Skip to content
WorkflowListedExternal
Open source

Anaglyph maker (Stereogram) — v1.0

👓 Qwen Any to Stereogram – ComfyUI Workflow

VersionRelease 3199660 — anaglyphMaker_v10.jsonEstimated VRAMNot yet characterizedDgrade

Runtime profile

Access
External workflow
Status
Listed
Version
anaglyphMaker_v10.json
Source
Civitai
Updated
Oct 16, 2026

Source description

👓 Qwen Any to Stereogram – ComfyUI Workflow

Created by Me – a filmmaker & AI workflow designer. This tool transforms any single image into a stereoscopic 3D stereogram – perfect for creating immersive 3D content, VR assets, or classic 3D viewing experiences. It generates multiple formats: Side‐by‐Side (SBS) , Anaglyph (Red‐Cyan) , Black‐&‐White Anaglyph , and standalone left/right eye views – all from one input image.


🧩 Overview

This workflow takes a 2D image, generates a left‐eye and right‐eye view using Qwen‐Image with a specialised Stereogram LoRA , then processes them into several stereoscopic formats:

  • Side‐by‐Side (SBS) – for VR headsets, 3D TVs, or cross‐eye viewing.

  • Anaglyph (Red‐Cyan) – for classic 3D glasses (colour and black‐&‐white variants).

  • Separate left/right images – for further custom compositing.

The result is a believable 3D depth effect that works with standard 3D viewing methods.


1️⃣ Required Models & Prerequisites

Make sure these files are placed in your ComfyUI models/ folders:

| Folder | Required Files |

|--------|----------------|

| diffusion_models/ | qwen_image_edit_2509_fp8_e4m3fn.safetensors (or qwen_image_edit_2511_bf16 ) |

| loras/ | Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors Create Stereogram - Qwen Edit 2509_(Make stereogram).safetensors |

| text_encoders/ | qwen_2.5_vl_7b_fp8_scaled.safetensors |

| vae/ | qwen_image_vae.safetensors |

⚠️ VRAM Requirement: ~8–10 GB recommended – the workflow uses Qwen‐Image with Lightning LoRA for fast 4‐step generation.


3️⃣ How It Works (2D → Stereogram in 5 Steps)

  1. Load your image – any 2D image (portrait, landscape, concept art, etc.).

  2. Generate left & right views – the image is passed through Qwen‐Image with the Stereogram LoRA to produce two slightly offset views (simulating binocular disparity).

  3. Side‐by‐Side assembly – the left and right images are stitched together horizontally using ImageStitch to create a classic SBS stereogram.

  4. Anaglyph creation – colour channels are merged (Red from left view, Cyan/Green+Blue from right view) to produce a red‐cyan anaglyph compatible with classic 3D glasses. A black‐&‐white variant is also generated by desaturating the image before channel merging.

  5. Save all formats – multiple outputs are saved: SBS, left‐only, right‐only, colour anaglyph, half‐colour anaglyph, and B&W anaglyph – all with descriptive prefixes.


6️⃣ Advanced Settings (Optional)

  • SEED – set a fixed seed for reproducible left/right view generation.

  • Positive Prompt – customise the prompt to guide the stereogram generation (default: "Make stereogram" ).

  • Negative Prompt – exclude unwanted elements (e.g., "low quality, bad anatomy..." ).

  • Hue / Saturation / Brightness – the workflow includes adjustable color‐grading nodes (HSL/HSB) to fine‐tune the anaglyph output (e.g., adjust red‐cyan balance).

  • Output Formats – you can choose which formats to save by connecting/disconnecting SaveImage nodes.


📦 Final Output

After running, you’ll get a set of stereogram files in your output folder:

  • Qw_SBS_*.png – Side‐by‐Side format (ready for 3D TVs/VR).

  • Qw_SBS_Left_.png / Qw_SBS_Right_.png – individual eye views.

  • Qw_SBS_Anaglyph_Color_*.png – red‐cyan anaglyph (full colour).

  • Qw_SBS_Anaglyph_Black&White_*.png – black‐&‐white anaglyph (often sharper and more comfortable for long viewing).

  • Qw_SBS_Anaglyph_Half_*.png – a half‐colour variant.


Why I built this: As a filmmaker, I often work with 3D concepts, VR storyboards, or want to give clients a quick 3D preview of a scene. This workflow turns any 2D concept into a stereoscopic experience in seconds – no complex 3D software needed. It’s perfect for pre‐visualisation, VR content creation, or just having fun with 3D! I hope it brings a new dimension to your creative projects! 👓✨


📬 Contact: If you’d like to donate, ask a question, or order a custom workflow, reach out to me on Civitai (SaeedKhalili) , visit my website SaeedKhalili.com , or email me at [email protected] . I’m always happy to help fellow creators!

What you need

Model files
9.5 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

5

Sources

1 source
CivitaiPrimaryVersion 3199660
civitai.com/models/2835167

Verified Oct 16

Source excerpts

1 excerpt

Source context: 78 downloads · Type Workflows · Base model Qwen