Initial commit
This commit is contained in:
Zhongwei Li
157
skills/gemini-imagegen/scripts/compose_images.py
Executable file
157
skills/gemini-imagegen/scripts/compose_images.py
Executable file
@@ -0,0 +1,157 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Compose multiple images into a new image using Gemini API.
|
||||
|
||||
Usage:
|
||||
python compose_images.py "instruction" output.png image1.png [image2.png ...]
|
||||
|
||||
Examples:
|
||||
python compose_images.py "Create a group photo of these people" group.png person1.png person2.png
|
||||
python compose_images.py "Put the cat from the first image on the couch from the second" result.png cat.png couch.png
|
||||
python compose_images.py "Apply the art style from the first image to the scene in the second" styled.png style.png photo.png
|
||||
|
||||
Note: Supports up to 14 reference images (Gemini 3 Pro only).
|
||||
|
||||
Environment:
|
||||
GEMINI_API_KEY - Required API key
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
|
||||
from PIL import Image
|
||||
from google import genai
|
||||
from google.genai import types
|
||||
|
||||
|
||||
def compose_images(
|
||||
instruction: str,
|
||||
output_path: str,
|
||||
image_paths: list[str],
|
||||
model: str = "gemini-3-pro-image-preview",
|
||||
aspect_ratio: str | None = None,
|
||||
image_size: str | None = None,
|
||||
) -> str | None:
|
||||
"""Compose multiple images based on instructions.
|
||||
|
||||
Args:
|
||||
instruction: Text description of how to combine images
|
||||
output_path: Path to save the result
|
||||
image_paths: List of input image paths (up to 14)
|
||||
model: Gemini model to use (pro recommended)
|
||||
aspect_ratio: Output aspect ratio
|
||||
image_size: Output resolution
|
||||
|
||||
Returns:
|
||||
Any text response from the model, or None
|
||||
"""
|
||||
api_key = os.environ.get("GEMINI_API_KEY")
|
||||
if not api_key:
|
||||
raise EnvironmentError("GEMINI_API_KEY environment variable not set")
|
||||
|
||||
if len(image_paths) > 14:
|
||||
raise ValueError("Maximum 14 reference images supported")
|
||||
|
||||
if len(image_paths) < 1:
|
||||
raise ValueError("At least one image is required")
|
||||
|
||||
# Verify all images exist
|
||||
for path in image_paths:
|
||||
if not os.path.exists(path):
|
||||
raise FileNotFoundError(f"Image not found: {path}")
|
||||
|
||||
client = genai.Client(api_key=api_key)
|
||||
|
||||
# Load images
|
||||
images = [Image.open(path) for path in image_paths]
|
||||
|
||||
# Build contents: instruction first, then images
|
||||
contents = [instruction] + images
|
||||
|
||||
# Build config
|
||||
config_kwargs = {"response_modalities": ["TEXT", "IMAGE"]}
|
||||
|
||||
image_config_kwargs = {}
|
||||
if aspect_ratio:
|
||||
image_config_kwargs["aspect_ratio"] = aspect_ratio
|
||||
if image_size:
|
||||
image_config_kwargs["image_size"] = image_size
|
||||
|
||||
if image_config_kwargs:
|
||||
config_kwargs["image_config"] = types.ImageConfig(**image_config_kwargs)
|
||||
|
||||
config = types.GenerateContentConfig(**config_kwargs)
|
||||
|
||||
response = client.models.generate_content(
|
||||
model=model,
|
||||
contents=contents,
|
||||
config=config,
|
||||
)
|
||||
|
||||
text_response = None
|
||||
image_saved = False
|
||||
|
||||
for part in response.parts:
|
||||
if part.text is not None:
|
||||
text_response = part.text
|
||||
elif part.inline_data is not None:
|
||||
image = part.as_image()
|
||||
image.save(output_path)
|
||||
image_saved = True
|
||||
|
||||
if not image_saved:
|
||||
raise RuntimeError("No image was generated.")
