Files

Nick ed5bf01972

Build and Push Docker Image / build (push) Successful in 3m47s

Details

Use /runpod-volume mount point for RunPod network volumes

RunPod mounts network volumes at /runpod-volume, not /userdata.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2025-12-26 23:01:08 +13:00

2.2 KiB

Raw Blame History

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

ComfyUI-based image-to-video generation service deployed on RunPod Serverless. Accepts base64 images and text prompts via RunPod API, processes them through ComfyUI workflows, and returns generated videos.

Architecture

RunPod API Request → handler.py → ComfyUI Server (port 8188) → GPU Inference → Response
                                        ↓
                              Network Volume (/runpod-volume) for models

Key flow in handler.py:

start_comfyui() - Launches ComfyUI server
upload_image() - Uploads base64 image to ComfyUI
inject_wan22_params() - Injects parameters into workflow nodes
queue_workflow() - Submits to ComfyUI queue
poll_for_completion() - Polls until done (max 600s)
fetch_output() - Retrieves generated video as base64

Build Commands

# Build Docker image
docker build -t comfyui-runpod:latest .

# Push to Gitea registry
docker push gitea.voyager.sh/nick/comfyui-serverless:latest

CI/CD via Gitea Actions triggers on push to main branch.

Local Testing

docker run --gpus all -p 8188:8188 \
  -v /path/to/models:/runpod-volume/models \
  comfyui-runpod:latest

API Input Schema

{
  "image": "base64 encoded image (required)",
  "prompt": "positive prompt (required)",
  "negative_prompt": "optional",
  "resolution": 720,
  "steps": 8,
  "split_step": 4,
  "timeout": 600
}

Workflow Node Mapping (Wan22-I2V-Remix)

Node ID	Purpose
148	LoadImage (input)
134	CLIPTextEncode (positive prompt)
137	CLIPTextEncode (negative prompt)
147	Resolution
150	Steps
151	Split Step
117	SaveVideo (output)

Stack

CUDA 12.8.1, Python 3.12, PyTorch 2.8.0+cu128
SageAttention 2.2 (compiled from source with --no-build-isolation)
Nunchaku 1.0.2
12 ComfyUI custom nodes (see Dockerfile)

Key Considerations

Models stored on RunPod Network Volume at /runpod-volume/models/
Cold start ~30-60s for ComfyUI initialization
Large outputs (>10MB) returned as file paths, not base64
Workflow files in workflows/ directory (API format)

2.2 KiB Raw Blame History