PseudoTerminal X commited on
Commit
6c87ba4
1 Parent(s): df96057

Trained for 0 epochs and 25000 steps.

Browse files

Trained with datasets ['text-embeds', 'text-embeds-extra', 'image-embeds', 'sports', 'mj-60', 'id-75k', 'celebrities', 'normalnudes', 'guys', 'pixel-art', 'signs', 'dalle3', 'sfwbooru', 'moviecollection', 'bookcovers', 'nijijourney', 'experimental', 'ethnic', 'gay', 'architecture', 'shutterstock', 'midjourney-v6-520k-raw', 'nijijourney-v6-520k-raw', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp']
Learning rate 1e-06, batch size 12, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'linspace' timestep spacing.
Base model: ptx0/pixart-900m-1024-ft-v0.7-stage1
VAE: ptx0/pixart-900m-1024-ft-v0.7-stage1

README.md CHANGED
@@ -10,512 +10,7 @@ tags:
10
  - full
11
 
12
  inference: true
13
- widget:
14
- - text: 'unconditional (blank prompt)'
15
- parameters:
16
- negative_prompt: 'blurry, cropped, ugly'
17
- output:
18
- url: ./assets/image_0_0.png
19
- - text: 'Alien planet, strange rock formations, glowing plants, bizarre creatures, surreal atmosphere'
20
- parameters:
21
- negative_prompt: 'blurry, cropped, ugly'
22
- output:
23
- url: ./assets/image_1_0.png
24
- - text: 'Alien marketplace, bizarre creatures, exotic goods, vibrant colors, otherworldly atmosphere'
25
- parameters:
26
- negative_prompt: 'blurry, cropped, ugly'
27
- output:
28
- url: ./assets/image_2_0.png
29
- - text: 'Child holding a balloon, happy expression, colorful balloons, sunny day, high detail'
30
- parameters:
31
- negative_prompt: 'blurry, cropped, ugly'
32
- output:
33
- url: ./assets/image_3_0.png
34
- - text: 'a 4-panel comic strip showing an orange cat saying the words ''HELP'' and ''LASAGNA'''
35
- parameters:
36
- negative_prompt: 'blurry, cropped, ugly'
37
- output:
38
- url: ./assets/image_4_0.png
39
- - text: 'a hand is holding a comic book with a cover that reads ''The Adventures of Superhero'''
40
- parameters:
41
- negative_prompt: 'blurry, cropped, ugly'
42
- output:
43
- url: ./assets/image_5_0.png
44
- - text: 'Underground cave filled with crystals, glowing lights, reflective surfaces, fantasy environment, high detail'
45
- parameters:
46
- negative_prompt: 'blurry, cropped, ugly'
47
- output:
48
- url: ./assets/image_6_0.png
49
- - text: 'Bustling cyberpunk bazaar, vendors, neon signs, advanced tech, crowded, high detail'
50
- parameters:
51
- negative_prompt: 'blurry, cropped, ugly'
52
- output:
53
- url: ./assets/image_7_0.png
54
- - text: 'Cyberpunk hacker in a dark room, neon glow, multiple screens, intense focus, high detail'
55
- parameters:
56
- negative_prompt: 'blurry, cropped, ugly'
57
- output:
58
- url: ./assets/image_8_0.png
59
- - text: 'a cybernetic anne of green gables with neural implant and bio mech augmentations'
60
- parameters:
61
- negative_prompt: 'blurry, cropped, ugly'
62
- output:
63
- url: ./assets/image_9_0.png
64
- - text: 'Post-apocalyptic cityscape, ruined buildings, overgrown vegetation, dark and gritty, high detail'
65
- parameters:
66
- negative_prompt: 'blurry, cropped, ugly'
67
- output:
68
- url: ./assets/image_10_0.png
69
- - text: 'Magical castle in a lush forest, glowing windows, fantasy architecture, high resolution, detailed textures'
70
- parameters:
71
- negative_prompt: 'blurry, cropped, ugly'
72
- output:
73
- url: ./assets/image_11_0.png
74
- - text: 'Ruins of an ancient temple in an enchanted forest, glowing runes, mystical creatures, high detail'
75
- parameters:
76
- negative_prompt: 'blurry, cropped, ugly'
77
- output:
78
- url: ./assets/image_12_0.png
79
- - text: 'Mystical forest, glowing plants, fairies, magical creatures, fantasy art, high detail'
80
- parameters:
81
- negative_prompt: 'blurry, cropped, ugly'
82
- output:
83
- url: ./assets/image_13_0.png
84
- - text: 'Magical garden with glowing flowers, fairies, serene atmosphere, detailed plants, high resolution'