|
||||
|
||||
return text_response
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Compose multiple images using Gemini API",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog=__doc__
|
||||
)
|
||||
parser.add_argument("instruction", help="Composition instruction")
|
||||
parser.add_argument("output", help="Output file path")
|
||||
parser.add_argument("images", nargs="+", help="Input images (up to 14)")
|
||||
parser.add_argument(
|
||||
"--model", "-m",
|
||||
default="gemini-3-pro-image-preview",
|
||||
choices=["gemini-2.5-flash-image", "gemini-3-pro-image-preview"],
|
||||
help="Model to use (pro recommended for composition)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--aspect", "-a",
|
||||
choices=["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"],
|
||||
help="Output aspect ratio"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--size", "-s",
|
||||
choices=["1K", "2K", "4K"],
|
||||
help="Output resolution"
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
text = compose_images(
|
||||
instruction=args.instruction,
|
||||
output_path=args.output,
|
||||
image_paths=args.images,
|
||||
model=args.model,
|
||||
aspect_ratio=args.aspect,
|
||||
image_size=args.size,
|
||||
)
|
||||
|
||||
print(f"Composed image saved to: {args.output}")
|
||||
if text:
|
||||
print(f"Model response: {text}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
144
skills/gemini-imagegen/scripts/edit_image.py
Executable file
144
skills/gemini-imagegen/scripts/edit_image.py
Executable file
@@ -0,0 +1,144 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Edit existing images using Gemini API.
|
||||
|
||||
Usage:
|
||||
python edit_image.py input.png "edit instruction" output.png [options]
|
||||
|
||||
Examples:
|
||||
python edit_image.py photo.png "Add a rainbow in the sky" edited.png
|
||||
python edit_image.py room.jpg "Change the sofa to red leather" room_edited.jpg
|
||||
python edit_image.py portrait.png "Make it look like a Van Gogh painting" artistic.png --model gemini-3-pro-image-preview
|
||||
|
||||
Environment:
|
||||
GEMINI_API_KEY - Required API key
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
|
||||
from PIL import Image
|
||||
from google import genai
|
||||
from google.genai import types
|
||||
|
||||
|
||||
def edit_image(
|
||||
input_path: str,
|
||||
instruction: str,
|
||||
output_path: str,
|
||||
model: str = "gemini-2.5-flash-image",
|
||||
aspect_ratio: str | None = None,
|
||||
image_size: str | None = None,
|
||||
) -> str | None:
|
||||
"""Edit an existing image based on text instructions.
|
||||
|
||||
Args:
|
||||
input_path: Path to the input image
|
||||
instruction: Text description of edits to make
|
||||
output_path: Path to save the edited image
|
||||
model: Gemini model to use
|
||||
aspect_ratio: Output aspect ratio
|
||||
image_size: Output resolution
|
||||
|
||||
Returns:
|
||||
Any text response from the model, or None
|
||||
"""
|
||||
api_key = os.environ.get("GEMINI_API_KEY")
|
||||
if not api_key:
|
||||
raise EnvironmentError("GEMINI_API_KEY environment variable not set")
|
||||
|
||||
if not os.path.exists(input_path):
|
||||
raise FileNotFoundError(f"Input image not found: {input_path}")
|
||||
|
||||
client = genai.Client(api_key=api_key)
|
||||
|
||||
# Load input image
|
||||
input_image = Image.open(input_path)
|
||||
|
||||
# Build config
|
||||
config_kwargs = {"response_modalities": ["TEXT", "IMAGE"]}
|
||||
|
||||
image_config_kwargs = {}
|
||||
if aspect_ratio:
|
||||
image_config_kwargs["aspect_ratio"] = aspect_ratio
|
||||
if image_size:
|
||||
image_config_kwargs["image_size"] = image_size
|
||||
|
||||
if image_config_kwargs:
|
||||
config_kwargs["image_config"] = types.ImageConfig(**image_config_kwargs)
|
||||
|
||||
config = types.GenerateContentConfig(**config_kwargs)
|
||||
|
||||
response = client.models.generate_content(
|
||||
model=model,
|
||||
contents=[instruction, input_image],
|
||||
config=config,
|
||||
)
|
||||
|
||||
text_response = None
|
||||
image_saved = False
|
||||
|
||||
for part in response.parts:
|
||||
if part.text is not None:
|
||||
text_response = part.text
|
||||
elif part.inline_data is not None:
|
||||
image = part.as_image()
|
||||
image.save(output_path)
|
||||
image_saved = True
|
||||
|
||||
if not image_saved:
|
||||
raise RuntimeError("No image was generated. Check your instruction and try again.")
