Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > ComfyUI-3d-photo-inpainting

ComfyUI Extension: ComfyUI-3d-photo-inpainting

Repo Name

ComfyUI-3d-photo-inpainting

Author
aifsh (Account age: 1105 days)
Nodes
View all nodes(1)
Latest Updated
2024-06-19
Github Stars
0.02K

How to Install ComfyUI-3d-photo-inpainting

Install this extension via the ComfyUI Manager by searching for ComfyUI-3d-photo-inpainting
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-3d-photo-inpainting in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

ComfyUI-3d-photo-inpainting Description

ComfyUI-3d-photo-inpainting turns a single image into a depth-enhanced video by estimating depth, filling hidden areas, and simulating camera moves such as zoom, dolly zoom, swing, and circle.

ComfyUI-3d-photo-inpainting Introduction

ComfyUI-3d-photo-inpainting is a ComfyUI custom node that uses the 3d-photo-inpainting project to turn a single image into a video with simulated camera movement. The original readme names four motions: zoom-in, dolly zoom, swing, and circle. This can help you give a still illustration or photograph a sense of depth without creating a full 3D scene. (github.com)

The effect is an interpretation of one image, not a reconstruction of a scene from every angle. The system estimates what is near and far, then generates content for areas that become visible as the viewpoint moves. Because those newly revealed areas were not present in the source image, they may not always match what you imagined. (github.com)

How ComfyUI-3d-photo-inpainting Works

Think of your image as a small stage set. A foreground subject sits closer to the camera, while the background sits farther away. Moving a virtual camera makes those layers shift by different amounts, creating parallax, the depth effect you notice when nearby objects appear to move faster than distant ones. (github.com)

The underlying 3d-photo-inpainting method builds this effect in three broad steps:

  1. Estimate depth. It determines which parts of the image appear closer or farther away.
  2. Fill hidden areas. When camera movement reveals a space behind an object, inpainting generates plausible color and depth for that space.
  3. Render the motion. It uses the resulting layered image to produce a moving view. (github.com)

For example, if a person stands in front of a landscape, a swing motion can shift the person relative to the background. The method must also invent portions of the landscape that the person concealed in the original image. This explains both the appeal of the effect and why some images may show visible artifacts around object edges. (github.com)

ComfyUI-3d-photo-inpainting Features

The extension’s original readme identifies these video motions:

  • Zoom-in: Moves the view closer to the image, drawing attention toward its center.
  • Dolly zoom: Combines camera movement and a changing view angle for a more dramatic perspective effect. The underlying project assumes the subject of focus is at the center of the image for its dolly-zoom-in result, so composition matters when choosing an image. (github.com)
  • Swing: Moves the viewpoint from side to side, making foreground and background separation easier to see.
  • Circle: Moves the viewpoint along a circular path to show the scene’s depth from changing directions. (github.com)

These describe the available motion types, not specific controls in the ComfyUI node. The supplied extension readme does not document its inputs, adjustable settings, or output options, so this guide does not assume that every setting in the underlying project is exposed in ComfyUI.

Troubleshooting ComfyUI-3d-photo-inpainting

The motion reveals strange-looking areas behind a subject. Those areas were hidden in the original image and must be generated. Try an image with clearer separation between foreground and background, or choose a motion that reveals less of the hidden area. This is a practical way to limit how much unseen content the effect has to invent. (github.com)

The dolly zoom does not emphasize the intended subject. Check whether the subject is near the center of the source image. The underlying project’s dolly-zoom-in effect assumes a centered focus. (github.com)

Does this create a complete 3D model? The underlying method creates a layered representation for rendering new views from one image. That is different from capturing a complete scene that can be viewed accurately from any angle. (github.com)

Which motion should you try first? Choose based on the feeling you want: zoom-in for a direct move toward the subject, swing for an easy-to-see parallax effect, circle for a changing viewpoint, or dolly zoom for a more dramatic perspective effect. These are creative starting points, not guaranteed results for every image.

Learn More about ComfyUI-3d-photo-inpainting

  • 3d-photo-inpainting project: The original method and project readme, credited by the extension’s author. It includes examples of the supported motion outputs. (github.com)
  • Project website: Visual examples that can help you understand the depth effect before trying it on your own images. (github.com)
  • Research paper: A deeper explanation of the layered-depth and inpainting method for readers interested in how the effect is produced. (github.com)

ComfyUI-3d-photo-inpainting Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

ComfyUI-3d-photo-inpainting detailed guide | ComfyUI