85
- parameters:
86
- negative_prompt: 'blurry, cropped, ugly'
87
- output:
88
- url: ./assets/image_14_0.png
89
- - text: 'Whimsical garden filled with fairies, magical plants, sparkling lights, serene atmosphere, high detail'
90
- parameters:
91
- negative_prompt: 'blurry, cropped, ugly'
92
- output:
93
- url: ./assets/image_15_0.png
94
- - text: 'Majestic dragon soaring through the sky, detailed scales, dynamic pose, fantasy art, high resolution'
95
- parameters:
96
- negative_prompt: 'blurry, cropped, ugly'
97
- output:
98
- url: ./assets/image_16_0.png
99
- - text: 'Fantasy world, floating islands in the sky, waterfalls, lush vegetation, detailed landscape, high resolution'
100
- parameters:
101
- negative_prompt: 'blurry, cropped, ugly'
102
- output:
103
- url: ./assets/image_17_0.png
104
- - text: 'Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus'
105
- parameters:
106
- negative_prompt: 'blurry, cropped, ugly'
107
- output:
108
- url: ./assets/image_18_0.png
109
- - text: 'Space battle scene, starships fighting, laser beams, explosions, cosmic background'
110
- parameters:
111
- negative_prompt: 'blurry, cropped, ugly'
112
- output:
113
- url: ./assets/image_19_0.png
114
- - text: 'Abandoned fairground at night, eerie rides, ghostly figures, fog, dark atmosphere, high detail'
115
- parameters:
116
- negative_prompt: 'blurry, cropped, ugly'
117
- output:
118
- url: ./assets/image_20_0.png
119
- - text: 'Spooky haunted mansion on a hill, dark and eerie, glowing windows, ghostly atmosphere, high detail'
120
- parameters:
121
- negative_prompt: 'blurry, cropped, ugly'
122
- output:
123
- url: ./assets/image_21_0.png
124
- - text: 'a hardcover physics textbook that is called PHYSICS FOR DUMMIES'
125
- parameters:
126
- negative_prompt: 'blurry, cropped, ugly'
127
- output:
128
- url: ./assets/image_22_0.png
129
- - text: 'Epic medieval battle, knights in armor, dynamic action, detailed landscape, high resolution'
130
- parameters:
131
- negative_prompt: 'blurry, cropped, ugly'
132
- output:
133
- url: ./assets/image_23_0.png
134
- - text: 'Bustling medieval market with merchants, knights, and jesters, vibrant colors, detailed'
135
- parameters:
136
- negative_prompt: 'blurry, cropped, ugly'
137
- output:
138
- url: ./assets/image_24_0.png
139
- - text: 'Cozy medieval tavern, warm firelight, adventurers drinking, detailed interior, rustic atmosphere'
140
- parameters:
141
- negative_prompt: 'blurry, cropped, ugly'
142
- output:
143
- url: ./assets/image_25_0.png
144
- - text: 'Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus'
145
- parameters:
146
- negative_prompt: 'blurry, cropped, ugly'
147
- output:
148
- url: ./assets/image_26_0.png
149
- - text: 'Forest with neon-lit trees, glowing plants, bioluminescence, surreal atmosphere, high detail'
150
- parameters:
151
- negative_prompt: 'blurry, cropped, ugly'
152
- output:
153
- url: ./assets/image_27_0.png
154
- - text: 'Bright neon sign in a busy city street, ''Open 24 Hours'', bold typography, glowing lights'
155
- parameters:
156
- negative_prompt: 'blurry, cropped, ugly'
157
- output:
158
- url: ./assets/image_28_0.png
159
- - text: 'Vibrant neon sign, ''Bar'', bold typography, dark background, glowing lights, detailed design'
160
- parameters:
161
- negative_prompt: 'blurry, cropped, ugly'
162
- output:
163
- url: ./assets/image_29_0.png
164
- - text: 'Pirate ship on the high seas, stormy weather, detailed sails, dramatic waves, photorealistic'
165
- parameters:
166
- negative_prompt: 'blurry, cropped, ugly'
167
- output:
168
- url: ./assets/image_30_0.png
169
- - text: 'Pirate discovering a treasure chest, detailed gold coins, tropical island, dramatic lighting'
170
- parameters:
171
- negative_prompt: 'blurry, cropped, ugly'
172
- output:
173
- url: ./assets/image_31_0.png
174
- - text: 'a photograph of a woman experiencing a psychedelic trip. trippy, 8k, uhd, fractal'
