MultiAngleEdit

INPUT OR STARTING POINT

Image-to-image editing. Camera angles used can be edited by the user.

Load a source image and use the QwenMultiangleCameraNode to set the desired camera angle and composition. The workflow passes the edited scene through QwenEdit and upscales the result. Adjust parameters to refine angle and framing before generating.

The first output shows the scene from the initial angle. Camera controls allow you to rotate, pan, or shift perspective while preserving scene content and style.

INPUT OR STARTING POINT

Image-to-image editing. Camera angles used can be edited by the user.

Using a different camera angle configuration produces an alternative view of the same scene. The MultiAngleEdit workflow supports multiple angle presets and custom settings for varied output compositions.

The second output demonstrates the same scene from a new perspective. Use MultiAngleEdit to explore different viewpoints for product shots, environments, or character renders without re-creating the entire scene.

How to use this workflow

Download the JSON above and open it in ComfyUI. The file contains the graph and saved settings; model weights, custom node packages and example input files are separate. Expand its subgraphs to inspect the complete pipeline before running it.

1. Load the source image

Replace the saved Image node filename with your own reference. Choose a source with a clearly visible subject and enough surrounding context to judge the changed viewpoint.

2. Set camera controls

Adjust the QwenMultiangleCameraNode controls and inspect the instruction it passes into the editing graph. Make one camera adjustment per test. Generated views are interpretations of the source; examine details and geometry instead of assuming hidden surfaces are recovered accurately.

3. Verify the editing subgraph

The Qwen-Image 2511 subgraph loads the edit model, Qwen 2.5 VL text encoder and Qwen image VAE. It also requests qwen-image-edit-2511-multiple-angles-lora.safetensors and a Lightning LoRA. Check the Enable 4steps LoRA switch and connected Steps and CFG branches before changing sampling values.

4. Generate and compare views

Run a baseline with the saved settings, then compare one changed camera setting against it. The graph includes SeedVR2 upscaling with a 4096 target and saves under 2511/2511_MultiAngleEdit_. Check whether object identity, framing and proportions still suit your intended use before choosing an output.

Missing nodes, models or memory errors?

If a node is missing, identify its exact type in the graph and install the matching custom node package from its maintainer. Restart ComfyUI after installation. If a loader cannot find a model, check the filename and loader selection against your installed files. For an out-of-memory error, reduce image dimensions or clip length before retrying. No minimum VRAM or render-time benchmark has been measured for these downloads.

Use the official ComfyUI documentation for installation and node guidance. These instructions describe the bundled JSON, rather than promising compatibility with every ComfyUI version.

Explore related workflows

Z-Image Turbo text-to-image with SeedVR2 upscaling · Z-Image Turbo depth control with SeedVR2 upscaling · Qwen Image Edit 2511 · LTX 2.3 image-to-video

More ComfyUI workflows

This earlier workflow remains available with its original graph. Explore our current image and video guides, free downloads and model licence guide.