|
||||
|
||||
return text_response
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Edit images using Gemini API",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog=__doc__
|
||||
)
|
||||
parser.add_argument("input", help="Input image path")
|
||||
parser.add_argument("instruction", help="Edit instruction")
|
||||
parser.add_argument("output", help="Output file path")
|
||||
parser.add_argument(
|
||||
"--model", "-m",
|
||||
default="gemini-2.5-flash-image",
|
||||
choices=["gemini-2.5-flash-image", "gemini-3-pro-image-preview"],
|
||||
help="Model to use (default: gemini-2.5-flash-image)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--aspect", "-a",
|
||||
choices=["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"],
|
||||
help="Output aspect ratio"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--size", "-s",
|
||||
choices=["1K", "2K", "4K"],
|
||||
help="Output resolution"
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
text = edit_image(
|
||||
input_path=args.input,
|
||||
instruction=args.instruction,
|
||||
output_path=args.output,
|
||||
model=args.model,
|
||||
aspect_ratio=args.aspect,
|
||||
image_size=args.size,
|
||||
)
|
||||
|
||||
print(f"Edited image saved to: {args.output}")
|
||||
if text:
|
||||
print(f"Model response: {text}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
263
skills/gemini-imagegen/scripts/gemini_images.py
Executable file
263
skills/gemini-imagegen/scripts/gemini_images.py
Executable file
@@ -0,0 +1,263 @@
|
||||
"""
|
||||
Gemini Image Generation Library
|
||||
|
||||
A simple Python library for generating and editing images with the Gemini API.
|
||||
|
||||
Usage:
|
||||
from gemini_images import GeminiImageGenerator
|
||||
|
||||
gen = GeminiImageGenerator()
|
||||
gen.generate("A sunset over mountains", "sunset.png")
|
||||
gen.edit("input.png", "Add clouds", "output.png")
|
||||
|
||||
Environment:
|
||||
GEMINI_API_KEY - Required API key
|
||||
"""
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Literal
|
||||
|
||||
from PIL import Image
|
||||
from google import genai
|
||||
from google.genai import types
|
||||
|
||||
|
||||
AspectRatio = Literal["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"]
|
||||
ImageSize = Literal["1K", "2K", "4K"]
|
||||
Model = Literal["gemini-2.5-flash-image", "gemini-3-pro-image-preview"]
|
||||
|
||||
|
||||
class GeminiImageGenerator:
|
||||
"""High-level interface for Gemini image generation."""
|
||||
|
||||
FLASH = "gemini-2.5-flash-image"
|
||||
PRO = "gemini-3-pro-image-preview"
|
||||
|
||||
def __init__(self, api_key: str | None = None, model: Model = FLASH):
|
||||
"""Initialize the generator.
|
||||
|
||||
Args:
|
||||
api_key: Gemini API key (defaults to GEMINI_API_KEY env var)
|
||||
model: Default model to use
|
||||
"""
|
||||
self.api_key = api_key or os.environ.get("GEMINI_API_KEY")
|
||||
if not self.api_key:
|
||||
raise EnvironmentError("GEMINI_API_KEY not set")
|
||||
|
||||
self.client = genai.Client(api_key=self.api_key)
|
||||
self.model = model
|
||||
|
||||
def _build_config(
|
||||
self,
|
||||
aspect_ratio: AspectRatio | None = None,
|
||||
image_size: ImageSize | None = None,
|
||||
google_search: bool = False,
|
||||
) -> types.GenerateContentConfig:
|
||||
"""Build generation config."""
|
||||
kwargs = {"response_modalities": ["TEXT", "IMAGE"]}
|
||||
|
||||
img_config = {}
|
||||
if aspect_ratio:
|
||||
img_config["aspect_ratio"] = aspect_ratio
|
||||
if image_size:
|
||||
img_config["image_size"] = image_size
|
||||
|
||||
if img_config:
|
||||
kwargs["image_config"] = types.ImageConfig(**img_config)
|
||||
|
||||
if google_search:
|
||||
kwargs["tools"] = [{"google_search": {}}]
|
||||
|
||||
return types.GenerateContentConfig(**kwargs)
|
||||
|
||||
def generate(
|
||||
self,
|
||||
prompt: str,
|
||||
output: str | Path,
|
||||
*,
|
||||
model: Model | None = None,
|
||||
aspect_ratio: AspectRatio | None = None,
|
||||
image_size: ImageSize | None = None,
|
||||
google_search: bool = False,
|
||||
) -> tuple[Path, str | None]:
|
||||
"""Generate an image from a text prompt.