175
- parameters:
176
- negative_prompt: 'blurry, cropped, ugly'
177
- output:
178
- url: ./assets/image_32_0.png
179
- - text: 'Cozy cafe on a rainy day, people sipping coffee, warm lights, reflections on wet pavement, photorealistic'
180
- parameters:
181
- negative_prompt: 'blurry, cropped, ugly'
182
- output:
183
- url: ./assets/image_33_0.png
184
- - text: '1980s arcade, neon lights, vintage game machines, kids playing, vibrant colors, nostalgic atmosphere'
185
- parameters:
186
- negative_prompt: 'blurry, cropped, ugly'
187
- output:
188
- url: ./assets/image_34_0.png
189
- - text: '1980s game room with vintage arcade machines, neon lights, vibrant colors, nostalgic feel'
190
- parameters:
191
- negative_prompt: 'blurry, cropped, ugly'
192
- output:
193
- url: ./assets/image_35_0.png
194
- - text: 'Robot blacksmith forging metal, sparks flying, detailed workshop, futuristic and medieval blend'
195
- parameters:
196
- negative_prompt: 'blurry, cropped, ugly'
197
- output:
198
- url: ./assets/image_36_0.png
199
- - text: 'Sleek robot performing a dance, futuristic theater, holographic effects, detailed, high resolution'
200
- parameters:
201
- negative_prompt: 'blurry, cropped, ugly'
202
- output:
203
- url: ./assets/image_37_0.png
204
- - text: 'High-tech factory where robots are assembled, detailed machinery, futuristic setting, high detail'
205
- parameters:
206
- negative_prompt: 'blurry, cropped, ugly'
207
- output:
208
- url: ./assets/image_38_0.png
209
- - text: 'Garden tended by robots, mechanical plants, colorful flowers, futuristic setting, high detail'
210
- parameters:
211
- negative_prompt: 'blurry, cropped, ugly'
212
- output:
213
- url: ./assets/image_39_0.png
214
- - text: 'Cute robotic pet, futuristic home, sleek design, detailed features, friendly and animated'
215
- parameters:
216
- negative_prompt: 'blurry, cropped, ugly'
217
- output:
218
- url: ./assets/image_40_0.png
219
- - text: 'cctv trail camera night time security picture of a wendigo in the woods'
220
- parameters:
221
- negative_prompt: 'blurry, cropped, ugly'
222
- output:
223
- url: ./assets/image_41_0.png
224
- - text: 'Astronaut exploring an alien planet, detailed landscape, futuristic suit, cosmic background'
225
- parameters:
226
- negative_prompt: 'blurry, cropped, ugly'
227
- output:
228
- url: ./assets/image_42_0.png
229
- - text: 'Futuristic space station orbiting a distant exoplanet, sleek design, detailed structures, cosmic backdrop'
230
- parameters:
231
- negative_prompt: 'blurry, cropped, ugly'
232
- output:
233
- url: ./assets/image_43_0.png
234
- - text: 'a person holding a sign that reads ''SOON'''
235
- parameters:
236
- negative_prompt: 'blurry, cropped, ugly'
237
- output:
238
- url: ./assets/image_44_0.png
239
- - text: 'Steampunk airship in the sky, intricate design, Victorian aesthetics, dynamic scene, high detail'
240
- parameters:
241
- negative_prompt: 'blurry, cropped, ugly'
242
- output:
243
- url: ./assets/image_45_0.png
244
- - text: 'Steampunk inventor in a workshop, intricate gadgets, Victorian attire, mechanical arm, goggles'
245
- parameters:
246
- negative_prompt: 'blurry, cropped, ugly'
247
- output:
248
- url: ./assets/image_46_0.png
249
- - text: 'Stormy ocean with towering waves, dramatic skies, detailed water, intense atmosphere, high resolution'
250
- parameters:
251
- negative_prompt: 'blurry, cropped, ugly'
252
- output:
253
- url: ./assets/image_47_0.png
254
- - text: 'Dramatic stormy sea, lighthouse in the distance, lightning striking, dark clouds, high detail'
255
- parameters:
256
- negative_prompt: 'blurry, cropped, ugly'
257
- output:
258
- url: ./assets/image_48_0.png
259
- - text: 'Graffiti artist creating a mural, vibrant colors, urban setting, dynamic action, high resolution'
260
- parameters:
261
- negative_prompt: 'blurry, cropped, ugly'
262
- output:
263
