Skip to main content
Qwen-Image-Edit-2511 is an enhanced version of Qwen-Image-Edit-2509, featuring multiple improvements including notably better consistency. This model extends Qwen-Image’s unique text rendering capabilities to editing tasks, enabling precise text editing with dual semantic and appearance editing capabilities. Key Enhancements in Qwen-Image-Edit-2511:
  • Mitigate Image Drift: Improved stability during editing operations
  • Improved Character Consistency: Better preservation of identity and visual characteristics during imaginative edits
  • Multi-Person Consistency: High-fidelity fusion of multiple person images into coherent group shots
  • Integrated LoRA Capabilities: Popular community LoRAs built directly into the base model
  • Enhanced Industrial Design Generation: Better support for batch industrial product design and material replacement
  • Strengthened Geometric Reasoning: Direct generation of auxiliary construction lines for design or annotation
Official Links:

Qwen-Image-Edit-2511 ComfyUI Native Workflow Example

Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

Qwen Image Edit 2511 - Material Replacement

Replace materials in objects (for example, furniture) by combining reference images with Qwen-Image-Edit-2511. Qwen-Image-Edit-2511 workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Qwen-Image-Edit-2511” in Template Library
Input materials Upload these files to the matching LoadImage nodes:

leather_sofa.png

LoadImage node 41 · leather_sofa.png

texture_fur.png

LoadImage node 83 · texture_fur.png
leather_sofa.pngtexture_fur.png
Example output
Input imageQwen-Image-Edit-2511 example output

1. Workflow file

After updating ComfyUI, you can find the workflow file from the templates, or drag the workflow preview above into ComfyUI to load it.

2. Model download

Text Encoders LoRA (Optional - for 4-step Lightning acceleration) Diffusion Models VAE Model Storage Location

Qwen-Image-Edit-2511 Multiple Angles with the 3D Camera Node

Load one photo, orbit a 3D camera around the subject, and Qwen-Image-Edit-2511 renders that same subject from the angle you picked. The template pairs the edit model with the multiple-angles LoRA, so you can re-shoot one input image from any angle you pick. Qwen-Image-Edit-2511 multiple angles workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Generate Multiple Angles with 3D Camera Node” in Template Library
Input material Upload this file to the LoadImage node:

cyber_genesis.png

LoadImage node 1

Camera Angle controls

The Compose Camera Angle Prompt node adds a 3D viewport above its angle fields. Pick a viewpoint in the viewport and the node writes a shot description such as front view eye-level shot medium shot into the workflow prompt, so you do not type it by hand. The angle fields follow as you move.
  • Camera / Object: Camera moves you around the subject, Object looks through the lens and turns the subject instead.
  • Horizontal angle, Vertical angle, Shot size: named positions: eight around the subject from Front to Front left, four elevations from Low angle to High angle, and three shot sizes from Wide shot to Close-up. Dragging in the 3D viewport sets the same values.
  • Preview: adds a picture-in-picture window with what the camera frame contains.
Connect an image to the node’s optional image input to show it on the front face of the subject, which makes left and right obvious while you orbit. Turbo mode (enable_turbo_mode, a control on the subgraph node) is on by default: 4 steps, CFG 1 and the 4-step Lightning LoRA. Switch it off for the 40-step, CFG 4 pass without the Lightning LoRA. Model downloads for this workflow

Diffusion model: qwen_image_edit_2511_int8_convrot

Place in ComfyUI/models/diffusion_models/

Text encoder: qwen_2.5_vl_7b_fp8_scaled

Place in ComfyUI/models/text_encoders/

VAE: qwen_image_vae

Place in ComfyUI/models/vae/

LoRA: multiple-angles

qwen-image-edit-2511-multiple-angles-lora.safetensors goes in ComfyUI/models/loras/

LoRA: Lightning 4-step

Place in ComfyUI/models/loras/
Model storage location