$ show paolaoshi/ComfyUI-dapaoAPI
This repository is a ComfyUI custom node pack (ComfyUI-dapaoAPI) that provides a comprehensive suite of nodes for AI-powered image, video, audio, and text generation. It acts as a unified relay client to multiple commercial AI services (dapaoAI, RunningHub, Gemini, Seedance, Wan, etc.), abstracting API details, handling media preprocessing, error diagnostics, task queue persistence, and concurrent batch execution. The architecture is a classic ComfyUI extension: each node type is defined as a Python class with input/output specifications, and shared utility modules (e.g., `dreamshark_runtime` for job submission, `image_input_utils` for tensor-to-PNG conversion, `node_error_utils` for formatted error handling) are used across all generation nodes. A front-end JavaScript layer adds dynamic widget behavior, price badges, and rich prompt editors within ComfyUI's existing UI framework. The pack notably includes a hybrid nature: it bundles a `skills/` directory containing detailed markdown-based AI agent instructions (for short drama writing, music caption rewriter, article formatting, GPT image templating) that are injected into LLM prompts during node execution or used as standalone agent guides. These skills are not data pipelines but rather structured knowledge assets for prompt engineering, giving the repository a dual character as both a custom node collection and an LLM orchestration framework.
The LLM identified 4 files worth highlighting for reuse:
Provides `serialize_registered_nodes()` and `install_comfy_scheduler_wait()` to enforce per-node-ID serialization for async ComfyUI operations while allowing items within a batch to execute concurrently. This is a non-trivial solution to ComfyUI's scheduler limitations, reusable by any custom node pack needing controlled async execution without blocking the UI.
Central runtime for all generation nodes: externalizes media assets to a relay service, submits JSON tasks with idempotency keys, polls for results, and recovers from failures via a SQLite-backed queue. The `submit_json_task()` function is a reusable pattern for paid API calls with interruptible, long-polling behavior, used by every generation node in the pack.
Contains `tensor_to_png_bytes()`, `tensor_to_pil_images()`, and `prepare_image_tensor()` which convert ComfyUI image tensors to PNG/JPEG bytes with automatic 2K resolution limits and Lanczos sampling. This isolates image format handling and size constraints into a single, independently reusable module – any ComfyUI custom node dealing with image output can adopt this without duplication.
Implements `format_node_error()` that maps HTTP status codes, business error patterns, and network exceptions to user-friendly Chinese diagnostic messages, while automatically redacting API keys and tokens from error output. The error catalog (`error_message_catalog.py`) is verified by contract test `test_node_error_utils.py` to ensure every code path has a documented message – a rare and valuable pattern for maintaining actionable error handling across many nodes.