File size: 40,555 Bytes
9b90da9
279374e
9b90da9
 
 
 
 
86ea854
f756321
f4c66f7
7215045
9b90da9
 
86ea854
 
 
 
 
9b90da9
89c081e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
02a494e
86ea854
02a494e
7dfe473
4f86d21
 
02a494e
4f86d21
 
 
 
7dfe473
4f86d21
2a952b2
 
 
4f86d21
cb99a56
2a952b2
 
 
 
 
 
 
 
4f86d21
 
ba84d74
89c081e
ba84d74
 
 
cb99a56
 
 
89c081e
 
2a952b2
 
 
 
7dfe473
 
2a952b2
7dfe473
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a952b2
 
 
 
 
 
 
7dfe473
 
2a952b2
7dfe473
ba84d74
 
4f86d21
02a494e
 
 
 
 
4f86d21
 
02a494e
4f86d21
1aca0b8
86ea854
 
02a494e
4f86d21
7215045
0e27fad
86ea854
 
1aca0b8
86ea854
a98439b
0e27fad
7215045
0e27fad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7215045
0e27fad
 
 
 
 
 
 
 
 
 
 
 
 
7215045
0e27fad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35126fc
 
 
0e27fad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9b90da9
02a494e
9b90da9
02a494e
9b90da9
 
02a494e
7215045
4f86d21
 
9b90da9
 
02a494e
9b90da9
02a494e
 
4f86d21
f5ef562
 
 
ba84d74
4f86d21
02a494e
f4c66f7
4f86d21
ba84d74
02a494e
 
ba84d74
 
7215045
 
1aca0b8
7215045
 
ba84d74
 
 
 
b37a1ad
 
 
 
 
 
 
 
 
 
a98439b
b37a1ad
 
 
 
 
 
 
 
f5ef562
4f86d21
ba84d74
4f86d21
02a494e
f5ef562
4f86d21
02a494e
4f86d21
 
 
 
f5ef562
7215045
4f86d21
 
 
 
02a494e
4f86d21
f5ef562
 
 
 
 
 
4f86d21
02a494e
f4c66f7
9b90da9
ba84d74
 
 
 
02a494e
 
ba84d74
 
7215045
 
1aca0b8
7215045
 
ba84d74
 
b37a1ad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f5ef562
4f86d21
 
02a494e
f5ef562
4f86d21
02a494e
9b90da9
4f86d21
9b90da9
 
02a494e
7215045
4f86d21
9b90da9
 
 
02a494e
9b90da9
f5ef562
 
 
4f86d21
 
02a494e
7215045
 
1aca0b8
7215045
 
f5ef562
f4c66f7
1aca0b8
f4c66f7
7215045
f4c66f7
 
 
1aca0b8
7215045
f4c66f7
 
410e41f
f4c66f7
 
 
 
1aca0b8
7215045
1aca0b8
 
 
 
 
 
 
 
 
 
 
 
7215045
1aca0b8
7215045
 
1aca0b8
7215045
 
1aca0b8
7215045
 
1aca0b8
 
 
 
7215045
1aca0b8
7215045
1aca0b8
 
410e41f
 
 
 
1aca0b8
 
410e41f
 
 
 
1aca0b8
410e41f
 
1aca0b8
 
 
 
410e41f
 
 
1aca0b8
410e41f
 
1aca0b8
 
 
 
410e41f
 
 
1aca0b8
410e41f
 
1aca0b8
 
 
 
410e41f
 
 
1aca0b8
410e41f
 
1aca0b8
 
 
 
410e41f
 
 
1aca0b8
410e41f
 
1aca0b8
 
 
 
410e41f
7215045
1aca0b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9b90da9
02a494e
9b90da9
f4c66f7
2a952b2
9b90da9
 
1aca0b8
4f86d21
 
02a494e
fae6e99
9b90da9
 
 
 
fae6e99
02a494e
 
 
 
 
fae6e99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4f86d21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e782ff
4f86d21
 
 
 
1aca0b8
 
2a952b2
 
 
 
 
 
 
 
 
 
1aca0b8
2a952b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f756321
86ea854
 
 
 
 
 
 
 
 
4f86d21
86ea854
4f86d21
86ea854
4f86d21
86ea854
 
 
 
 
4f86d21
 
2a952b2
86ea854
 
 
 
 
 
 
 
 
 
 
2a952b2
86ea854
9b90da9
4f86d21
 
 
2a952b2
 
4f86d21
 
 
 
 
 
 
 
2a952b2
9b90da9
 
 
86ea854
 
 
 
