File size: 14,075 Bytes
3d205c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
*Note: commited intentionally for educational purposes

Given the following code snippets, and the list of image generation models with example API requests.

[TASK]
<|gradio_app_instructions|>
Your task is to complete the code snippets by adding the necessary code to make the API requests.
The steps are really simple; user inputs any prompt; for example; "A girl with short pink hair wearing a oversize hoodie.". 
Then, the prompt will be passed to the enhance_prompt function to enhance the prompt.
The enhanced prompt will be passed to the image generation model to generate the image. 
However, here user will select which image generation model to use.
The image will be generated and displayed to the user.

[UI]
<|gradio_app_ui|>
List the image generation models on the left side of the UI.
Make image generation model selection as checkbox.
Display as much Image Output as user selected image generation models.
For example; we have 13 image generation models, and user selected 3 models using checkbox.
After user enters the prompt. The image will be generated using 3 models and displayed to the user.

[DOCS]
Feel free to use Gradio documentation to complete the task.

[CODE]
<|start_of_code_snippet|>
import gradio as gr
from openai import OpenAI
from dotenv import load_dotenv
import os

load_dotenv()

client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

# i will update [SYSTEM_PROMPT] myself, ignore for now.
SYSTEM_PROMPT = """
<i will update myself, ignore for now.>
"""

# general function to enhance prompt
# user prompt will be passed as an argument
# this is very first step after user input
# then enhanced prompt will be passed to the image generation model
def enhance_prompt(user_prompt) -> str:
    completion = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {"role": "system", "content": SYSTEM_PROMPT},
            {"role": "user", "content": user_prompt}
        ]
    )

    ep = completion.choices[0].message.content
    print('Enhanced Prompt: ' ,ep)

    return ep

# title should be centered
# gradio app title
title = "Let's Generate Cutesy AI Sticker!"

# align project_website and paper_url center and in one row
project_website = "https://ai-sticker-maker.vercel.app/"
paper_url = "https://rebrand.ly/aistickermakerpaper"

# call to action text should be also centered
call_to_action_text = "Please consider starring ⭐️ the [GitHub Repo](https://github.com/abdibrokhim/ai-sticker-maker) if you find this useful!"

# to build from scratch, you can follow the tutorial on medium and dev.to
tutorial_on_medium_link = "https://medium.com/@abdibrokhim/building-an-ai-sticker-maker-platform-with-ai-ml-api-next-js-8b0767a7e159"
tutorial_on_dev_link = "https://dev.to/abdibrokhim/building-an-ai-sticker-maker-platform-with-aiml-api-nextjs-react-and-tailwind-css-using-openai-gpt-4o-and-dalle-3-models-46ip"

# general input placeholder
placeholder = "A girl with short pink hair wearing a oversize hoodie..."

<|list_of_image_generation_models|>
# list of image generation models with example API requests

# 1. stable-diffusion-v35-large
# import requests
# import base64
# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "stable-diffusion-v35-large",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 2. flux-pro/v1.1
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "flux-pro/v1.1",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 3. dall-e-3
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "dall-e-3",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 4. stable-diffusion-v3-medium
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "stable-diffusion-v3-medium",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 5. runwayml/stable-diffusion-v1-5
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "runwayml/stable-diffusion-v1-5",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 6. stabilityai/stable-diffusion-xl-base-1.0
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "stabilityai/stable-diffusion-xl-base-1.0",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 7. stabilityai/stable-diffusion-2-1
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "stabilityai/stable-diffusion-2-1",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 8. SG161222/Realistic_Vision_V3.0_VAE
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "SG161222/Realistic_Vision_V3.0_VAE",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 9. prompthero/openjourney
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "prompthero/openjourney",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 10. wavymulder/Analog-Diffusion
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "wavymulder/Analog-Diffusion",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 11. flux-pro
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "flux-pro",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 12. flux-realism
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "flux-realism",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

# 13. dall-e-2
# import requests
# import base64


# def main():
#     headers = {
#         "Authorization": "Bearer <YOUR_API_KEY>",
#     }

#     payload = {
#         "prompt": "Hyperrealistic art featuring a cat in costume.",
#         "model": "dall-e-2",
#     }

#     response = requests.post(
#         "https://api.aimlapi.com/images/generations", headers=headers, json=payload
#     )

#     image_base64 = response.json()["output"]["choices"][0]["image_base64"]
#     image_data = base64.b64decode(image_base64)

#     with open("./image.png", "wb") as file:
#         file.write(image_data)


# main()

<|end_of_code_snippet|>



Refactor examples part. Follow this steps:
1. make 4 columns: 1) user prompt, 2) enhanced prompt, 3) generated image, 4) ai model
2. rewrite column labels also.
3. better make dictionary for each entry. so i can easily add more examples.

here is example table info:
[entry 1:]
user prompt: "An adorable kitten playing with a ball of yarn"
enhanced prompt: "An adorable, fluffy kitten with big, sparkling eyes and playful whiskers, tumbling around with a vibrant ball of yarn. The kitten's fur is a soft blend of warm creams and greys, giving it a cuddly, huggable appearance. Its expression is full of joy and mischief, with a tiny pink tongue playfully sticking out. The ball of yarn is a bright and cheerful red, unraveling with dynamic loops and curls. The style is chibi-like and sticker-friendly, with minimalistic lines and gentle shading. The background is a simple, soft pastel color with tiny floating paw prints, enhancing the cute and playful theme."
generated image: "./generated-images/cat-and-yarn.jpeg"
ai model: "dall-e-3"

[entry 2:]
user prompt: "A cutesy cat eating ice cream under a rainbow"
enhanced prompt: "A playful, cartoonish cat with big, sparkling eyes and soft, rounded features, happily licking a colorful ice cream cone. The cat has fluffy fur, pastel colors—like soft cream, peach, or light gray—and tiny pink blush on its cheeks for added charm. It sits contentedly under a bright, arched rainbow with soft, blended hues. Small, floating sparkles and tiny hearts surround the cat and ice cream to add a touch of magic. The ice cream cone has multiple scoops in fun, bright colors like pink, blue, and mint green, making the whole scene feel adorable and sweet, perfect for a cute sticker!"
generated image: "./generated-images/cat-and-icecream.jpeg"
ai model: "dall-e-3"

[entry 3:]
user prompt: "A girl with short pink+black hair wearing a pink shirt."
enhanced prompt: "An adorable chibi-style character with a soft, cozy look. She has a short, wavy bob hairstyle in gradient shades of gray with delicate highlights that sparkle. Her large, expressive brown eyes have a gentle shine, and her cheeks are lightly blushed, adding a touch of warmth. She wears an off-shoulder, cream-colored sweater, giving a relaxed and comforting vibe. The background is a soft pastel gradient in warm beige and cream tones, decorated with small, floating sparkles and star shapes for a magical effect. The overall style is cute, minimalist, and sticker-friendly."
generated image: "./generated-images/girl-with-white-grey-hair.png"
ai model: "dall-e-3"