- url: ./assets/image_49_0.png
264
- - text: 'Urban alleyway filled with vibrant graffiti art, tags and murals, realistic textures'
265
- parameters:
266
- negative_prompt: 'blurry, cropped, ugly'
267
- output:
268
- url: ./assets/image_50_0.png
269
- - text: 'Urban street sign, ''Main Street'', bold typography, realistic textures, weathered look'
270
- parameters:
271
- negative_prompt: 'blurry, cropped, ugly'
272
- output:
273
- url: ./assets/image_51_0.png
274
- - text: 'Classic car show with vintage vehicles, vibrant colors, nostalgic atmosphere, high detail'
275
- parameters:
276
- negative_prompt: 'blurry, cropped, ugly'
277
- output:
278
- url: ./assets/image_52_0.png
279
- - text: 'Retro diner sign, ''Joe''s Diner'', classic 1950s design, neon lights, weathered look'
280
- parameters:
281
- negative_prompt: 'blurry, cropped, ugly'
282
- output:
283
- url: ./assets/image_53_0.png
284
- - text: 'Vintage store sign with elaborate typography, ''Antique Shop'', hand-painted, weathered look'
285
- parameters:
286
- negative_prompt: 'blurry, cropped, ugly'
287
- output:
288
- url: ./assets/image_54_0.png
289
- - text: 'A cinematic portrait photograph of a white tiger in a lush forest at twilight'
290
- parameters:
291
- negative_prompt: 'blurry, cropped, ugly'
292
- output:
293
- url: ./assets/image_55_0.png
294
- - text: 'A landscape photograph of a small cottage in the middle of a field of wild flowers with mountains off in the distance at sunset'
295
- parameters:
296
- negative_prompt: 'blurry, cropped, ugly'
297
- output:
298
- url: ./assets/image_56_0.png
299
- - text: 'A portrait photograph of a young black woman wearing a ball gown in a mansion'
300
- parameters:
301
- negative_prompt: 'blurry, cropped, ugly'
302
- output:
303
- url: ./assets/image_57_0.png
304
- - text: 'A photograph of a sleek and modern house interior with plants and foliage all over the place '
305
- parameters:
306
- negative_prompt: 'blurry, cropped, ugly'
307
- output:
308
- url: ./assets/image_58_0.png
309
- - text: 'A photograph of a snowy forest and river from above at dusk'
310
- parameters:
311
- negative_prompt: 'blurry, cropped, ugly'
312
- output:
313
- url: ./assets/image_59_0.png
314
- - text: 'A macro photograph of a lady bug on the petal of a rose'
315
- parameters:
316
- negative_prompt: 'blurry, cropped, ugly'
317
- output:
318
- url: ./assets/image_60_0.png
319
- - text: 'A photograph of a traditional Japanese meal on top of a bamboo desk'
320
- parameters:
321
- negative_prompt: 'blurry, cropped, ugly'
322
- output:
323
- url: ./assets/image_61_0.png
324
- - text: 'A photograph of a small fairy house covered in mushrooms moss and flowers in a sunny forest'
325
- parameters:
326
- negative_prompt: 'blurry, cropped, ugly'
327
- output:
328
- url: ./assets/image_62_0.png
329
- - text: 'A cinematic landscape photograph of an organic geometric building at night time'
330
- parameters:
331
- negative_prompt: 'blurry, cropped, ugly'
332
- output:
333
- url: ./assets/image_63_0.png
334
- - text: 'A photograph of an abstract cake inspired off of marble and art deco'
335
- parameters:
336
- negative_prompt: 'blurry, cropped, ugly'
337
- output:
338
- url: ./assets/image_64_0.png
339
- - text: 'painting of a water color fart that was both silent and deadly'
340
- parameters:
341
- negative_prompt: 'blurry, cropped, ugly'
342
- output:
343
- url: ./assets/image_65_0.png
344
- - text: 'cleavage shot of harley quinn, fujifilm XT3 sharp focus kodak moment'
345
- parameters:
346
- negative_prompt: 'blurry, cropped, ugly'
347
- output:
348
- url: ./assets/image_66_0.png
349
- - text: 'a woman doing yoga, fujifilm XT3 sharp focus kodak moment'
350
- parameters:
351
- negative_prompt: 'blurry, cropped, ugly'
352
- output:
353
- url: ./assets/image_67_0.png
354
