jtydhr88/ComfyUI-qwenmultiangle

A ComfyUI custom node for 3D camera angle control. Provides an interactive Three.js viewport to adjust camera angles and outputs formatted prompt strings for multi-angle image generation.

What it solves

This project provides a visual, interactive way to control camera angles for image generation, specifically designed for use with the Qwen-Image-Edit-2511-Multiple-Angles-LoRA. Instead of guessing text prompts for camera positions, users can manipulate a 3D viewport to precisely define the perspective.

How it works

It is a custom node for ComfyUI that integrates a Three.js-powered 3D scene. Users can adjust the camera's horizontal angle (azimuth), vertical angle (elevation), and zoom level using three methods: dragging handles in the 3D viewport, using slider widgets, or selecting presets from dropdown menus.

The node then converts these 3D coordinates into a formatted prompt string (e.g., <sks> front view eye-level shot medium shot) that the LoRA can understand. It also includes a translation node to convert these camera terms into Chinese, Japanese, or Korean to maintain language consistency with the base prompt.

Who it’s for

Digital artists and AI image generators using ComfyUI who want precise, intuitive 3D camera control over their generated images without manually writing complex angle descriptions.

Highlights

  • Interactive 3D Viewport: Use a Three.js scene to visually adjust camera angles and zoom.
  • Bidirectional Sync: Changes in the 3D viewport, sliders, and dropdowns are all synchronized in real-time.
  • Camera View Mode: Toggle a perspective view to see exactly what the camera is seeing.
  • Preset Camera Angles: Quick-select menus for common shots like "wide shot" or "high-angle shot".
  • Multi-language Support: UI labels and a dedicated translation node for camera prompts in multiple languages.

Related

  • Project
    Gourieff/ComfyUI-ReActor

    A set of ComfyUI nodes for fast and simple face swapping in images and videos, featuring face restoration and blended face model creation.

  • Project
    ShiftHackZ/Stable-Diffusion-KMP

    An open-source, cross-platform AI image generation client for Android and iOS that connects to self-hosted Stable Diffusion servers, cloud APIs, and local on-device runtimes.

  • Project
    FireRedTeam/FireRed-Image-Edit

    A general-purpose image editing model that provides high-fidelity, consistent edits with strong identity preservation and multi-element fusion capabilities.

  • Project
    ModelTC/LightX2V-Qwen-Image-Lightning

    A distilled, faster version of the Qwen‑Image text‑to‑image model (4‑ or 8‑step diffusion) with fp32/bf16/fp8 checkpoints, LoRA adapters, and ready‑to‑use ComfyUI workflows. Provides 12–25× speed‑up with modest quality loss and integrates with Diffusers, ComfyUI, Nunchaku, and Cache‑dit.