|
||||
|
||||
Args:
|
||||
prompt: Text description
|
||||
output: Output file path
|
||||
model: Override default model
|
||||
aspect_ratio: Output aspect ratio
|
||||
image_size: Output resolution
|
||||
google_search: Enable Google Search grounding (Pro only)
|
||||
|
||||
Returns:
|
||||
Tuple of (output path, optional text response)
|
||||
"""
|
||||
output = Path(output)
|
||||
config = self._build_config(aspect_ratio, image_size, google_search)
|
||||
|
||||
response = self.client.models.generate_content(
|
||||
model=model or self.model,
|
||||
contents=[prompt],
|
||||
config=config,
|
||||
)
|
||||
|
||||
text = None
|
||||
for part in response.parts:
|
||||
if part.text:
|
||||
text = part.text
|
||||
elif part.inline_data:
|
||||
part.as_image().save(output)
|
||||
|
||||
return output, text
|
||||
|
||||
def edit(
|
||||
self,
|
||||
input_image: str | Path | Image.Image,
|
||||
instruction: str,
|
||||
output: str | Path,
|
||||
*,
|
||||
model: Model | None = None,
|
||||
aspect_ratio: AspectRatio | None = None,
|
||||
image_size: ImageSize | None = None,
|
||||
) -> tuple[Path, str | None]:
|
||||
"""Edit an existing image.
|
||||
|
||||
Args:
|
||||
input_image: Input image (path or PIL Image)
|
||||
instruction: Edit instruction
|
||||
output: Output file path
|
||||
model: Override default model
|
||||
aspect_ratio: Output aspect ratio
|
||||
image_size: Output resolution
|
||||
|
||||
Returns:
|
||||
Tuple of (output path, optional text response)
|
||||
"""
|
||||
output = Path(output)
|
||||
|
||||
if isinstance(input_image, (str, Path)):
|
||||
input_image = Image.open(input_image)
|
||||
|
||||
config = self._build_config(aspect_ratio, image_size)
|
||||
|
||||
response = self.client.models.generate_content(
|
||||
model=model or self.model,
|
||||
contents=[instruction, input_image],
|
||||
config=config,
|
||||
)
|
||||
|
||||
text = None
|
||||
for part in response.parts:
|
||||
if part.text:
|
||||
text = part.text
|
||||
elif part.inline_data:
|
||||
part.as_image().save(output)
|
||||
|
||||
return output, text
|
||||
|
||||
def compose(
|
||||
self,
|
||||
instruction: str,
|
||||
images: list[str | Path | Image.Image],
|
||||
output: str | Path,
|
||||
*,
|
||||
model: Model | None = None,
|
||||
aspect_ratio: AspectRatio | None = None,
|
||||
image_size: ImageSize | None = None,
|
||||
) -> tuple[Path, str | None]:
|
||||
"""Compose multiple images into one.
|
||||
|
||||
Args:
|
||||
instruction: Composition instruction
|
||||
images: List of input images (up to 14)
|
||||
output: Output file path
|
||||
model: Override default model (Pro recommended)
|
||||
aspect_ratio: Output aspect ratio
|
||||
image_size: Output resolution
|
||||
|
||||
Returns:
|
||||
Tuple of (output path, optional text response)
|
||||
"""
|
||||
output = Path(output)
|
||||
|
||||
# Load images
|
||||
loaded = []
|
||||
for img in images:
|
||||
if isinstance(img, (str, Path)):
|
||||
loaded.append(Image.open(img))
|
||||
else:
|
||||
loaded.append(img)
|
||||
|
||||
config = self._build_config(aspect_ratio, image_size)
|
||||
contents = [instruction] + loaded
|
||||
|
||||
response = self.client.models.generate_content(
|
||||
model=model or self.PRO, # Pro recommended for composition
|
||||
contents=contents,
|
||||
config=config,
|
||||
)
|
||||
|
||||
text = None
|
||||
for part in response.parts:
|
||||
if part.text:
|
||||
text = part.text
|
||||
elif part.inline_data:
|
||||
part.as_image().save(output)
|
||||
|
||||
return output, text
|
||||
|
||||
def chat(self) -> "ImageChat":
|
||||
"""Start an interactive chat session for iterative refinement."""