- - text: 'a black and white photo of a woman, dress shirt, somewhat androgenic, one model, rugged, sydney, taken with a canon eos 5d, rugged and dirty, focus on girl, boyish, brigitte, photographed, blue steel, youth, charlie immer, without makeup, uniquely beautiful, on the street, lady kima'
355
- parameters:
356
- negative_prompt: 'blurry, cropped, ugly'
357
- output:
358
- url: ./assets/image_68_0.png
359
- - text: 'obama with his shirt off, muscles flexing'
360
- parameters:
361
- negative_prompt: 'blurry, cropped, ugly'
362
- output:
363
- url: ./assets/image_69_0.png
364
- - text: 'muscle-bound obama, shirtless, flexing, fujifilm XT3 sharp focus kodak moment'
365
- parameters:
366
- negative_prompt: 'blurry, cropped, ugly'
367
- output:
368
- url: ./assets/image_70_0.png
369
- - text: 'donald trump as a religious icon, protestant church-goer, fujifilm XT3 sharp focus kodak moment'
370
- parameters:
371
- negative_prompt: 'blurry, cropped, ugly'
372
- output:
373
- url: ./assets/image_71_0.png
374
- - text: 'a stunning portrait of a shirtless, muscle-bound Justin Trudeau, Canadian Prime Minister bodybuilder, fujifilm XT3 sharp focus kodak moment'
375
- parameters:
376
- negative_prompt: 'blurry, cropped, ugly'
377
- output:
378
- url: ./assets/image_72_0.png
379
- - text: 'a stunning portrait of a shirtless, muscle-bound John Madden bodybuilder, fujifilm XT3 sharp focus kodak moment'
380
- parameters:
381
- negative_prompt: 'blurry, cropped, ugly'
382
- output:
383
- url: ./assets/image_73_0.png
384
- - text: 'a portrait of edward scissorhands looking down at his cellphone, fujifilm XT3'
385
- parameters:
386
- negative_prompt: 'blurry, cropped, ugly'
387
- output:
388
- url: ./assets/image_74_0.png
389
- - text: 'john cena, clown baby, fujifilm XT3, sharp focus'
390
- parameters:
391
- negative_prompt: 'blurry, cropped, ugly'
392
- output:
393
- url: ./assets/image_75_0.png
394
- - text: 'stunning and impossible caustics experiment, suspended liquids, amorphous liquid forms, high intensity light rays, unreal engine 5, raytracing, 4k, laser dot fields, curving light energy beams, glowing energetic caustic liquids, thousands of prismatic bubbles, quantum entangled light rays from other dimensions, negative width height, recursive dimensional portals'
395
- parameters:
396
- negative_prompt: 'blurry, cropped, ugly'
397
- output:
398
- url: ./assets/image_76_0.png
399
- - text: 'stunning and ((impossible)) ((caustics)) ((experiment)) suspended liquids amorphous liquid forms high intensity light rays unreal engine 5 raytracing 4k laser dot arterial flow bioluminescent '
400
- parameters:
401
- negative_prompt: 'blurry, cropped, ugly'
402
- output:
403
- url: ./assets/image_77_0.png
404
- - text: 'terrified pixar child in their bedroom looking up at the ceiling as a glowing red uranium core melts through the ceiling'
405
- parameters:
406
- negative_prompt: 'blurry, cropped, ugly'
407
- output:
408
- url: ./assets/image_78_0.png
409
- - text: 'stunning portrait of john cusack as a twisted jester at the mardi gras carnival, epic, cinematic, 8k'
410
- parameters:
411
- negative_prompt: 'blurry, cropped, ugly'
412
- output:
413
- url: ./assets/image_79_0.png
414
- - text: 'stunning portrait of a beer bottle (with a label that says "LIGMA GRAVY")1.4 full of gravy, epic, cinematic, advertisement'
415
- parameters:
416
- negative_prompt: 'blurry, cropped, ugly'
417
- output:
418
- url: ./assets/image_80_0.png
419
- - text: 'stunning++ photographs of luchador+ wrestlers at the twisted carnival-'
420
- parameters:
421
- negative_prompt: 'blurry, cropped, ugly'
422
- output:
423
- url: ./assets/image_81_0.png
424
- - text: 'The unforeseen friendship: a crow and a cat share a quiet moment, upending the laws of the natural world'
425
- parameters:
426
- negative_prompt: 'blurry, cropped, ugly'
427
- output:
428
- url: ./assets/image_82_0.png
429
- - text: 'A breathtaking landscape of a mystical anime village surrounded by cherry blossoms at sunrise'