7215045
f4c66f7
 
 
86ea854
 
410e41f
86ea854
4f86d21
02a494e
4f86d21
 
 
f4c66f7
4f86d21
86ea854
 
f4c66f7
02a494e
d0a3276
1e782ff
d0a3276
1e782ff
 
7215045
 
 
 
f4c66f7
4f86d21
9b90da9
86ea854
f4c66f7
9b90da9
 
1e782ff
02a494e
9b90da9
02a494e
 
9b90da9
4f86d21
f4c66f7
 
4f86d21
7dfe473
02a494e
4f86d21
 
f4c66f7
 
 
4f86d21
 
 
f5ef562
02a494e
9b90da9
 
35126fc
89c081e
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
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
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
import gradio as gr
from google import genai
from google.genai import types
from PIL import Image
from io import BytesIO
import base64
import os
import json
import random
import urllib.parse
import time

# Initialize the Google Generative AI client with the API key from environment variables
try:
    api_key = os.environ['GEMINI_API_KEY']
except KeyError:
    raise ValueError("Please set the GEMINI_API_KEY environment variable.")
client = genai.Client(api_key=api_key)

def clean_response_text(response_text):
    """
    Clean the API response by removing Markdown code block markers.
    
    Args:
        response_text (str): The raw response text from the API.
    
    Returns:
        str: The cleaned response text.
    """
    cleaned_text = response_text.strip()
    if cleaned_text.startswith("```json"):
        cleaned_text = cleaned_text[len("```json"):].strip()
    if cleaned_text.endswith("```"):
        cleaned_text = cleaned_text[:-len("```")].strip()
    return cleaned_text

def generate_ideas(user_input):
    """
    Generate a diverse set of ideas based on the user's input concept using the LLM.
    Validate the relevance of each idea using a cheaper LLM (gemini-2.0-flash-lite).
    
    Args:
        user_input (str): The user's input concept or idea (e.g., "blindfolded Rubik's Cube challenge").
    
    Returns:
        list: A list of ideas as strings.
    """
    # Step 1: Generate ideas using gemini-2.0-flash
    prompt = f"""
    The user has provided the concept: "{user_input}". You must generate 5 diverse and creative ideas for a TikTok video that are directly and explicitly related to "{user_input}".
    Each idea must clearly incorporate and focus on the core theme of "{user_input}" without deviating into unrelated topics.
    Each idea should be a short sentence describing a specific scene or concept.
    Return the response as a JSON object with a single key 'ideas' containing a list of 5 ideas.
    Ensure the response is strictly in JSON format.
    Example for "blindfolded Rubik's Cube challenge":
    {{"ideas": [
        "A blindfolded speedcubing competition with dramatic music",
        "A close-up of a person solving a Rubik's Cube blindfolded under a spotlight",
        "A time-lapse of a blindfolded Rubik's Cube solve with colorful lighting",
        "A blindfolded Rubik's Cube challenge in a futuristic setting",
        "A split-screen of two people racing to solve a Rubik's Cube blindfolded"
    ]}}
    """
    try:
        response = client.models.generate_content(
            model='gemini-2.0-flash',
            contents=[prompt],
            config=types.GenerateContentConfig(temperature=1.2)
        )
        print(f"Raw response for ideas: {response.text}")  # Debugging
        if not response.text or response.text.isspace():
            raise ValueError("Empty response from API")
        cleaned_text = clean_response_text(response.text)
        response_json = json.loads(cleaned_text)
        if 'ideas' not in response_json or not isinstance(response_json['ideas'], list) or len(response_json['ideas']) != 5:
            raise ValueError("Invalid JSON format: 'ideas' key missing, not a list, or incorrect length")
        
        ideas = response_json['ideas']
        
        # Step 2: Validate relevance of each idea using gemini-2.0-flash-lite
        for idea in ideas:
            validation_prompt = f"""
            Determine if the following idea for a TikTok video is related to the user's concept.
            User's concept: "{user_input}"
            Idea: "{idea}"
            Respond with a JSON object containing a single key 'is_related' with a boolean value (true or false).
            Example:
            {{"is_related": true}}
            """
            try:
                validation_response = client.models.generate_content(
                    model='gemini-2.0-flash-lite',
                    contents=[validation_prompt],
                    config=types.GenerateContentConfig(temperature=0.0)  # Low temperature for deterministic output
                )
                print(f"Validation response for idea '{idea}': {validation_response.text}")  # Debugging
                if not validation_response.text or validation_response.text.isspace():
                    raise ValueError("Empty validation response from API")
                cleaned_validation_text = clean_response_text(validation_response.text)
                validation_json = json.loads(cleaned_validation_text)
                if 'is_related' not in validation_json or not isinstance(validation_json['is_related'], bool):
                    raise ValueError("Invalid validation JSON format: 'is_related' key missing or not a boolean")
                
