HAVC Server DiT

Hybrid Automatic Video Colorizer (HAVC) server that exposes a GPU-accelerated colorization pipeline for black-and-white images and video frames based on Diffusion Transformer (DiT) models.

5 backends, one API : pick the one that fits your hardware:

• nunchaku-qwen: SVDQuant FP4/INT4 transformer via Nunchaku : 4 sec/frame¹, requires RTX 30/40/50 (16GB+ VRAM, 64GB RAM) & CUDA 13.0
• gguf-qwen: Qwen-Image-Edit 2511 (native int8 ConvRot or GGUF Q3_K_S) : ~7.3 sec/frame¹ (Fast Pipeline) or ~10.5 sec/frame, runs on RTX 30/40/50 (12GB+ VRAM with Q3_K_S, 16GB+ with int8; 32GB+ RAM with Q3_K_S, 48GB+ with int8), zero ComfyUI GUI dependency
• longcat-gguf: LongCat-Image-Edit-Turbo GGUF pipeline (Q3_K_M–Q8_0) : ~12 sec/frame², runs on RTX 30/40/50 (12GB+ VRAM, 32GB+ RAM), better image quality than gguf-qwen, zero ComfyUI GUI dependency
• qwen21-viggle: Qwen-Image-2.1 (native ComfyUI int8 ConvRot UNet) + Viggle-Turbo LoRA : ~3 sec/frame¹ (Fast Pipeline) or ~6 sec/frame, runs on RTX 30/40/50 (14GB+ VRAM; 12GB with Fast Pipeline; 32GB+ RAM), optional enhance_prompt (Qwen3-VL image-aware prompt rewriting)
• qwen21-turbo: Qwen-Image-2.1-Turbo (native ComfyUI int8 ConvRot UNet) : ~4.5 sec/frame¹ (single split) or ~2.3 sec/frame with the paired split (fast_split_TE), runs on RTX 30/40/50 (14GB+ VRAM; 12GB with Fast Pipeline; 32GB+ RAM), richer colors than qwen21-viggle but less stable between similar frames — the shipped default stays qwen21-viggle

¹ Measured with Fast Pipeline — the cached text-encoder split for qwen21-viggle, qwen21-turbo (the ~2.3 s/frame figure: its paired fast_split_TE variant) and gguf-qwen, paired inference for nunchaku-qwen. ² longcat-gguf has no Fast Pipeline path — single-image time, not directly comparable. Steady-state per-frame times, warm-up excluded; the gguf-qwen figure comes from a 17-frame test at 2 steps. Speed/hardware/quality trade-offs, the recommended picks and the full measurement notes: docs/backends.md.

📥 Install

Installer (recommended) — download HAVC-Setup-<version>.exe from the Releases page and run it: a single self-contained file (no .NET runtime needed) that installs the pinned Python runtime, the server stack, the GUI, external tools and the vs-cmnet2 plugins/weights — and keeps everything updated (Check for updates, Repair, Uninstall from the manager). Model weights are downloaded on first use and preserved across updates. Details: docs/installation.md.

⚠️ Windows SmartScreen will warn on first run because the exe is not code-signed: More info → Run anyway. The sha256 of every asset is published in the release notes.

Manual installation (advanced) — clone the repository and run install.cmd (requires Git + Python 3.12): step-by-step instructions in docs/installation.md.

🚀 Quick start

From the install folder (or the repository root on a manual install):

HAVC.vbs               # desktop GUI (the recommended front-end)
HAVC-Server.cmd        # console server — optional arg: alias or config name (no arg: int4)
start_server.cmd q3    # console server with a backend/quantization or a config name

CLI arguments, the full launch-script reference and the suggested inference steps: docs/server_usage.md.

📋 Requirements

• Windows 10/11, NVIDIA RTX 30/40/50 GPU, CUDA 13.0+
• VRAM / RAM by backend: nunchaku-qwen 16 GB+ / 64 GB+ · gguf-qwen 12 GB+ (qwen-2511_q3) or 16 GB+ (qwen-2511_int8) / 32 GB+ (qwen-2511_q3) or 48 GB+ (qwen-2511_int8) · longcat-gguf 12 GB+ / 32 GB+ · qwen21-viggle / qwen21-turbo 14 GB+ (12 GB+ with Fast Pipeline) / 32 GB+ — details
• Disk: a few GB for the software stack; model weights (up to tens of GB for the largest configs) are downloaded on first use

✨ Features

• 📦 5 backends, one API : nunchaku-qwen (FP4/INT4, 4 sec/frame) for speed, gguf-qwen (Qwen-Image-Edit 2511: native int8 ConvRot or Q3_K_S, ~7.3 sec/frame with Fast Pipeline) and longcat-gguf (Q3, …, Q8) for lower VRAM, qwen21-viggle (int8 ConvRot UNet, ~3 sec/frame with Fast Pipeline) with optional Qwen3-VL prompt rewriting, qwen21-turbo (Qwen-Image-2.1-Turbo, ~2.3 sec/frame with the paired split) for the richest colors
• 🎨 Batch colorization : process entire directories of B&W images via filesystem paths
• 🖼️ Paired inference : colorize two images in a single forward pass (faster, temporally consistent)
• 📡 In-memory RPC : pass raw PNG frames over XML-RPC without touching the filesystem (ideal for video pipelines)
• ⚡ 4-step lightning model : SVDQuant FP4 quantized transformer for maximum throughput
• 🔒 Thread-safe : pipeline loading and stop control are protected by locks; every RPC call runs in its own thread
• ⚙️ Startup preload : optional --load-pipeline flag loads the model at boot from a JSON config file
• 🚀 Shared memory transport : zero-copy image transfer for same-host deployments (~23% faster than standard RPC)

---

📚 Documentation

• Installation — installer, manual setup, updating, project layout
• Backends & requirements — choosing the right backend
• Server usage — server startup, launch scripts, CLI arguments, suggested steps
• Pipeline configuration — config files and key reference
• RPC API — XML-RPC API, example clients, shared-memory transport
• GUI usage — the desktop client
• Troubleshooting
• What's New — changelog

🔗 Credits

• Model: Qwen/Qwen-Image-Edit-2511, Qwen/Qwen-Image-2.1, LongCat-Image-Edit-Turbo
• VapourSynth filter for video colorization with CMNET2: vs-cmnet2
• Viggle-Turbo LoRA: Viggle/Qwen-Image-2.1-viggle-turbo
• Nunchaku quantization: Nunchaku / SVDQuant
• GGUF dequantization kernels: adapted from ComfyUI-GGUF (Apache 2.0), Qwen3-VL mmproj support from the ComfyUI-GGUF-Reboot fork (molbal)
• Pipeline: Hugging Face Diffusers