples.shape[3]
            old_height = samples.shape[2]
            old_aspect = old_width / old_height
            new_aspect = width / height
            x = 0
            y = 0
            if old_aspect > new_aspect:
                x = round((old_width - old_width * (new_aspect / old_aspect)) / 2)
            elif old_aspect < new_aspect:
                y = round((old_height - old_height * (old_aspect / new_aspect)) / 2)
            s = samples[:,:,y:old_height-y,x:old_width-x]
        else:
            s = samples
        s = torch.nn.functional.interpolate(s, size=(height // 8, width // 8), mode=upscale_method)
comfyanonymous's avatar
comfyanonymous committed
199
200
        return (s,)

comfyanonymous's avatar
comfyanonymous committed
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
class LatentRotate:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "samples": ("LATENT",),
                              "rotation": (["none", "90 degrees", "180 degrees", "270 degrees"],),
                              }}
    RETURN_TYPES = ("LATENT",)
    FUNCTION = "rotate"

    CATEGORY = "latent"

    def rotate(self, samples, rotation):
        s = samples.clone()
        rotate_by = 0
        if rotation.startswith("90"):
            rotate_by = 1
        elif rotation.startswith("180"):
            rotate_by = 2
        elif rotation.startswith("270"):
            rotate_by = 3

        s = torch.rot90(samples, k=rotate_by, dims=[3, 2])
        return (s,)
comfyanonymous's avatar
comfyanonymous committed
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
class KSampler:
    def __init__(self, device="cuda"):
        self.device = device

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

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

246
247
    CATEGORY = "sampling"

comfyanonymous's avatar
comfyanonymous committed
248
249
250
251
252
253
    def sample(self, model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=1.0):
        noise = torch.randn(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, generator=torch.manual_seed(seed), device="cpu")
        model = model.to(self.device)
        noise = noise.to(self.device)
        latent_image = latent_image.to(self.device)

comfyanonymous's avatar
comfyanonymous committed
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
        positive_copy = []
        negative_copy = []

        for p in positive:
            t = p[0]
            if t.shape[0] < noise.shape[0]:
                t = torch.cat([t] * noise.shape[0])
            t = t.to(self.device)
            positive_copy += [[t] + p[1:]]
        for n in negative:
            t = n[0]
            if t.shape[0] < noise.shape[0]:
                t = torch.cat([t] * noise.shape[0])
            t = t.to(self.device)
            negative_copy += [[t] + n[1:]]
comfyanonymous's avatar
comfyanonymous committed
269
270
271
272
273
274
275

        if sampler_name in comfy.samplers.KSampler.SAMPLERS:
            sampler = comfy.samplers.KSampler(model, steps=steps, device=self.device, sampler=sampler_name, scheduler=scheduler, denoise=denoise)
        else:
            #other samplers
            pass

comfyanonymous's avatar
comfyanonymous committed
276
        samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image)
comfyanonymous's avatar
comfyanonymous committed
277
278
279
280
281
282
283
284
285
286
287
288
        samples = samples.cpu()
        model = model.cpu()
        return (samples, )


class SaveImage:
    def __init__(self):
        self.output_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "output")

    @classmethod
    def INPUT_TYPES(s):
        return {"required": 
289
290
                    {"images": ("IMAGE", ),
                     "filename_prefix": ("STRING", {"default": "ComfyUI"})},
comfyanonymous's avatar
comfyanonymous committed
291
292
293
294
295
296
297
298
                "hidden": {"prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"},
                }

    RETURN_TYPES = ()
    FUNCTION = "save_images"

    OUTPUT_NODE = True

299
300
    CATEGORY = "image"

301
302
303
304
305
306
307
308
309
310
311
312
313
    def save_images(self, images, filename_prefix="ComfyUI", prompt=None, extra_pnginfo=None):
        def map_filename(filename):
            prefix_len = len(filename_prefix)
            prefix = filename[:prefix_len + 1]
            try:
                digits = int(filename[prefix_len + 1:].split('_')[0])
            except:
                digits = 0
            return (digits, prefix)
        try:
            counter = max(filter(lambda a: a[1][:-1] == filename_prefix and a[1][-1] == "_", map(map_filename, os.listdir(self.output_dir))))[0] + 1
        except ValueError:
            counter = 1
comfyanonymous's avatar
comfyanonymous committed
314
315
316
317
318
319
320
321
322
        for image in images:
            i = 255. * image.cpu().numpy()
            img = Image.fromarray(i.astype(np.uint8))
            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]))
323
324
            img.save(f"output/{filename_prefix}_{counter:05}_.png", pnginfo=metadata, optimize=True)
            counter += 1
comfyanonymous's avatar
comfyanonymous committed
325

326
327
328
329
330
331
332
class LoadImage:
    input_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "input")
    @classmethod
    def INPUT_TYPES(s):
        return {"required":
                    {"image": (os.listdir(s.input_dir), )},
                }
333
334

    CATEGORY = "image"
335
336
337
338
339
340
341
342
343
344

    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "load_image"
    def load_image(self, image):
        image_path = os.path.join(self.input_dir, image)
        image = Image.open(image_path).convert("RGB")
        image = np.array(image).astype(np.float32) / 255.0
        image = torch.from_numpy(image[None])[None,]
        return image

345
346
347
348
349
350
351
352
    @classmethod
    def IS_CHANGED(s, image):
        image_path = os.path.join(s.input_dir, image)
        m = hashlib.sha256()
        with open(image_path, 'rb') as f:
            m.update(f.read())
        return m.digest().hex()

353

comfyanonymous's avatar
comfyanonymous committed
354
355
356
357
358
359
360
361
362
363
364

NODE_CLASS_MAPPINGS = {
    "KSampler": KSampler,
    "CheckpointLoader": CheckpointLoader,
    "CLIPTextEncode": CLIPTextEncode,
    "VAEDecode": VAEDecode,
    "VAEEncode": VAEEncode,
    "VAELoader": VAELoader,
    "EmptyLatentImage": EmptyLatentImage,
    "LatentUpscale": LatentUpscale,
    "SaveImage": SaveImage,
comfyanonymous's avatar
comfyanonymous committed
365
366
367
    "LoadImage": LoadImage,
    "ConditioningCombine": ConditioningCombine,
    "ConditioningSetArea": ConditioningSetArea,
comfyanonymous's avatar
comfyanonymous committed
368
    "LatentRotate": LatentRotate,
comfyanonymous's avatar
comfyanonymous committed
369
370
371
}