                if not validation_json['is_related']:
                    print(f"Idea '{idea}' is not related to '{user_input}'. Falling back to default ideas.")
                    return [
                        f"A dramatic {user_input} scene with cinematic lighting",
                        f"A close-up of {user_input} in a futuristic setting",
                        f"A high-energy {user_input} moment with vibrant colors",
                        f"A serene {user_input} scene with soft focus",
                        f"An action-packed {user_input} challenge with dynamic angles"
                    ]
            except Exception as e:
                print(f"Error validating idea '{idea}': {e}. Falling back to default ideas.")
                return [
                    f"A dramatic {user_input} scene with cinematic lighting",
                    f"A close-up of {user_input} in a futuristic setting",
                    f"A high-energy {user_input} moment with vibrant colors",
                    f"A serene {user_input} scene with soft focus",
                    f"An action-packed {user_input} challenge with dynamic angles"
                ]
        
        # All ideas are related, return them
        return ideas
    
    except Exception as e:
        print(f"Error generating ideas: {e}")
        return [
            f"A dramatic {user_input} scene with cinematic lighting",
            f"A close-up of {user_input} in a futuristic setting",
            f"A high-energy {user_input} moment with vibrant colors",
            f"A serene {user_input} scene with soft focus",
            f"An action-packed {user_input} challenge with dynamic angles"
        ]

def generate_item(user_input, ideas, generate_video=False, max_retries=3):
    """
    Generate a single feed item (image and optionally one video) using one of the ideas.
    
    Args:
        user_input (str): The user's input concept or idea.
        ideas (list): List of ideas to choose from.
        generate_video (bool): Whether to generate a video from the image.
        max_retries (int): Maximum number of retries for image generation per cycle.
    
    Returns:
        dict: A dictionary with 'text' (str), 'image_base64' (str), 'video_base64' (str or None), and 'ideas' (list).
    """
    video_base64 = None
    max_total_attempts = 3  # Maximum total attempts for combined image and video generation cycles
    
    total_attempts = 0
    while total_attempts < max_total_attempts:
        total_attempts += 1
        
        # Step 1: Generate an image (retry up to max_retries times)
        for image_attempt in range(max_retries):
            selected_idea = random.choice(ideas)
            prompt = f"""
            The user has provided the concept: "{user_input}". Based on this concept and the specific idea "{selected_idea}", create content for a TikTok video.
            Return a JSON object with two keys:
            - 'caption': A short, viral TikTok-style caption with hashtags that reflects "{user_input}".
            - 'image_prompt': A detailed image prompt for generating a high-quality visual scene, ensuring the theme of "{user_input}" is central.
            The image prompt should describe the scene vividly, specify a perspective and style, and ensure no text or letters are included.
            Ensure the response is strictly in JSON format.
            Example: {{"caption": "Blindfolded Rubik's Cube MAGIC! 🀯 #rubiks", "image_prompt": "A close-up view of a person solving a Rubik's Cube blindfolded, in a dramatic style, no text or letters"}}
            """
            try:
                response = client.models.generate_content(
                    model='gemini-2.0-flash',
                    contents=[prompt],
                    config=types.GenerateContentConfig(temperature=1.2)
                )
                print(f"Raw response for item (image attempt {image_attempt + 1}, total attempt {total_attempts}): {response.text}")  # Debugging
                if not response.text or response.text.isspace():
                    raise ValueError("Empty response from API")
                cleaned_text = clean_response_text(response.text)
                response_json = json.loads(cleaned_text)
                if 'caption' not in response_json or 'image_prompt' not in response_json:
                    raise ValueError("Invalid JSON format: 'caption' or 'image_prompt' key missing")
                text = response_json['caption']
                image_prompt = response_json['image_prompt']
            except Exception as e:
                print(f"Error generating item (image attempt {image_attempt + 1}, total attempt {total_attempts}): {e}")
                text = f"Amazing {user_input}! πŸ”₯ #{user_input.replace(' ', '')}"
                image_prompt = f"A vivid scene of {selected_idea} related to {user_input}, in a vibrant pop art style, no text or letters"