430
- parameters:
431
- negative_prompt: 'blurry, cropped, ugly'
432
- output:
433
- url: ./assets/image_83_0.png
434
- - text: 'A dramatic portrait of an anime hero poised for battle against a dystopian cityscape backdrop'
435
- parameters:
436
- negative_prompt: 'blurry, cropped, ugly'
437
- output:
438
- url: ./assets/image_84_0.png
439
- - text: 'A towering, battle-ready mecha robot standing amidst ruins, fujifilm XT3 sharp focus'
440
- parameters:
441
- negative_prompt: 'blurry, cropped, ugly'
442
- output:
443
- url: ./assets/image_85_0.png
444
- - text: 'A sumptuous anime-style feast laid out on a traditional Japanese tatami mat'
445
- parameters:
446
- negative_prompt: 'blurry, cropped, ugly'
447
- output:
448
- url: ./assets/image_86_0.png
449
- - text: 'A photograph capturing an epic fantasy anime scene with dragons flying over ancient castles at twilight'
450
- parameters:
451
- negative_prompt: 'blurry, cropped, ugly'
452
- output:
453
- url: ./assets/image_87_0.png
454
- - text: 'A neon-lit nighttime bustling anime cityscape, with vivid colors and futuristic architecture'
455
- parameters:
456
- negative_prompt: 'blurry, cropped, ugly'
457
- output:
458
- url: ./assets/image_88_0.png
459
- - text: 'two anime characters in a high-energy duel, swords clashing with sparks flying'
460
- parameters:
461
- negative_prompt: 'blurry, cropped, ugly'
462
- output:
463
- url: ./assets/image_89_0.png
464
- - text: 'A cute anime character with their adorable, mystical pet creature in a magical forest'
465
- parameters:
466
- negative_prompt: 'blurry, cropped, ugly'
467
- output:
468
- url: ./assets/image_90_0.png
469
- - text: 'A lively anime school scene, students in uniform bustling around in a cherry-blossom-filled courtyard'
470
- parameters:
471
- negative_prompt: 'blurry, cropped, ugly'
472
- output:
473
- url: ./assets/image_91_0.png
474
- - text: 'A enchanting underwater anime world, with mermaids and exotic sea creatures amidst coral reefs'
475
- parameters:
476
- negative_prompt: 'blurry, cropped, ugly'
477
- output:
478
- url: ./assets/image_92_0.png
479
- - text: 'A breathtaking space anime scene, with starships battling among the stars and nebulas'
480
- parameters:
481
- negative_prompt: 'blurry, cropped, ugly'
482
- output:
483
- url: ./assets/image_93_0.png
484
- - text: 'A photograph showcasing a cyberpunk anime street scene, neon lights reflecting off rain-slicked streets'
485
- parameters:
486
- negative_prompt: 'blurry, cropped, ugly'
487
- output:
488
- url: ./assets/image_94_0.png
489
- - text: 'A serene anime spirit wandering through an ethereal, mist-covered forest'
490
- parameters:
491
- negative_prompt: 'blurry, cropped, ugly'
492
- output:
493
- url: ./assets/image_95_0.png
494
- - text: 'A powerful lone anime samurai standing tall against a backdrop of a setting sun and ancient temples'
495
- parameters:
496
- negative_prompt: 'blurry, cropped, ugly'
497
- output:
498
- url: ./assets/image_96_0.png
499
- - text: 'A anime cooking showdown, chefs in a frantic battle with flames and flying ingredients'
500
- parameters:
501
- negative_prompt: 'blurry, cropped, ugly'
502
- output:
503
- url: ./assets/image_97_0.png
504
- - text: 'A serene anime winter landscape, a small village blanketed in snow with characters in colorful kimonos'
505
- parameters:
506
- negative_prompt: 'blurry, cropped, ugly'
507
- output:
508
- url: ./assets/image_98_0.png
509
- - text: 'A vibrant anime-style festival, lanterns glowing and characters in traditional attire dancing joyfully'
510
- parameters:
511
- negative_prompt: 'blurry, cropped, ugly'
512
- output:
513
- url: ./assets/image_99_0.png
514
- - text: 'a cute anime character named toast, holding a sign that reads SOON'
515
- parameters:
516
- negative_prompt: 'blurry, cropped, ugly'
517
- output:
518
- url: ./assets/image_100_0.png
519
  ---
520
 
