Duplicate from thisisvaze/enhanced-dalle2

Co-authored-by: Aaditya Vaze <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Enhanced Dalle2
+emoji: ⚡
+colorFrom: indigo
+colorTo: gray
+sdk: gradio
+sdk_version: 3.32.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: thisisvaze/enhanced-dalle2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,102 @@
+import openai
+import requests
+import urllib.parse
+import json
+import gradio as gr
+from PIL import Image, ImageDraw, ImageFont
+from io import BytesIO
+import os
+
+openai.api_key = os.environ["OPEN_AI_KEY"]
+
+
+
+png_bytes_array = []
+images = []
+
+system_prompt = """Transcript of a dialog, where the User interacts with an Assistant named Stablediffy. Stablediffy knows much about prompt engineering for stable diffusion (an open-source image generation software). The User asks Stablediffy about prompts for stable diffusion Image Generation.
+
+Possible keywords for stable diffusion: "cinematic, colorful background, concept art, dramatic lighting, high detail, highly detailed, hyper realistic, intricate, intricate sharp details, octane render, smooth, studio lighting, trending on artstation, landscape, scenery, cityscape, underwater, salt flat, tundra, jungle, desert mountain, ocean, beach, lake, waterfall, ripples, swirl, waves, avenue, horizon, pasture, plateau, garden, fields, floating island, forest, cloud forest, grasslands, flower field, flower ocean, volcano, cliff, snowy mountain
+city, cityscape, street, downtown"
+
+-- Transcript --
+
+USER: suggest a prompt for a young girl from Swiss sitting by the window with headphones on
+ASSISTANT: gorgeous young Swiss girl sitting by window with headphones on, wearing white bra with translucent shirt over, soft lips, beach blonde hair, octane render, unreal engine, photograph, realistic skin texture, photorealistic, hyper realism, highly detailed, 85mm portrait photography, award winning, hard rim lighting photography
+
+USER: suggest a prompt for an mysterious city
+ASSISTANT: Mysterious city, cityscape, urban, downtown, street, noir style, cinematic lightning, dramatic lightning, intricate, sharp details, octane render, unreal engine, highly detailed, night scene, dark lighting, gritty atmosphere
+
+USER: suggest a prompt for a high quality render of a car in 1950
+ASSISTANT: Car in 1950, highly detailed, classic car, 1950's, highly detailed, dramatic lightning, cinematic lightning, unreal engine
+
+USER:"""
+
+def get_modified_text_response(user_query):
+    try:
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "system", "content": system_prompt},
+                    {"role": "user", "content": "suggest a prompt for" +  user_query}]
+        )
+        res = response["choices"][0]["message"]["content"].replace('\'', '')
+        print(res)
+        return res
+    except:
+        return "no gpt response"
+
+def text_to_image(text, selected_value):
+    global png_bytes_array
+    images = []
+    if(selected_value == "New"):
+        png_bytes_array = []
+        image_urls = generate_image(text)
+        for img in image_urls:
+            response = requests.get(img['url'])
+            image = Image.open(BytesIO(response.content))
+            images.append(image)
+            bytesIO = BytesIO()
+            image.save(bytesIO, format="PNG")
+            png_bytes = bytesIO.getvalue()
+            png_bytes_array.append(png_bytes)
+        return images
+    
+    else:
+        index = int(selected_value[-1])
+        image_urls = variation_image(png_bytes_array[index])
+        for img in image_urls:
+            response = requests.get(img['url'])
+            image = Image.open(BytesIO(response.content))
+            images.append(image)
+        return images
+    
+def variation_image(image):
+    response = openai.Image.create_variation(
+    image = image,
+    n=4,
+    size="1024x1024"
+        )
+    #print(response)
+    #image_url = response['data'][0]['url']
+    return response['data']
+def generate_image(prompt):
+    better_prompt = get_modified_text_response(prompt)
+    response = openai.Image.create(
+    prompt=better_prompt,
+    n=4,
+    size="1024x1024"
+        )
+
+    return response['data']
+def main():
+    radio_buttons = gr.inputs.Radio(["New", "Var0","Var1", "Var2", "Var3"], label="Select a variation option")
+    out = gr.Gallery(
+            label="Generated images", show_label=False, elem_id="gallery"
+        ).style(columns=[2], rows=[2], object_fit="contain", height="auto")
+    iface = gr.Interface(fn=text_to_image, inputs=["text",radio_buttons], 
+                         #outputs=gr.Gallery([gr.Image(type="pil").style(height=300,width=300),gr.Image(type="pil").style(height=300,width=300),gr.Image(type="pil").style(height=300,width=300),gr.Image(type="pil").style(height=300,width=300)]))
+                         outputs = out)
+    iface.launch()  
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,4 @@
+openai
+requests
+gradio
+pillow