|
||||
return ImageChat(self.client, self.model)
|
||||
|
||||
|
||||
class ImageChat:
|
||||
"""Multi-turn chat session for iterative image generation."""
|
||||
|
||||
def __init__(self, client: genai.Client, model: Model):
|
||||
self.client = client
|
||||
self.model = model
|
||||
self._chat = client.chats.create(
|
||||
model=model,
|
||||
config=types.GenerateContentConfig(response_modalities=["TEXT", "IMAGE"]),
|
||||
)
|
||||
self.current_image: Image.Image | None = None
|
||||
|
||||
def send(
|
||||
self,
|
||||
message: str,
|
||||
image: Image.Image | str | Path | None = None,
|
||||
) -> tuple[Image.Image | None, str | None]:
|
||||
"""Send a message and optionally an image.
|
||||
|
||||
Returns:
|
||||
Tuple of (generated image or None, text response or None)
|
||||
"""
|
||||
contents = [message]
|
||||
if image:
|
||||
if isinstance(image, (str, Path)):
|
||||
image = Image.open(image)
|
||||
contents.append(image)
|
||||
|
||||
response = self._chat.send_message(contents)
|
||||
|
||||
text = None
|
||||
img = None
|
||||
for part in response.parts:
|
||||
if part.text:
|
||||
text = part.text
|
||||
elif part.inline_data:
|
||||
img = part.as_image()
|
||||
self.current_image = img
|
||||
|
||||
return img, text
|
||||
|
||||
def reset(self):
|
||||
"""Reset the chat session."""
|
||||
self._chat = self.client.chats.create(
|
||||
model=self.model,
|
||||
config=types.GenerateContentConfig(response_modalities=["TEXT", "IMAGE"]),
|
||||
)
|
||||
self.current_image = None
|
||||
133
skills/gemini-imagegen/scripts/generate_image.py
Executable file
133
skills/gemini-imagegen/scripts/generate_image.py
Executable file
@@ -0,0 +1,133 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Generate images from text prompts using Gemini API.
|
||||
|
||||
Usage:
|
||||
python generate_image.py "prompt" output.png [--model MODEL] [--aspect RATIO] [--size SIZE]
|
||||
|
||||
Examples:
|
||||
python generate_image.py "A cat in space" cat.png
|
||||
python generate_image.py "A logo for Acme Corp" logo.png --model gemini-3-pro-image-preview --aspect 1:1
|
||||
python generate_image.py "Epic landscape" landscape.png --aspect 16:9 --size 2K
|
||||
|
||||
Environment:
|
||||
GEMINI_API_KEY - Required API key
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
|
||||
from google import genai
|
||||
from google.genai import types
|
||||
|
||||
|
||||
def generate_image(
|
||||
prompt: str,
|
||||
output_path: str,
|
||||
model: str = "gemini-2.5-flash-image",
|
||||
aspect_ratio: str | None = None,
|
||||
image_size: str | None = None,
|
||||
) -> str | None:
|
||||
"""Generate an image from a text prompt.
|
||||
|
||||
Args:
|
||||
prompt: Text description of the image to generate
|
||||
output_path: Path to save the generated image
|
||||
model: Gemini model to use
|
||||
aspect_ratio: Aspect ratio (1:1, 16:9, 9:16, etc.)
|
||||
image_size: Resolution (1K, 2K, 4K - 4K only for pro model)
|
||||
|
||||
Returns:
|
||||
Any text response from the model, or None
|
||||
"""
|
||||
api_key = os.environ.get("GEMINI_API_KEY")
|
||||
if not api_key:
|
||||
raise EnvironmentError("GEMINI_API_KEY environment variable not set")
|
||||
|
||||
client = genai.Client(api_key=api_key)
|
||||
|
||||
# Build config
|
||||
config_kwargs = {"response_modalities": ["TEXT", "IMAGE"]}
|
||||
|
||||
image_config_kwargs = {}
|
||||
if aspect_ratio:
|
||||
image_config_kwargs["aspect_ratio"] = aspect_ratio
|
||||
if image_size:
|
||||
image_config_kwargs["image_size"] = image_size
|
||||
|
||||
if image_config_kwargs:
|
||||
config_kwargs["image_config"] = types.ImageConfig(**image_config_kwargs)
|
||||
|
||||
config = types.GenerateContentConfig(**config_kwargs)
|
||||
|
||||
response = client.models.generate_content(
|
||||
model=model,
|
||||
contents=[prompt],
|
||||
config=config,
|
||||
)
|
||||
|
||||
text_response = None
|
||||
image_saved = False
|
||||
|
||||
for part in response.parts:
|
||||
if part.text is not None:
|
||||
text_response = part.text
|
||||
elif part.inline_data is not None:
|
||||
image = part.as_image()
|
||||
image.save(output_path)
|
||||
image_saved = True
|
||||
|
||||
if not image_saved:
|
||||
raise RuntimeError("No image was generated. Check your prompt and try again.")