            # Attempt to generate the image
            try:
                imagen = client.models.generate_images(
                    model='imagen-3.0-generate-002',
                    prompt=image_prompt,
                    config=types.GenerateImagesConfig(
                        aspect_ratio="9:16",
                        number_of_images=1
                    )
                )
                if imagen.generated_images and len(imagen.generated_images) > 0:
                    generated_image = imagen.generated_images[0]
                    image = Image.open(BytesIO(generated_image.image.image_bytes))
                    # Ensure the image matches the desired aspect ratio (9:16 = 0.5625)
                    target_width = 360
                    target_height = int(target_width / 9 * 16)  # 9:16 aspect ratio
                    image = image.resize((target_width, target_height), Image.LANCZOS)
                    # Convert image to base64
                    buffered = BytesIO()
                    image.save(buffered, format="PNG")
                    img_str = base64.b64encode(buffered.getvalue()).decode()
                    break  # Successfully generated image, exit image retry loop
                else:
                    print(f"Image generation failed (image attempt {image_attempt + 1}, total attempt {total_attempts}): No images returned")
                    if image_attempt == max_retries - 1:
                        # Last image attempt in this cycle, use a gray placeholder if max total attempts not reached
                        if total_attempts == max_total_attempts:
                            image = Image.new('RGB', (360, 640), color='gray')
                            buffered = BytesIO()
                            image.save(buffered, format="PNG")
                            img_str = base64.b64encode(buffered.getvalue()).decode()
                            return {
                                'text': text,
                                'image_base64': img_str,
                                'video_base64': None,
                                'ideas': ideas
                            }
                        # Otherwise, select a new idea and retry image generation in the next cycle
                        continue
            except Exception as e:
                print(f"Error generating image (image attempt {image_attempt + 1}, total attempt {total_attempts}): {e}")
                if image_attempt == max_retries - 1:
                    # Last image attempt in this cycle
                    if total_attempts == max_total_attempts:
                        # Max total attempts reached, use a gray placeholder
                        image = Image.new('RGB', (360, 640), color='gray')
                        buffered = BytesIO()
                        image.save(buffered, format="PNG")
                        img_str = base64.b64encode(buffered.getvalue()).decode()
                        return {
                            'text': text,
                            'image_base64': img_str,
                            'video_base64': None,
                            'ideas': ideas
                        }
                    # Otherwise, select a new idea and retry image generation in the next cycle
                    continue

        # Step 2: Generate video if enabled (with retries using the same image)
        if generate_video:
            max_video_retries_per_image = 1  # Try video generation twice per image
            for video_attempt in range(max_video_retries_per_image):
                try:
                    # Base video prompt
                    video_prompt_base = f"""
                    The user concept is "{user_input}". Based on this and the scene: {image_prompt}, create a video.
                    Use a close-up shot with a slow dolly shot circling around the subject, 
                    using shallow focus on the main subject to emphasize details, in a realistic style with cinematic lighting.
                    """
                    # Modify the prompt slightly for each retry
                    if video_attempt == 0:
                        video_prompt = video_prompt_base
                    else:
                        video_prompt = f"""
                        The user concept is "{user_input}". Based on this and a simplified scene: {image_prompt}, create a video.
                        Use a static close-up shot of the subject in a realistic style.
                        """

                    print(f"Attempting video generation (video attempt {video_attempt + 1}, total attempt {total_attempts}): {video_prompt}")
                    operation = client.models.generate_videos(
                        model="veo-2.0-generate-001",
                        prompt=video_prompt,
                        image=generated_image.image,
                        config=types.GenerateVideosConfig(
                            aspect_ratio="9:16",
                            number_of_videos=1,
                            duration_seconds=8,
                            negative_prompt="blurry, low quality, text, letters"
                        )
                    )
                    # Wait for video to generate
                    while not operation.done:
                        time.sleep(20)
                        operation = client.operations.get(operation)
                    
                    # Enhanced error handling for video generation response
                    if operation.error:
                        raise ValueError(f"Video generation operation failed with error: {operation.error.message}")
                    if operation.response is None:
                        raise ValueError("Video generation operation failed: No response")
                    if not hasattr(operation.response, 'generated_videos') or operation.response.generated_videos is None:
                        raise ValueError("Video generation operation failed: No generated_videos in response")
                    
                    # Process the single generated video
                    if len(operation.response.generated_videos) > 0:
                        video = operation.response.generated_videos[0]
                        if video is None or not hasattr(video, 'video'):
                            raise ValueError("Video is invalid or missing video data")
                        fname = 'with_image_input.mp4'
                        print(f"Generated video: {fname}")
                        # Download the video and get the raw bytes
                        video_data = client.files.download(file=video.video)
                        # Ensure video_data is in bytes
                        if isinstance(video_data, bytes):
                            video_bytes = video_data
                        else:
                            # If video_data is a file-like object, read the bytes
                            video_buffer = BytesIO()
                            for chunk in video_data:
                                video_buffer.write(chunk)
                            video_bytes = video_buffer.getvalue()
                        # Encode the video bytes as base64
                        video_base64 = base64.b64encode(video_bytes).decode()
                        # Successfully generated video, return the result
                        return {
                            'text': text,
                            'image_base64': img_str,
                            'video_base64': video_base64,
                            'ideas': ideas
                        }
                    else:
                        raise ValueError("No video was generated")
                except Exception as e:
                    print(f"Error generating video (video attempt {video_attempt + 1}, total attempt {total_attempts}): {e}")
                    if video_attempt == max_video_retries_per_image - 1:
                        if total_attempts == max_total_attempts:
                            print("Max total attempts reached. Proceeding without video.")
                            video_base64 = None
                            return {
                                'text': text,
                                'image_base64': img_str,
                                'video_base64': video_base64,
                                'ideas': ideas
                            }
                        # Video generation failed with this image, break to outer loop to try a new image
                        print(f"Video generation failed after {max_video_retries_per_image} attempts with this image. Selecting a new idea and generating a new image.")
                        break
                    continue  # Retry video generation with the same image but a modified prompt
        