521
  # pixart-900m-1024-ft-v0.7-stage1
@@ -540,7 +35,7 @@ a cute anime character named toast, holding a sign that reads SOON
540
 
541
  Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
542
 
543
- You can find some example images in the following gallery:
544
 
545
 
546
  <Gallery />
@@ -552,7 +47,7 @@ You may reuse the base model text encoder for inference.
552
  ## Training settings
553
 
554
  - Training epochs: 0
555
- - Training steps: 20000
556
  - Learning rate: 1e-06
557
  - Effective batch size: 96
558
  - Micro-batch size: 12
@@ -634,7 +129,7 @@ You may reuse the base model text encoder for inference.
634
  ### dalle3
635
  - Repeats: 0
636
  - Total number of images: ~1126080
637
- - Total number of aspect buckets: 33
638
  - Resolution: 1.0 megapixels
639
  - Cropped: False
640
  - Crop style: None
@@ -642,7 +137,7 @@ You may reuse the base model text encoder for inference.
642
  ### sfwbooru
643
  - Repeats: 0
644
  - Total number of images: ~491344
645
- - Total number of aspect buckets: 63
646
  - Resolution: 1.0 megapixels
647
  - Cropped: False
648
  - Crop style: None
@@ -746,14 +241,14 @@ You may reuse the base model text encoder for inference.
746
  ### anatomy
747
  - Repeats: 5
748
  - Total number of images: ~16320
749
- - Total number of aspect buckets: 3
750
  - Resolution: 1.0 megapixels
751
  - Cropped: True
752
  - Crop style: random
753
  - Crop aspect: random
754
  ### bg20k-1024
755
  - Repeats: 0
756
- - Total number of images: ~89248
757
  - Total number of aspect buckets: 3
758
  - Resolution: 1.0 megapixels
759
  - Cropped: True
 
10
  - full
11
 
12
  inference: true
13
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
  # pixart-900m-1024-ft-v0.7-stage1
 
35
 
36
  Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
37
 
38
+
39
 
40
 
41
  <Gallery />
 
47
  ## Training settings
48
 
49
  - Training epochs: 0
50
+ - Training steps: 25000
51
  - Learning rate: 1e-06
52
  - Effective batch size: 96
53
  - Micro-batch size: 12
 
129
  ### dalle3
130
  - Repeats: 0
131
  - Total number of images: ~1126080
132
+ - Total number of aspect buckets: 32
133
  - Resolution: 1.0 megapixels
134
  - Cropped: False
135
  - Crop style: None
 
137
  ### sfwbooru
138
  - Repeats: 0
139
  - Total number of images: ~491344
140
+ - Total number of aspect buckets: 57
141
  - Resolution: 1.0 megapixels
142
  - Cropped: False
143
  - Crop style: None
 