|
||||
|
||||
return text_response
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Generate images from text prompts using Gemini API",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog=__doc__
|
||||
)
|
||||
parser.add_argument("prompt", help="Text prompt describing the image")
|
||||
parser.add_argument("output", help="Output file path (e.g., output.png)")
|
||||
parser.add_argument(
|
||||
"--model", "-m",
|
||||
default="gemini-2.5-flash-image",
|
||||
choices=["gemini-2.5-flash-image", "gemini-3-pro-image-preview"],
|
||||
help="Model to use (default: gemini-2.5-flash-image)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--aspect", "-a",
|
||||
choices=["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"],
|
||||
help="Aspect ratio"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--size", "-s",
|
||||
choices=["1K", "2K", "4K"],
|
||||
help="Image resolution (4K only available with pro model)"
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
text = generate_image(
|
||||
prompt=args.prompt,
|
||||
output_path=args.output,
|
||||
model=args.model,
|
||||
aspect_ratio=args.aspect,
|
||||
image_size=args.size,
|
||||
)
|
||||
|
||||
print(f"Image saved to: {args.output}")
|
||||
if text:
|
||||
print(f"Model response: {text}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
216
skills/gemini-imagegen/scripts/multi_turn_chat.py
Executable file
216
skills/gemini-imagegen/scripts/multi_turn_chat.py
Executable file
@@ -0,0 +1,216 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Interactive multi-turn image generation and refinement using Gemini API.
|
||||
|
||||
Usage:
|
||||
python multi_turn_chat.py [--model MODEL] [--output-dir DIR]
|
||||
|
||||
This starts an interactive session where you can:
|
||||
- Generate images from prompts
|
||||
- Iteratively refine images through conversation
|
||||
- Load existing images for editing
|
||||
- Save images at any point
|
||||
|
||||
Commands:
|
||||
/save [filename] - Save current image
|
||||
/load <path> - Load an image into the conversation
|
||||
/clear - Start fresh conversation
|
||||
/quit - Exit
|
||||
|
||||
Environment:
|
||||
GEMINI_API_KEY - Required API key
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
from PIL import Image
|
||||
from google import genai
|
||||
from google.genai import types
|
||||
|
||||
|
||||
class ImageChat:
|
||||
"""Interactive chat session for image generation and refinement."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
model: str = "gemini-2.5-flash-image",
|
||||
output_dir: str = ".",
|
||||
):
|
||||
api_key = os.environ.get("GEMINI_API_KEY")
|
||||
if not api_key:
|
||||
raise EnvironmentError("GEMINI_API_KEY environment variable not set")
|
||||
|
||||
self.client = genai.Client(api_key=api_key)
|
||||
self.model = model
|
||||
self.output_dir = Path(output_dir)
|
||||
self.output_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
self.chat = None
|
||||
self.current_image = None
|
||||
self.image_count = 0
|
||||
|
||||
self._init_chat()
|
||||
|
||||
def _init_chat(self):
|
||||
"""Initialize or reset the chat session."""
|
||||
config = types.GenerateContentConfig(
|
||||
response_modalities=["TEXT", "IMAGE"]
|
||||
)
|
||||
self.chat = self.client.chats.create(
|
||||
model=self.model,
|
||||
config=config,
|
||||
)
|
||||
self.current_image = None
|
||||
|
||||
def send_message(self, message: str, image: Image.Image | None = None) -> tuple[str | None, Image.Image | None]:
|
||||
"""Send a message and optionally an image, return response text and image."""
