Create images for blogs - Stability AI

lib/gpt_providers/text_to_image_generation/gen_stabl_diff_img.py

@@ -1,41 +1,56 @@
-from PIL import Image
-import requests
-
 # Ensure you sign up for an account to obtain an API key:
 # https://platform.stability.ai/
 # Your API key can be found here after account creation:
 # https://platform.stability.ai/account/keys
 
+import base64
+import os
+import requests
+from PIL import Image
+from io import BytesIO
+
+from .save_image import save_generated_image
+
 
 def generate_stable_diffusion_image(prompt):
-    """
-    Generate images using Stable Diffusion API based on a given prompt.
-
-    Args:
-        prompt (str): The prompt to generate the image.
-        image_dir (str): The directory where the image will be saved.
-
-    Raises:
-        Warning: If the adult content classifier is triggered.
-        Exception: For any issues during image generation or saving.
-    """
-    api_key = os.getenv('STABILITY_API_KEY')
-
+    engine_id = "stable-diffusion-xl-1024-v1-0"
+    api_host = os.getenv('API_HOST', 'https://api.stability.ai')
+    api_key = os.getenv("STABILITY_API_KEY")
+    
+    if api_key is None:
+        raise Exception("Missing Stability API key.")
+    
     response = requests.post(
-        f"https://api.stability.ai/v2beta/stable-image/generate/sd3",
+        f"{api_host}/v1/generation/{engine_id}/text-to-image",
         headers={
-            "authorization": f"Bearer {api_key}",
-            "accept": "image/*"
+            "Content-Type": "application/json",
+            "Accept": "application/json",
+            "Authorization": f"Bearer {api_key}"
         },
-        files={"none": ''},
-        data={
-            "prompt": prompt,
-            "output_format": "webp",
+        json={
+            "text_prompts": [
+                {
+                    "text": prompt
+                }
+            ],
+            "cfg_scale": 7,
+            "height": 1024,
+            "width": 1024,
+            "samples": 1,
+            "steps": 30,
         },
     )
+    
+    if response.status_code != 200:
+        raise Exception("Non-200 response: " + str(response.text))
+    
+    data = response.json()
+    save_generated_image(data)
 
-    if response.status_code == 200:
-        with open("./dog-wearing-glasses.jpeg", 'wb') as file:
-            file.write(response.content)
-    else:
-        raise Exception(str(response.json()))
+    for i, image in enumerate(data["artifacts"]):
+        # Decode base64 image data
+        img_data = base64.b64decode(image["base64"])
+        # Open image using PIL
+        img = Image.open(BytesIO(img_data))
+        # Display the image
+        img.show()  

lib/gpt_providers/text_to_image_generation/main_generate_image_from_prompt.py

@@ -23,9 +23,10 @@ logger.add(sys.stdout,
 #from .gen_dali2_images
 from .gen_dali3_images import generate_dalle3_images
 from .gen_stabl_diff_img import generate_stable_diffusion_image
+from ..text_generation.main_text_generation import llm_text_gen
 
 
-def generate_image(user_prompt, image_engine="dalle3"):
+def generate_image(user_prompt, image_engine):
     """
     The generation API endpoint creates an image based on a text prompt.
 
@@ -41,15 +42,17 @@ def generate_image(user_prompt, image_engine="dalle3"):
     Must be one of "url" or "b64_json". Defaults to "url".
     --> user (str): A unique identifier representing your end-user, which will help OpenAI to monitor and detect abuse.
     """
-    img_prompt = generate_img_prompt(user_prompt) 
-    # call the OpenAI API to generate image from prompt.
-    logger.info(f"Calling image.generate with prompt: {img_prompt}")
-
-    if 'Dalle3' in image_engine:
-        image_stored_at = generate_dalle3_images(img_prompt)
-    elif 'Stable Diffusion' in image_engine:
-        image_stored_at = generate_stable_diffusion_image(img_prompt)
-
+    try:
+        img_prompt = generate_img_prompt(user_prompt)
+        if 'Dalle3' in image_engine:
+            logger.info(f"Calling Dalle3 text-to-image with prompt: {img_prompt}")
+            image_stored_at = generate_dalle3_images(img_prompt)
+        elif 'Stability-Stable-Diffusion' in image_engine:
+            logger.info(f"Calling Stable diffusion text-to-image with prompt: \n{img_prompt}")
+            print("\n\n")
+            image_stored_at = generate_stable_diffusion_image(img_prompt)
+    except Exception as err:
+        logger.error(f"Failed to generate Image: {err}")
     return image_stored_at
 
