installation was not complicated, but I also could not get it to work this way.
I installed it on embedded python - there are quite a few models - C:\Users\YOUR_USERNAME\.cache\huggingface\hub\ - 30.8 GB
Then I created two python files in the installation folder E:\DiTServerRPC
rpc_wrapper.py
from dit_client_example import main as _run_single
def colorize_image(image_path: str):
"""
Wrapper around working CLI logic.
Returns bytes of output image.
"""
# It just uses the existing working flow
# (we do not touch the RPC logic)
return _run_single(image_path)
batch_colorize_turbo.py
import xmlrpc.client
import io
from pathlib import Path
from PIL import Image
import time
# =========================
# CONFIG
# =========================
HOST = "127.0.0.1"
PORT = 8765
INPUT_DIR = Path("assets")
OUTPUT_DIR = Path("output")
OUTPUT_DIR.mkdir(exist_ok=True)
SUPPORTED = {".png", ".jpg", ".jpeg", ".webp"}
PROMPT = "Colorize this photo, natural skin tones, cinematic lighting"
STEPS = 4
# =========================
# HELPERS
# =========================
def pil_to_bytes(img):
buf = io.BytesIO()
img.save(buf, format="PNG")
return buf.getvalue()
def bytes_to_pil(data):
raw = data.data if hasattr(data, "data") else data
return Image.open(io.BytesIO(raw)).convert("RGB")
# =========================
# MAIN
# =========================
def main():
print("🚀 Connecting...")
server = xmlrpc.client.ServerProxy(
f"http://{HOST}:{PORT}/",
use_builtin_types=True
)
server.ping()
print("✅ Server OK")
images = sorted([
p for p in INPUT_DIR.iterdir()
if p.suffix.lower() in SUPPORTED
])
print(f"🚀 Found {len(images)} images")
start = time.perf_counter()
# 🔥 IMPORTANT: SERIAL (GPU-safe)
for img_path in images:
print(f"[RPC] {img_path.name}")
img = Image.open(img_path).convert("RGB")
try:
result = server.colorize_frame(
pil_to_bytes(img),
PROMPT,
0,
STEPS
)
if not result["ok"]:
print(f"❌ ERROR: {result['msg']}")
continue
out = bytes_to_pil(result["data"])
out_path = OUTPUT_DIR / img_path.name
out.save(out_path)
print(f"✅ Saved: {out_path}")
except Exception as e:
print(f"❌ ERROR {img_path.name}: {e}")
print(f"\n⚡ TOTAL TIME: {time.perf_counter() - start:.2f}s")
if __name__ == "__main__":
main()
I added this function to the existing dit_client_example.py
I run it with this command in powershell
cd E:\DiTServerRPC
E:\python_embeded\python.exe dit_rpc_server.py --load-pipeline --pipeline-config qwen_config_fp4.json
then in another powershell window
cd E:\DiTServerRPC
E:\python_embeded\python.exe batch_colorize_turbo.py
What it does is the following - it takes the frames one by one from the folder "E:\DiTServerRPC\assets" and processes them one after the other automatically in the folder "E:\DiTServerRPC\output" while keeping the same name, resolution and jpg format.
The result is an average of 9 seconds per image, uses an average of 23 GB of gpu memory and 39 GB of ram during the process /my card is rtx5090/, It is probably possible to improve the time, but it will be at the expense of quality. It does not colorize quite evenly - on different frames the same thing sometimes colors it differently - probably a lot depends on what is set in the prompt.
Once again, thanks to Dan and Selur for what they have done.
