Spaces:
Sleeping
Sleeping
File size: 5,109 Bytes
58e6885 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 | import argparse
import base64
import json
import os
import sys
from concurrent.futures import ThreadPoolExecutor, as_completed
from pathlib import Path
from openai import OpenAI
ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT))
os.chdir(ROOT)
from config import api_key, base_url
DEFAULT_PROMPT = "improve this infographics to make it look more visual coherent and appealing."
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--input-root",
default=None,
help="chart_template_samples 下某次任务目录；默认取最新时间戳目录",
)
parser.add_argument(
"--output-dir",
default=None,
help="输出目录；默认 <input-root>/gpt_image_2_improved",
)
parser.add_argument("--model", default="gpt-image-2")
parser.add_argument("--prompt", default=DEFAULT_PROMPT)
parser.add_argument("--limit", type=int, default=0)
parser.add_argument("--workers", type=int, default=1)
parser.add_argument("--size", default="auto")
parser.add_argument("--quality", default="auto")
parser.add_argument("--overwrite", action="store_true")
return parser.parse_args()
def latest_sample_run(root: Path):
runs = [
p
for p in root.iterdir()
if p.is_dir() and (p / "run_config.json").is_file() and p.name[:8].isdigit()
]
if not runs:
raise SystemExit(f"no timestamp run found under {root}")
return sorted(runs, key=lambda p: p.name)[-1]
def collect_pngs(input_root: Path, output_dir: Path, limit: int):
pngs = [
p
for p in input_root.rglob("*.png")
if output_dir not in p.parents
]
pngs = sorted(pngs)
if limit > 0:
pngs = pngs[:limit]
return pngs
def output_path_for(input_root: Path, output_dir: Path, image_path: Path):
rel = image_path.relative_to(input_root)
return output_dir / rel.parent / f"{image_path.stem}_gpt_image_2.png"
def write_jsonl(path: Path, record: dict):
path.parent.mkdir(parents=True, exist_ok=True)
with open(path, "a", encoding="utf-8") as f:
f.write(json.dumps(record, ensure_ascii=False) + "\n")
def improve_one(client, image_path: Path, out_path: Path, args):
out_path.parent.mkdir(parents=True, exist_ok=True)
with open(image_path, "rb") as image_file:
result = client.images.edit(
model=args.model,
image=image_file,
prompt=args.prompt,
size=args.size,
quality=args.quality,
n=1,
)
image_bytes = base64.b64decode(result.data[0].b64_json)
with open(out_path, "wb") as f:
f.write(image_bytes)
return {
"input": str(image_path),
"output": str(out_path),
"model": args.model,
"prompt": args.prompt,
}
def improve_job(job):
args, image_path, out_path = job
client = OpenAI(api_key=api_key, base_url=base_url)
return improve_one(client, image_path, out_path, args)
def main():
args = parse_args()
input_root = Path(args.input_root) if args.input_root else latest_sample_run(
ROOT / "output" / "chart_template_samples"
)
output_dir = Path(args.output_dir) if args.output_dir else input_root / "gpt_image_2_improved"
output_dir.mkdir(parents=True, exist_ok=True)
images = collect_pngs(input_root, output_dir, args.limit)
manifest = output_dir / "manifest.jsonl"
if manifest.exists() and args.overwrite:
manifest.unlink()
jobs = []
for image_path in images:
out_path = output_path_for(input_root, output_dir, image_path)
if out_path.exists() and not args.overwrite:
continue
jobs.append((args, image_path, out_path))
print(f"input_root={input_root}", flush=True)
print(f"output_dir={output_dir}", flush=True)
print(f"images={len(images)} pending={len(jobs)} workers={args.workers}", flush=True)
if args.workers > 1:
with ThreadPoolExecutor(max_workers=args.workers) as executor:
futures = [executor.submit(improve_job, job) for job in jobs]
for index, future in enumerate(as_completed(futures), 1):
record = future.result()
write_jsonl(manifest, record)
print(f"[{index}/{len(jobs)}] {record['output']}", flush=True)
else:
client = OpenAI(api_key=api_key, base_url=base_url)
for index, (_args, image_path, out_path) in enumerate(jobs, 1):
record = improve_one(client, image_path, out_path, args)
write_jsonl(manifest, record)
print(f"[{index}/{len(jobs)}] {record['output']}", flush=True)
summary = {
"input_root": str(input_root),
"output_dir": str(output_dir),
"model": args.model,
"prompt": args.prompt,
"total_images": len(images),
"submitted_images": len(jobs),
}
with open(output_dir / "summary.json", "w", encoding="utf-8") as f:
json.dump(summary, f, indent=2, ensure_ascii=False)
if __name__ == "__main__":
main()
|