 
@@ -57,17 +60,16 @@ def generate_img_prompt(user_prompt):
     """
     Given prompt, this functions generated a prompt for image generation.
     """
-    # I want you to act as an artist advisor providing advice on various art styles such tips on utilizing 
-    # light & shadow effects effectively in painting, shading techniques while sculpting etc.
-    # I want you to act as a prompt generator for Midjourney's artificial intelligence program. 
-    # Your job is to provide detailed and creative descriptions that will inspire unique and interesting images from the AI. 
-    # Here is your first prompt: ""
-    logger.info(f"Generate image prompt for : {user_prompt}")
-    prompt = f"""As an educationist and expert infographic artist, your tasked to create prompts that will be used for image generation.
-            Craft prompt for Openai Dall-e image generation program. Clearly describe the given text to represent it as image.
-            Make sure to avoid common image generation mistakes. 
-            Advice for creating prompt for image from the given text(no more than 150 words).
-            Reply with only one answer and no descrition. Generate image prompt for the below text.
-            Text: {user_prompt}"""
-    response = (prompt)
+    prompt = f"""
+        As an expert prompt engineer and artist, I will provide you with 'text' for creating image.
+        I want you to act as a prompt generator for AI text to image models(no more than 150 words).
+        \n
+        Choose from various art styles, utilize light & shadow effects etc.
+        Make sure to avoid common image generation mistakes.
+        Reply with only one answer, no descrition and in plaintext.
+        Make sure your prompt is detailed and creative descriptions that will inspire unique and interesting images from the AI. 
+        
+        \n\ntext:{user_prompt} """
+
+    response = llm_text_gen(prompt)
     return response

lib/gpt_providers/text_to_image_generation/save_image.py

@@ -1,35 +1,28 @@
+import base64
 import datetime
 import os
 import requests
 from PIL import Image
 import logging
 
-def save_generated_image(img_generation_response, image_dir):
+def save_generated_image(img_generation_response):
     """
     Save generated images for blog, ensuring unique names for SEO.
     """
     logging.basicConfig(level=logging.INFO)
     logger = logging.getLogger(__name__)
 
-    generated_image_name = f"generated_image_{datetime.datetime.now():%Y-%m-%d-%H-%M-%S}.png"
-    generated_image_filepath = os.path.join(image_dir, generated_image_name)
-    generated_image_url = img_generation_response.data[0].url
+    generated_image_name = f"generated_image_{datetime.datetime.now():%Y-%m-%d-%H-%M-%S}.webp"
+    generated_image_filepath = os.path.join(os.getenv('IMG_SAVE_DIR'), generated_image_name)
 
-    logger.info(f"Fetch the image from url: {generated_image_url}")
     try:
-        response = requests.get(generated_image_url, stream=True)
-        response.raise_for_status()
-        with open(generated_image_filepath, "wb", encoding="utf-8") as image_file:
-            image_file.write(response.content)
+        for i, image in enumerate(img_generation_response["artifacts"]):
+            with open(generated_image_filepath, "wb") as f:
+                f.write(base64.b64decode(image["base64"]))
     except requests.exceptions.RequestException as e:
         logger.error(f"Failed to get generated image content: {e}")
         return None
 
     logger.info(f"Saved image at path: {generated_image_filepath}")
 
-    if os.environ.get('DISPLAY', ''):  # Check if display is supported
-        img = Image.open(generated_image_filepath)
-        img.show()
-
     return generated_image_filepath
-

lib/utils/alwrity_utils.py

@@ -8,6 +8,8 @@ from prompt_toolkit import prompt
 from prompt_toolkit.completion import WordCompleter
 from prompt_toolkit.validation import Validator, ValidationError
 from prompt_toolkit.shortcuts import radiolist_dialog
+import typer
+from rich import print
 
 from lib.ai_web_researcher.gpt_online_researcher import gpt_web_researcher
 from lib.ai_web_researcher.metaphor_basic_neural_web_search import metaphor_find_similar
@@ -15,7 +17,7 @@ from lib.ai_writers.keywords_to_blog import write_blog_from_keywords
 from lib.ai_writers.speech_to_blog.main_audio_to_blog import generate_audio_blog
 from lib.gpt_providers.text_generation.ai_story_writer import ai_story_generator
 from lib.gpt_providers.text_generation.ai_essay_writer import ai_essay_generator
-from lib.gpt_providers.text_to_image_generation.generate_image_from_prompt import generate_image
+from lib.gpt_providers.text_to_image_generation.main_generate_image_from_prompt import generate_image
 
 
 def blog_from_audio():
@@ -270,7 +272,21 @@ def image_generator():
     print("Choose between:: Stable-Diffusion, Dalle2, Dalle3")
     img_model = prompt('Choose the image model to use for generation: ', completer=img_models, validator=ModelTypeValidator())
 