|
||||
contents = []
|
||||
if message:
|
||||
contents.append(message)
|
||||
if image:
|
||||
contents.append(image)
|
||||
|
||||
if not contents:
|
||||
return None, None
|
||||
|
||||
response = self.chat.send_message(contents)
|
||||
|
||||
text_response = None
|
||||
image_response = None
|
||||
|
||||
for part in response.parts:
|
||||
if part.text is not None:
|
||||
text_response = part.text
|
||||
elif part.inline_data is not None:
|
||||
image_response = part.as_image()
|
||||
self.current_image = image_response
|
||||
|
||||
return text_response, image_response
|
||||
|
||||
def save_image(self, filename: str | None = None) -> str | None:
|
||||
"""Save the current image to a file."""
|
||||
if self.current_image is None:
|
||||
return None
|
||||
|
||||
if filename is None:
|
||||
self.image_count += 1
|
||||
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
filename = f"image_{timestamp}_{self.image_count}.png"
|
||||
|
||||
filepath = self.output_dir / filename
|
||||
self.current_image.save(filepath)
|
||||
return str(filepath)
|
||||
|
||||
def load_image(self, path: str) -> Image.Image:
|
||||
"""Load an image from disk."""
|
||||
img = Image.open(path)
|
||||
self.current_image = img
|
||||
return img
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Interactive multi-turn image generation",
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
epilog=__doc__
|
||||
)
|
||||
parser.add_argument(
|
||||
"--model", "-m",
|
||||
default="gemini-2.5-flash-image",
|
||||
choices=["gemini-2.5-flash-image", "gemini-3-pro-image-preview"],
|
||||
help="Model to use"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--output-dir", "-o",
|
||||
default=".",
|
||||
help="Directory to save images"
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
chat = ImageChat(model=args.model, output_dir=args.output_dir)
|
||||
except Exception as e:
|
||||
print(f"Error initializing: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
print(f"Gemini Image Chat ({args.model})")
|
||||
print("Commands: /save [name], /load <path>, /clear, /quit")
|
||||
print("-" * 50)
|
||||
|
||||
while True:
|
||||
try:
|
||||
user_input = input("\nYou: ").strip()
|
||||
except (EOFError, KeyboardInterrupt):
|
||||
print("\nGoodbye!")
|
||||
break
|
||||
|
||||
if not user_input:
|
||||
continue
|
||||
|
||||
# Handle commands
|
||||
if user_input.startswith("/"):
|
||||
parts = user_input.split(maxsplit=1)
|
||||
cmd = parts[0].lower()
|
||||
arg = parts[1] if len(parts) > 1 else None
|
||||
|
||||
if cmd == "/quit":
|
||||
print("Goodbye!")
|
||||
break
|
||||
|
||||
elif cmd == "/clear":
|
||||
chat._init_chat()
|
||||
print("Conversation cleared.")
|
||||
continue
|
||||
|
||||
elif cmd == "/save":
|
||||
path = chat.save_image(arg)
|
||||
if path:
|
||||
print(f"Image saved to: {path}")
|
||||
else:
|
||||
print("No image to save.")
|
||||
continue
|
||||
|
||||
elif cmd == "/load":
|
||||
if not arg:
|
||||
print("Usage: /load <path>")
|
||||
continue
|
||||
try:
|
||||
chat.load_image(arg)
|
||||
print(f"Loaded: {arg}")
|
||||
print("You can now describe edits to make.")
|
||||
except Exception as e:
|
||||
print(f"Error loading image: {e}")
|
||||
continue
|
||||
|
||||
else:
|
||||
print(f"Unknown command: {cmd}")
|
||||
continue
|
||||
|
||||
# Send message to model
|
||||
try:
|
||||
# If we have a loaded image and this is first message, include it
|
||||
image_to_send = None
|
||||
if chat.current_image and not chat.chat.history:
|
||||
image_to_send = chat.current_image
|
||||
|
||||
text, image = chat.send_message(user_input, image_to_send)
|
||||
|
||||
if text:
|
||||
print(f"\nGemini: {text}")
|
||||
|
||||
if image:
|
||||
# Auto-save
|
||||
path = chat.save_image()
|
||||
print(f"\n[Image generated: {path}]")
|
||||
|
||||
except Exception as e:
|
||||
print(f"\nError: {e}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user