500kg's picture ryanlee-dev's picture
MiniMax-H3-Image
7b6142f
Raw History Blame Contribute Delete
2.79 kB
#!/usr/bin/env python3
"""Send reference1.png and prompt.edit.txt to a MiniMax-H3-Image server and write the PNG.
python3 edit.py [--url http://127.0.0.1:30000] [--out edit.png]
The images are sent in --image order, which defines <Picture 1>, <Picture 2>, ... in the
prompt. Uses only the Python standard library.
"""
import argparse
import base64
import json
import mimetypes
import urllib.request
import uuid
from pathlib import Path
# absolute(), not resolve(): in the Hugging Face cache this file is a symlink into blobs/.
HERE = Path(__file__).absolute().parent
def multipart(fields: dict, images: list) -> tuple:
boundary = f"minimax-h3-image-{uuid.uuid4().hex}"
parts = []
for name, value in fields.items():
parts.append(f'--{boundary}\r\nContent-Disposition: form-data; name="{name}"\r\n\r\n{value}\r\n'.encode())
for path in images:
content_type = mimetypes.guess_type(path.name)[0] or "application/octet-stream"
parts.append(
f'--{boundary}\r\nContent-Disposition: form-data; name="image"; filename="{path.name}"\r\n'
f"Content-Type: {content_type}\r\n\r\n".encode()
)
parts.append(path.read_bytes() + b"\r\n")
parts.append(f"--{boundary}--\r\n".encode())
return b"".join(parts), f"multipart/form-data; boundary={boundary}"
def main() -> None:
parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument("--url", default="http://127.0.0.1:30000", help="server base URL")
parser.add_argument("--image", action="append", type=Path,
help="reference image; repeat for <Picture 2>, ... (default: reference1.png)")
parser.add_argument("--prompt", type=Path, default=HERE / "prompt.edit.txt", help="prompt file")
parser.add_argument("--size", default="4096x4096", help="WIDTHxHEIGHT")
parser.add_argument("--seed", type=int, default=1234)
parser.add_argument("--out", default="edit.png")
args = parser.parse_args()
fields = {
"prompt": args.prompt.read_text(),
"size": args.size,
"seed": str(args.seed),
"generator_device": "cpu",
"response_format": "b64_json",
"output_format": "png",
}
body, content_type = multipart(fields, args.image or [HERE / "reference1.png"])
request = urllib.request.Request(
f"{args.url.rstrip('/')}/v1/images/edits", data=body, headers={"Content-Type": content_type}
)
with urllib.request.urlopen(request, timeout=1800) as response:
payload = json.load(response)
with open(args.out, "wb") as image:
image.write(base64.b64decode(payload["data"][0]["b64_json"]))
print(f"wrote {args.out}")
if __name__ == "__main__":
main()