-    print(f"{img_prompt}----{img_model}")
+    if 'Stability-Stable-Diffusion' in img_model:
+        api_key = 'STABILITY_API_KEY'
+    elif 'Dalle3' in img_model:
+        api_key = 'OPENAI_API_KEY'
+
+    if os.getenv(api_key) is None:
+        print(f"\n\n[bold green] 🙋 Get {api_key} Here:https://platform.stability.ai/docs/getting-started 🙋 -- \n")
+        user_input = typer.prompt(f"💩 -**Please Enter(copy/paste) {api_key} Key** - Here🙋:")
+        os.environ[api_key] = user_input
+        try:
+            with open(".env", "a") as env_file:
+                env_file.write(f"{api_key}={user_input}\n")
+                print(f"✅ API Key added to .env file.")
+        except Exception as err:
+            print(f"Error: {err}")
     try:
         generate_image(img_prompt, img_model)
     except Exception as err:

lib/workspace/blogs_already_written_on.py

@@ -0,0 +1,233 @@
+2201.11990
+2210.02414
+2112.11446v2
+2203.15556
+2201.08239
+2204.06745
+2305.10403
+2307.09288
+2208.11857
+2302.12095
+1905.00537
+2209.12356
+2301.08745
+2302.10198
+2009.03300
+2208.03299
+2212.13138
+2201.11903
+2211.14275
+2001.08361
+2001.08361
+2307.01952
+2206.07682
+2302.06476
+2206.04615
+2211.02011
+2212.10403
+2303.17564
+2204.02329
+2205.10625
+2205.09712
+2206.02336
+2206.06315
+2207.10342
+2209.14610
+2210.03057
+2209.07686
+2210.03493
+2210.02441
+2210.07128
+2210.11610
+2212.08635
+2212.09597
+2212.09561
+2212.10001
+2212.10071
+2301.13379
+2302.00923
+2302.00093
+2302.12246
+2303.11381
+2305.04118
+2305.11255
+2305.17812
+2301.13848
+2311.16452
+2303.08774
+2304.01373
+2302.13971v1
+2303.04360
+2208.10442
+2302.13007
+2303.15056
+2302.04166
+2303.12712
+2303.11366
+2308.12950
+2306.08568
+2107.03374
+2305.06161
+2305.07922
+2203.13474
+2204.02311
+2302.13971
+2303.17568
+2203.07814
+2301.03988
+2305.02309
+2207.01780
+2301.13816
+2307.04349
+2207.10397
+2304.05128
+2306.09896
+2306.02907
+2108.07732
+2306.03091
+2308.10335
+2312.17244
+2305.02301
+2305.15717
+2310.02421
+2305.11170
+2309.00384
+2310.06839
+2312.04737
+2309.14021
+2312.07046
+2308.07633
+2305.17888
+2306.08162
+2309.05210
+2308.14903
+2310.19102
+2311.09550
+2311.00502
+2312.08583
+2305.11627
+2301.00774
+2212.09095
+2310.01801
+2310.01382
+2310.08915
+2310.09499
+https://github.com/Significant-Gravitas/AutoGPT
+https://github.com/gpt-engineer-org/gpt-engineer
+https://github.com/reworkd/AgentGPT
+https://github.com/geekan/MetaGPT
+https://github.com/Josh-XT/AGiXT
+https://github.com/litanlitudan/skyagi
+https://github.com/joonspk-research/generative_agents
+https://github.com/smol-ai/developer
+https://github.com/Forethought-Technologies/AutoChain
+https://github.com/TransformerOptimus/SuperAGI
+https://github.com/homanp/superagent
+https://github.com/a16z-infra/ai-town
+https://github.com/AI-Engineer-Foundation/agent-protocol
+https://github.com/microsoft/autogen
+https://github.com/cpacker/MemGPT
+https://github.com/shroominic/codeinterpreter-api
+https://github.com/aiwaves-cn/agents
+https://github.com/dataelement/bisheng
+https://github.com/Maplemx/Agently
+https://github.com/zilliztech/GPTCache
+http://github.com//Significant-Gravitas/AutoGPT
+http://github.com//AUTOMATIC1111/stable-diffusion-webui
+http://github.com//gpt-engineer-org/gpt-engineer
+http://github.com//lencx/ChatGPT
+http://github.com//Pythagora-io/gpt-pilot
+http://github.com//mouredev/Hello-Python
+http://github.com//Bin-Huang/chatbox
+http://github.com//getumbrel/llama-gpt
+http://github.com//transitive-bullshit/chatgpt-api
+http://github.com//python-telegram-bot/python-telegram-bot
+http://github.com//skorch-dev/skorch