241
  ### anatomy
242
  - Repeats: 5
243
  - Total number of images: ~16320
244
+ - Total number of aspect buckets: 1
245
  - Resolution: 1.0 megapixels
246
  - Cropped: True
247
  - Crop style: random
248
  - Crop aspect: random
249
  ### bg20k-1024
250
  - Repeats: 0
251
+ - Total number of images: ~89088
252
  - Total number of aspect buckets: 3
253
  - Resolution: 1.0 megapixels
254
  - Cropped: True
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e92f668f6fc8f511024efc1440e60dd7bc59d93019890b9cdc8cb75814481675
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1b3b8c77143c84eb53253880b39796a9b3fc8eb8aee516f47e78f47e676a8bf
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0816777cd0b7375a87399b93e6219b6633d31cfc3d8a1db65bd220c47f097f7a
3
  size 16100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd10ef0b678516aaa1e5acaa0da09115b61b861b0e8401dadbc73d743d7e20c
3
  size 16100
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6fd7bd8b5f2482c926826dec71eec3d1a641c7998c4e848e3e47591e0597
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb22b42a16f473d95c3bf4aaf904827e1c3996a556d6991010731e5ba62cbfe
3
  size 1000
training_state-anatomy.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-bg20k-1024.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-dalle3.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be45d75448f9a205b2f4e519502884a8b691b299d68ee809f9c923ef0673e50b
3
- size 8866406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26effa9343dce0c1d19088cca0d32ac1cbf0f0799b45a30e24b43ba63b0f53da
3
+ size 9564186
training_state-midjourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24a362d0d5b2a83f6bdefcb09531b321b71b2507e542ff37314f18ce0e5a0f03
3
- size 2839067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456327bb05867cfb3a7959b31cee6c6afdc8ce32272b176960502d648c2beb2a
3
+ size 3408287
training_state-mj-60.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-nijijourney-v6-520k-raw.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0469b9abbf903d7c264d7a20c23d01957fbb0dacd4fb533f8f1b2d250435412
3
- size 2996375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1468d4005de99023713d6ff4a5920e2d161dbac3ef47f3a6d638e44592f754
3
+ size 3561143
training_state-sfwbooru.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state-text-1mp.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 20000, "epoch_step": 20000, "epoch": 1, "exhausted_backends": ["guys", "signs", "nijijourney", "pixel-art", "bookcovers", "celebrities", "normalnudes", "gay", "moviecollection", "sports", "experimental", "ethnic", "cinemamix-1mp", "yoga", "architecture", "nsfw-1024", "shutterstock", "photo-aesthetics", "id-75k", "text-1mp"], "repeats": {"guys": 0, "signs": 0, "nijijourney": 0, "pixel-art": 0, "bookcovers": 0, "celebrities": 0, "normalnudes": 0, "gay": 0, "moviecollection": 0, "sports": 0, "experimental": 0, "ethnic": 0, "cinemamix-1mp": 0, "yoga": 0, "architecture": 0, "text-1mp": 0, "nsfw-1024": 0, "shutterstock": 0, "anatomy": 2, "photo-aesthetics": 0, "id-75k": 0}}
 
1
+ {"global_step": 25000, "epoch_step": 25000, "epoch": 1, "exhausted_backends": ["guys", "signs", "nijijourney", "pixel-art", "bookcovers", "celebrities", "normalnudes", "gay", "moviecollection", "sports", "experimental", "ethnic", "cinemamix-1mp", "yoga", "architecture", "nsfw-1024", "shutterstock", "photo-aesthetics", "id-75k", "text-1mp", "bg20k-1024"], "repeats": {"guys": 0, "signs": 0, "nijijourney": 0, "pixel-art": 0, "bookcovers": 0, "celebrities": 0, "normalnudes": 0, "gay": 0, "moviecollection": 0, "sports": 0, "experimental": 0, "ethnic": 0, "cinemamix-1mp": 0, "yoga": 0, "architecture": 0, "text-1mp": 0, "nsfw-1024": 0, "shutterstock": 0, "anatomy": 4, "photo-aesthetics": 0, "id-75k": 0, "bg20k-1024": 0}}
transformer/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "PixArtTransformer2DModel",
3
  "_diffusers_version": "0.30.0.dev0",
4
- "_name_or_path": "/home/ubuntu/training/output/lite-models/checkpoint-18500",
5
  "activation_fn": "gelu-approximate",
6
  "attention_bias": true,
7
  "attention_head_dim": 72,
 
1
  {
2
  "_class_name": "PixArtTransformer2DModel",
3
  "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "/home/ubuntu/training/output/lite-models/checkpoint-20000",
5
  "activation_fn": "gelu-approximate",
6
  "attention_bias": true,
7
  "attention_head_dim": 72,
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39c9737b0442b0d75f96a694634647176ed0121977d677c56a02ee7fa1707db2
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5c3bae3c7f3ceefcba3c63af327b323a633188f4a5dff6bbb11f009c24e3ecf
3
  size 1816969728