Generate images with GPT Image

%pip install pillow openai -U

import base64
import os
from openai import OpenAI
from PIL import Image
from io import BytesIO
from IPython.display import Image as IPImage, display

client = OpenAI()
# Set your API key if not set globally
#client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY", "<your OpenAI API key if not set as env var>"))

# Create imgs/ folder
folder_path = "imgs"
os.makedirs(folder_path, exist_ok=True)

prompt1 = """
Render a realistic image of this character:
Blobby Alien Character Spec Name: Glorptak (or nickname: "Glorp")
Visual Appearance Body Shape: Amorphous and gelatinous. Overall silhouette resembles a teardrop or melting marshmallow, shifting slightly over time. Can squish and elongate when emotional or startled.
Material Texture: Semi-translucent, bio-luminescent goo with a jelly-like wobble. Surface occasionally ripples when communicating or moving quickly.
Color Palette:
- Base: Iridescent lavender or seafoam green
- Accents: Subsurface glowing veins of neon pink, electric blue, or golden yellow
- Mood-based color shifts (anger = dark red, joy = bright aqua, fear = pale gray)
Facial Features:
- Eyes: 3–5 asymmetrical floating orbs inside the blob that rotate or blink independently
- Mouth: Optional—appears as a rippling crescent on the surface when speaking or emoting
- No visible nose or ears; uses vibration-sensitive receptors embedded in goo
- Limbs: None by default, but can extrude pseudopods (tentacle-like limbs) when needed for interaction or locomotion. Can manifest temporary feet or hands.
Movement & Behavior Locomotion:
- Slides, bounces, and rolls.
- Can stick to walls and ceilings via suction. When scared, may flatten and ooze away quickly.
Mannerisms:
- Constant wiggling or wobbling even at rest
- Leaves harmless glowing slime trails
- Tends to absorb nearby small objects temporarily out of curiosity
"""

img_path1 = "imgs/glorptak.jpg"

# Generate the image
result1 = client.images.generate(
    model="gpt-image-1",
    prompt=prompt1,
    size="1024x1024"
)

# Save the image to a file and resize/compress for smaller files
image_base64 = result1.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Adjust this if you want a high-quality Glorptak
image = Image.open(BytesIO(image_bytes))
image = image.resize((300, 300), Image.LANCZOS)
image.save(img_path1, format="JPEG", quality=80, optimize=True)

prompt2 = "generate a portrait, pixel-art style, of a grey tabby cat dressed as a blond woman on a dark background."
img_path2 = "imgs/cat_portrait_pixel.jpg"

# Generate the image
result2 = client.images.generate(
    model="gpt-image-1",
    prompt=prompt2,
    quality="low",
    output_compression=50,
    output_format="jpeg",
    size="1024x1536"
)

# Save the image to a file and resize/compress for smaller files
image_base64 = result2.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

image = Image.open(BytesIO(image_bytes))
image = image.resize((250, 375), Image.LANCZOS)
image.save(img_path2, format="JPEG", quality=80, optimize=True)

prompt3 = "generate a pixel-art style picture of a green bucket hat with a pink quill on a transparent background."
img_path3 = "imgs/hat.png"

result3 = client.images.generate(
    model="gpt-image-1",
    prompt=prompt3,
    quality="low",
    output_format="png",
    size="1024x1024"
)
image_base64 = result3.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save the image to a file and resize/compress for smaller files
image_base64 = result3.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

image = Image.open(BytesIO(image_bytes))
image = image.resize((250, 250), Image.LANCZOS)
image.save(img_path3, format="PNG")

prompt_edit = """
Combine the images of the cat and the hat to show the cat wearing the hat while being perched in a tree, still in pixel-art style.
"""
img_path_edit = "imgs/cat_with_hat.jpg"

img1 = open(img_path2, "rb")
img2 = open(img_path3, "rb")

# Generate the new image
result_edit = client.images.edit(
    model="gpt-image-1",
    image=[img1,img2], 
    prompt=prompt_edit,
    size="1024x1536"
)

# Save the image to a file and resize/compress for smaller files
image_base64 = result_edit.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

image = Image.open(BytesIO(image_bytes))
image = image.resize((250, 375), Image.LANCZOS)
image.save(img_path_edit, format="JPEG", quality=80, optimize=True)    

img_path_mask = "imgs/mask.png"
prompt_mask = "generate a mask delimiting the entire character in the picture, using white where the character is and black for the background. Return an image in the same size as the input image."

img_input = open(img_path1, "rb")

# Generate the mask
result_mask = client.images.edit(
    model="gpt-image-1",
    image=img_input, 
    prompt=prompt_mask
)

# Save the image to a file and resize/compress for smaller files
image_base64 = result_mask.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

image = Image.open(BytesIO(image_bytes))
image = image.resize((300, 300), Image.LANCZOS)
image.save(img_path_mask, format="PNG")

# 1. Load your black & white mask as a grayscale image
mask = Image.open(img_path_mask).convert("L")

# 2. Convert it to RGBA so it has space for an alpha channel
mask_rgba = mask.convert("RGBA")

# 3. Then use the mask itself to fill that alpha channel
mask_rgba.putalpha(mask)

# 4. Convert the mask into bytes
buf = BytesIO()
mask_rgba.save(buf, format="PNG")
mask_bytes = buf.getvalue()

# Save the resulting file
img_path_mask_alpha = "imgs/mask_alpha.png"
with open(img_path_mask_alpha, "wb") as f:
    f.write(mask_bytes)

prompt_mask_edit = "A strange character on a colorful galaxy background, with lots of stars and planets."
mask = open(img_path_mask_alpha, "rb")

result_mask_edit = client.images.edit(
    model="gpt-image-1",         
    prompt=prompt_mask_edit,
    image=img_input,
    mask=mask,
    size="1024x1024"
)