+http://github.com//botpress/botpress
+http://github.com//TransformerOptimus/SuperAGI
+http://github.com//AMAI-GmbH/AI-Expert-Roadmap
+http://github.com//babysor/MockingBird
+http://github.com//gventuri/pandas-ai
+http://github.com//hpcaitech/ColossalAI
+http://github.com//LAION-AI/Open-Assistant
+http://github.com//xitu/gold-miner
+http://github.com//google-research/google-research
+http://github.com//photoprism/photoprism
+http://github.com//explosion/spaCy
+http://github.com//StanGirard/quivr
+http://github.com//microsoft/AI-For-Beginners
+http://github.com//GitHubDaily/GitHubDaily
+http://github.com//Lightning-AI/pytorch-lightning
+http://github.com//lutzroeder/netron
+http://github.com//bentoml/OpenLLM
+http://github.com//cloneofsimo/lora
+http://github.com//eosphoros-ai/DB-GPT
+http://github.com//labring/FastGPT
+http://github.com//Mintplex-Labs/anything-llm
+http://github.com//danswer-ai/danswer
+http://github.com//neuml/txtai
+http://github.com//run-llama/rags
+http://github.com//postgresml/postgresml
+http://github.com//JushBJJ/Mr.-Ranedeer-AI-Tutor
+http://github.com//s0md3v/roop
+http://github.com//microsoft/generative-ai-for-beginners
+http://github.com//leon-ai/leon
+http://github.com//geekan/MetaGPT
+http://github.com//jmorganca/ollama
+http://github.com//run-llama/llama_index
+http://github.com//milvus-io/milvus
+http://github.com//chatchat-space/Langchain-Chatchat
+http://github.com//zhayujie/chatgpt-on-wechat
+http://github.com//mindsdb/mindsdb
+http://github.com//FlowiseAI/Flowise
+http://github.com//microsoft/unilm
+http://github.com//mlabonne/llm-course
+http://github.com//sweepai/sweep
+http://github.com//lucidrains/imagen-pytorch
+http://github.com//GokuMohandas/Made-With-ML
+http://github.com//TabbyML/tabby
+http://github.com//chroma-core/chroma
+http://github.com//eugeneyan/open-llms
+http://github.com//cleanlab/cleanlab
+http://github.com//microsoft/semantic-kernel
+http://github.com//ymcui/Chinese-LLaMA-Alpaca
+http://github.com//mudler/LocalAI
+http://github.com//mlc-ai/mlc-llm
+http://github.com//THUDM/ChatGLM2-6B
+http://github.com//langgenius/dify
+http://github.com//vllm-project/vllm
+http://github.com//ludwig-ai/ludwig
+http://github.com//hiyouga/LLaMA-Factory
+http://github.com//h2oai/h2ogpt
+http://github.com//css-doodle/css-doodle
+http://github.com//williamngan/pts
+http://github.com//dair-ai/Prompt-Engineering-Guide
+http://github.com//AI4Finance-Foundation/FinGPT
+http://github.com//yzfly/awesome-chatgpt-zh
+http://github.com//microsoft/promptflow
+http://github.com//jina-ai/jina
+http://github.com//deepset-ai/haystack
+http://github.com//open-mmlab/mmagic
+http://github.com//bentoml/BentoML
+http://github.com//openvinotoolkit/openvino
+http://github.com//reworkd/AgentGPT
+http://github.com//logspace-ai/langflow
+http://github.com//mayooear/gpt4-pdf-chatbot-langchain
+http://github.com//activeloopai/deeplake
+http://github.com//danny-avila/LibreChat
+http://github.com//liaokongVFX/LangChain-Chinese-Getting-Started-Guide
+http://github.com//kyrolabs/awesome-langchain
+http://github.com//zilliztech/GPTCache
+http://github.com//speechbrain/speechbrain
+http://github.com//vercel/ai
+http://github.com//baichuan-inc/Baichuan-7B
+http://github.com//microsoft/autogen
+http://github.com//f/awesome-chatgpt-prompts
+http://github.com//xtekky/gpt4free
+http://github.com//wechaty/wechaty
+http://github.com//RasaHQ/rasa
+http://github.com//lobehub/lobe-chat
+http://github.com//GaiZhenbiao/ChuanhuChatGPT
+http://github.com//gunthercox/ChatterBot
+http://github.com//mamoe/mirai
+http://github.com//haotian-liu/LLaVA