        # If video generation is not enabled or succeeded, return the result
        return {
            'text': text,
            'image_base64': img_str,
            'video_base64': video_base64,
            'ideas': ideas
        }

    # If max total attempts reached without success, use a gray placeholder image
    print("Max total attempts reached without successful image generation. Using placeholder.")
    image = Image.new('RGB', (360, 640), color='gray')
    buffered = BytesIO()
    image.save(buffered, format="PNG")
    img_str = base64.b64encode(buffered.getvalue()).decode()
    return {
        'text': f"Amazing {user_input}! πŸ”₯ #{user_input.replace(' ', '')}",
        'image_base64': img_str,
        'video_base64': None,
        'ideas': ideas
    }

def start_feed(user_input, generate_video, current_index, feed_items):
    """
    Start or update the feed based on the user input.
    
    Args:
        user_input (str): The user's input concept or idea.
        generate_video (bool): Whether to generate a video.
        current_index (int): The current item index.
        feed_items (list): The current list of feed items.
    
    Returns:
        tuple: (current_user_input, current_index, feed_items, html_content, share_links, is_loading)
    """
    if not user_input.strip():
        user_input = "trending"
    
    # Update current_user_input with the new user_input
    current_user_input = user_input
    
    # Set loading state
    is_loading = True
    html_content = generate_html([], False, 0, user_input, is_loading)
    share_links = ""

    try:
        ideas = generate_ideas(user_input)
        item = generate_item(user_input, ideas, generate_video=generate_video)
        feed_items = [item]
        current_index = 0
        share_links = generate_share_links(
            item['image_base64'],
            item['video_base64'],
            item['text']
        )
    except Exception as e:
        print(f"Error in start_feed: {e}")
        feed_items = []
        current_index = 0
        html_content = """
        <div style="
            display: flex;
            flex-direction: column;
            align-items: center;
            justify-content: center;
            max-width: 360px;
            margin: 0 auto;
            background-color: #000;
            height: 640px;
            border: 1px solid #333;
            border-radius: 10px;
            color: white;
            font-family: Arial, sans-serif;
        ">
            <p>Error generating content. Please try again!</p>
        </div>
        """
        is_loading = False
        return current_user_input, current_index, feed_items, html_content, share_links, is_loading

    # Set loading state to False and update UI
    is_loading = False
    html_content = generate_html(feed_items, False, current_index, user_input, is_loading)
    return current_user_input, current_index, feed_items, html_content, share_links, is_loading

def load_next(user_input, generate_video, current_index, feed_items):
    """
    Load the next item in the feed.
    
    Args:
        user_input (str): The user's input concept or idea (updated from the textbox).
        generate_video (bool): Whether to generate a video.
        current_index (int): The current item index.
        feed_items (list): The current list of feed items.
    
    Returns:
        tuple: (current_user_input, current_index, feed_items, html_content, share_links, is_loading)
    """
    # Update current_user_input with the latest user_input from the textbox
    current_user_input = user_input if user_input.strip() else "trending"
    
    # Use current_user_input for generating the next item
    user_input = current_user_input
    
    is_loading = True
    html_content = generate_html(feed_items, False, current_index, user_input, is_loading)
    share_links = ""

    try:
        if current_index + 1 < len(feed_items):
            current_index += 1
        else:
            ideas = feed_items[-1]['ideas'] if feed_items else generate_ideas(user_input)
            new_item = generate_item(user_input, ideas, generate_video=generate_video)
            feed_items.append(new_item)
            current_index = len(feed_items) - 1
        share_links = generate_share_links(
            feed_items[current_index]['image_base64'],
            feed_items[current_index]['video_base64'],
            feed_items[current_index]['text']
        )
    except Exception as e:
        print(f"Error in load_next: {e}")
        html_content = """
        <div style="
            display: flex;
            flex-direction: column;
            align-items: center;
            justify-content: center;
            max-width: 360px;
            margin: 0 auto;
            background-color: #000;
            height: 640px;
            border: 1px solid #333;
            border-radius: 10px;
            color: white;
            font-family: Arial, sans-serif;
        ">
            <p>Error generating content. Please try again!</p>
        </div>
        """
        is_loading = False
        return current_user_input, current_index, feed_items, html_content, share_links, is_loading

    is_loading = False
    html_content = generate_html(feed_items, False, current_index, user_input, is_loading)
    return current_user_input, current_index, feed_items, html_content, share_links, is_loading

def load_previous(user_input, generate_video, current_index, feed_items):
    """
    Load the previous item in the feed.
    
