Skip to content
WorkflowVerifiedExternal
Open source

【QWEN】OUTPAINT — v2.0

🔄 Full Nodes 2.0 rewrite

Sourcecivitai.com/models/2100465
TaskMultiCapabilitiesImage edit · Text to image · UpscalingFamilyQwen-ImageVersionEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Verified
Version
QWEN_Outpaint_Auto.json
Source
Civitai
Updated
Oct 1, 2026

Source description

🔄 Full Nodes 2.0 rewrite

Rebuilt entirely with the UmeAiRT Toolkit pipeline (only 1 custom node needed)

SeedVR2 Upscaler and metadata saver now built-in with on/off toggles

8 nodes total — clean, visual, beginner-friendly

⚠️ Requires "Nodes V2 (Vue)" enabled in ComfyUI settings

What you need

Hardware and download-size estimates are not available yet.

Requirements

Models

2

  • QWEN/Image

    Possible

    Checkpoint · Hugging Face · QWEN/Image

  • seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors

    Not resolved

    Upscaler · Unknown

Node packs

1

  • comfyui-umeairt-toolkit

    Not resolved

    Node pack · Registry

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • 【QWEN】OUTPAINT is an 8-node ComfyUI workflow for QWEN outpainting and text-to-image generation. Give it a QWEN model and written prompt to produce images that can be saved with generation parameters.

Flow

  • A built-in SeedVR2 tiled upscaler can be switched on or off.

  • The auto version includes automatic model downloading.

  • Saved images include generation parameters for online publishing and remixing.

Inputs and outputs

  • The main inputs are a written prompt and a loaded QWEN model; the output is a generated image.

Setup

  • In ComfyUI, open Settings, turn on “Use Nodes V2 (Vue),” refresh the page, and load the workflow.

  • Install ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.

Dependencies

  • The required custom node is ComfyUI-UmeAiRT-Toolkit.

  • Manual setup lists qwen_2.5_vl_7b_fp8_scaled.safetensors, Qwen-Image-InstantX-ControlNet-Inpainting.safetensors, qwen_image_vae.safetensors, and either Qwen-Image-Lightning-8steps-V2.0.safetensors or Qwen-Image-Lightning-4steps-V2.0.safetensors.

Configuration

  • Three LoRA slots have individual on/off toggles and strength controls, and additional LoRA modules can be connected.

  • Manual setup offers base model options fp8 or bf16; GGUF model options Q8, Q5, or Q4; and GGUF CLIP options Q8, Q6, Q5, Q4, or Q3.

Cautions

  • If Nodes 2.0 (Vue) is not enabled, the workflow may have display problems.

  • Before manual setup, verify which checkpoint is intended by “QWEN/Image”; no filename is provided, and no license information is listed.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiSourceVersion 3092120
civitai.com/models/2100465

Verified Oct 1

Source excerpts

3 excerpts
NoteOct 1civitai.com/models/2100465

Source context: 1092 downloads · Type Workflows · Base model Qwen

NoteJul 18civitai.com/models/2100465

Source context: 916 downloads · Type Workflows · Base model Qwen

NoteJul 17civitai.com/models/2100465

Source context: 911 downloads · Type Workflows · Base model Qwen