    Args:
        user_input (str): The user's input concept or idea.
        generate_video (bool): Whether to generate a video (not used here).
        current_index (int): The current item index.
        feed_items (list): The current list of feed items.
    
    Returns:
        tuple: (current_user_input, current_index, feed_items, html_content, share_links, is_loading)
    """
    # Update current_user_input with the latest user_input
    current_user_input = user_input if user_input.strip() else "trending"
    
    if current_index > 0:
        current_index -= 1
    html_content = generate_html(feed_items, False, current_index, user_input, False)
    share_links = generate_share_links(
        feed_items[current_index]['image_base64'],
        feed_items[current_index]['video_base64'],
        feed_items[current_index]['text']
    )
    return current_user_input, current_index, feed_items, html_content, share_links, False

def generate_share_links(image_base64, video_base64, caption):
    """
    Generate share links for social media platforms with download links for image and video.
    
    Args:
        image_base64 (str): The base64-encoded image data.
        video_base64 (str or None): The base64-encoded video data (single video).
        caption (str): The caption to share.
    
    Returns:
        str: HTML string with share links and download instructions.
    """
    image_data_url = f"data:image/png;base64,{image_base64}"
    encoded_caption = urllib.parse.quote(caption)

    # Generate download links for image and video (if available)
    download_links = f"""
        <p style="text-align: center; margin-bottom: 10px;">Download the media to share:</p>
        <div style="display: flex; flex-wrap: wrap; justify-content: center; gap: 8px; margin-bottom: 15px;">
            <a href="{image_data_url}" download="feed_item.png" style="
                background-color: #4CAF50;
                color: white;
                padding: 8px 16px;
                border-radius: 5px;
                text-decoration: none;
                font-size: 14px;
                font-weight: bold;
                transition: background-color 0.3s;
            " onmouseover="this.style.backgroundColor='#45a049'" onmouseout="this.style.backgroundColor='#4CAF50'">Download Image</a>
    """
    if video_base64:  # Only include video download link if a video exists
        video_data_url = f"data:video/mp4;base64,{video_base64}"
        download_links += f"""
            <a href="{video_data_url}" download="feed_video.mp4" style="
                background-color: #4CAF50;
                color: white;
                padding: 8px 16px;
                border-radius: 5px;
                text-decoration: none;
                font-size: 14px;
                font-weight: bold;
                transition: background-color 0.3s;
            " onmouseover="this.style.backgroundColor='#45a049'" onmouseout="this.style.backgroundColor='#4CAF50'">Download Video</a>
        """
    download_links += "</div>"

    # Generate share links for social media platforms
    share_links = """
        <div style="
            display: flex;
            flex-wrap: wrap;
            justify-content: center;
            gap: 8px;
            margin-bottom: 15px;
        ">
            <a href="https://www.tiktok.com/upload?caption={caption}" target="_blank" style="
                background-color: #00f2ea;
                color: #000;
                padding: 8px 16px;
                border-radius: 5px;
                text-decoration: none;
                font-size: 14px;
                font-weight: bold;
                transition: background-color 0.3s;
            " onmouseover="this.style.backgroundColor='#00d9d1'" onmouseout="this.style.backgroundColor='#00f2ea'">Share on TikTok</a>
            <a href="https://www.instagram.com/?caption={caption}" target="_blank" style="
                background-color: #e1306c;
                color: white;
                padding: 8px 16px;
                border-radius: 5px;
                text-decoration: none;
                font-size: 14px;
                font-weight: bold;
                transition: background-color 0.3s;
            " onmouseover="this.style.backgroundColor='#c72b5e'" onmouseout="this.style.backgroundColor='#e1306c'">Share on Instagram</a>
            <a href="https://www.facebook.com/sharer/sharer.php?quote={caption}" target="_blank" style="
                background-color: #4267b2;
                color: white;
                padding: 8px 16px;
                border-radius: 5px;
                text-decoration: none;
                font-size: 14px;
                font-weight: bold;
                transition: background-color 0.3s;
            " onmouseover="this.style.backgroundColor='#395a9d'" onmouseout="this.style.backgroundColor='#4267b2'">Share on Facebook</a>
            <a href="https://twitter.com/intent/tweet?text={caption}" target="_blank" style="
                background-color: #1da1f2;
                color: white;
                padding: 8px 16px;
                border-radius: 5px;
                text-decoration: none;
                font-size: 14px;
                font-weight: bold;
                transition: background-color 0.3s;
            " onmouseover="this.style.backgroundColor='#1a91da'" onmouseout="this.style.backgroundColor='#1da1f2'">Share on X</a>
            <a href="https://pinterest.com/pin/create/button/?description={caption}" target="_blank" style="
                background-color: #bd081c;
                color: white;
                padding: 8px 16px;
                border-radius: 5px;
                text-decoration: none;
                font-size: 14px;
                font-weight: bold;
                transition: background-color 0.3s;
            " onmouseover="this.style.backgroundColor='#a30718'" onmouseout="this.style.backgroundColor='#bd081c'">Share on Pinterest</a>
        </div>
    """

    # Add YouTube Shorts share button if a video is available
    youtube_share = ""
    if video_base64:  # Only show YouTube Shorts share button if a video is generated
        youtube_share = f"""
            <div style="
                display: flex;
                justify-content: center;
                margin-top: 10px;
            ">
                <a href="https://www.youtube.com/upload?description={caption}" target="_blank" style="
                    background-color: #ff0000;
                    color: white;
                    padding: 8px 16px;
                    border-radius: 5px;
                    text-decoration: none;
                    font-size: 14px;
                    font-weight: bold;
                    transition: background-color 0.3s;
                " onmouseover="this.style.backgroundColor='#e60000'" onmouseout="this.style.backgroundColor='#ff0000'">Share to YouTube as a Short</a>
            </div>
        """

    return f"""
    <div style="
        display: flex;
        flex-direction: column;
        align-items: center;
        gap: 10px;
        margin-top: 10px;
        color: white;
        font-family: Arial, sans-serif;
    ">
        {download_links}
        {share_links}
        {youtube_share}
    </div>
    """.format(caption=encoded_caption)

def generate_html(feed_items, scroll_to_latest=False, current_index=0, user_input="", is_loading=False):
    """
    Generate an HTML string to display the current feed item with click navigation.
    Displays a video if available, otherwise falls back to the image.
    
    Args:
        feed_items (list): List of dictionaries containing 'text', 'image_base64', and 'video_base64'.
        scroll_to_latest (bool): Whether to auto-scroll to the latest item (not used here).
        current_index (int): The index of the item to display.
        user_input (str): The user's input concept or idea for loading messages.
        is_loading (bool): Whether the feed is currently loading.
    
    Returns:
        str: HTML string representing the feed.
    """
    loading_messages = [
        f"Cooking up a {user_input} masterpiece... 🍳",
        f"Snapping a vibrant {user_input} moment... πŸ“Έ",
        f"Creating a {user_input} vibe that pops... ✨",
        f"Getting that perfect {user_input} shot... πŸŽ₯",
        f"Bringing {user_input} to life... 🌟"
    ]

    if is_loading:
        return f"""
        <div id="feed-container" style="
            display: flex;
            flex-direction: column;
            align-items: center;
            justify-content: center;
            max-width: 360px;
            margin: 0 auto;
            background-color: #000;
            height: 640px;
            border: 1px solid #333;
            border-radius: 10px;
            color: white;
            font-family: Arial, sans-serif;
            position: relative;
        ">
            <div id="loading-message" style="
                font-size: 18px;
                font-weight: bold;
                text-align: center;
                margin-bottom: 20px;
                text-shadow: 1px 1px 2px rgba(0,0,0,0.5);
            ">
                {loading_messages[0]}
            </div>
            <div style="
                width: 80%;
                height: 10px;
                background-color: #333;
                border-radius: 5px;
                overflow: hidden;
            ">
                <div style="
                    width: 0%;
                    height: 100%;
                    background: linear-gradient(to right, #ff2d55, #ff5e78);
                    animation: loading 2s infinite;
                "></div>
            </div>
            <style>
                @keyframes loading {{
                    0% {{ width: 0%; }}
                    50% {{ width: 100%; }}
                    100% {{ width: 0%; }}
                }}
            </style>
            <script>
                const messages = {json.dumps(loading_messages)};
                let currentMessageIndex = 0;
                const messageElement = document.getElementById('loading-message');
                function rotateMessages() {{
                    currentMessageIndex = (currentMessageIndex + 1) % messages.length;
                    messageElement.textContent = messages[currentMessageIndex];
                }}
                setInterval(rotateMessages, 2000);
            </script>
        </div>
        """

    if not feed_items or current_index >= len(feed_items):
        return """
        <div style="
            display: flex;
            flex-direction: column;
            align-items: center;
            justify-content: center;
            max-width: 360px;
            margin: 0 auto;
            background-color: #000;
            height: 640px;
            border: 1px solid #333;
            border-radius: 10px;
            color: white;
            font-family: Arial, sans-serif;
        ">
            <p>Enter a concept or idea to start your feed!</p>
        </div>
        """

    item = feed_items[current_index]
    # Check if there is a video to display
    if item['video_base64']:
        media_element = f"""
            <video id="feed-video" controls style="
                width: 100%;
                height: 100%;
                object-fit: cover;
                position: absolute;
                top: 0;
                left: 0;
                z-index: 1;
            ">
                <source src="data:video/mp4;base64,{item['video_base64']}" type="video/mp4">
                Your browser does not support the video tag.
            </video>
        """
    else:
        # Fallback to image if no video is available
        media_element = f"""
            <img id="feed-image" src="data:image/png;base64,{item['image_base64']}" style="
                width: 100%;
                height: 100%;
                object-fit: cover;
                position: absolute;
                top: 0;
                left: 0;
                z-index: 1;
            ">
        """

    html_str = f"""
    <div id="feed-container" style="
        display: flex;
        flex-direction: column;
        align-items: center;
        max-width: 360px;
        margin: 0 auto;
        background-color: #000;
        height: 640px;
        border: 1px solid #333;
        border-radius: 10px;
        position: relative;
    ">
        <div class="feed-item" style="
            width: 100%;
            height: 100%;
            position: relative;
            display: flex;
            flex-direction: column;
            justify-content: flex-end;
            overflow: hidden;
            cursor: pointer;
        " onclick="handleClick(event)">
            {media_element}
            <div style="
                position: relative;
                z-index: 2;
                background: linear-gradient(to top, rgba(0,0,0,0.7), transparent);
                padding: 20px;
                color: white;
                font-family: Arial, sans-serif;
                font-size: 18px;
                font-weight: bold;
                text-shadow: 1px 1px 2px rgba(0,0,0,0.5);
            ">
                {item['text']}
            </div>
        </div>
    </div>
    <script>
        function handleClick(event) {{
            const media = document.getElementById('feed-video') || document.getElementById('feed-image');
            const rect = media.getBoundingClientRect();
            const clickX = event.clientX - rect.left;
            const width = rect.width;
            if (clickX > width * 0.75) {{
                document.getElementById('previous-button').click();
            }}
        }}
    </script>
    <button id="previous-button" style="display: none;" onclick="document.getElementById('previous-button').click()"></button>
    """
    return html_str

# Define the Gradio interface
with gr.Blocks(
    css="""
        body { background-color: #000; color: #fff; font-family: Arial, sans-serif; }
        .gradio-container { max-width: 400px; margin: 0 auto; padding: 10px; }
        input, select, button, .gr-checkbox { border-radius: 5px; background-color: #222; color: #fff; border: 1px solid #444; }
        button { background-color: #ff2d55; border: none; }
        button:hover { background-color: #e0264b; }
        .gr-button { width: 100%; margin-top: 10px; }
        .gr-form { background-color: #111; padding: 15px; border-radius: 10px; }
    """,
    title="Create Your Feed"
) as demo:
    # State variables
    current_user_input = gr.State(value="")
    current_index = gr.State(value=0)
    feed_items = gr.State(value=[])
    is_loading = gr.State(value=False)
    share_links = gr.State(value="")

    # Input section
    with gr.Column(elem_classes="gr-form"):
        gr.Markdown("### Create Your Feed")
        user_input = gr.Textbox(
            label="Enter Concept or Ideas",
            value="",
            placeholder="e.g., sushi adventure, neon tech",
            submit_btn=False
        )
        generate_video_checkbox = gr.Checkbox(
            label="Generate Video (may take longer)",
            value=False
        )
        magic_button = gr.Button("✨ Generate Next Item", elem_classes="gr-button")

    # Output display
    feed_html = gr.HTML()
    share_html = gr.HTML(label="Share this item:")

    # Event handlers
    # Handle Enter keypress in the concept input
    user_input.submit(
        fn=start_feed,
        inputs=[user_input, generate_video_checkbox, current_index, feed_items],
        outputs=[current_user_input, current_index, feed_items, feed_html, share_html, is_loading]
    )

    # Handle magic button click to generate next item
    magic_button.click(
        fn=load_next,
        inputs=[user_input, generate_video_checkbox, current_index, feed_items],
        outputs=[current_user_input, current_index, feed_items, feed_html, share_html, is_loading]
    )

    # Hidden button for previous item navigation
    previous_button = gr.Button("Previous", elem_id="previous-button", visible=False)

    # Handle click to go to previous item
    previous_button.click(
        fn=load_previous,
        inputs=[user_input, generate_video_checkbox, current_index, feed_items],
        outputs=[current_user_input, current_index, feed_items, feed_html, share_html, is_loading]
    )

# Launch the app
demo.launch()