Skip to main content
Back to All Models

Qwen Image 2.1 - Image Edit

imageQwenQwen-Image2 Workflows

ComfyUI in the Cloud

Deploy Qwen Image 2.1 - Image Edit, from

$0.60 / hour

RTX A6000
Deploy with ComfyUISee every GPU option

Qwen-Image-2.1 ComfyUI Workflow

A ComfyUI image generation workflow powered by Qwen-Image-2.1, featuring INT8-quantized models, Qwen3-VL conditioning, and efficient sampling settings.

Qwen-Image-2.1 ComfyUI INT8 Quantized AI Image Generation

Workflow Overview

This workflow utilizes the Qwen-Image-2.1 model for AI image generation within ComfyUI. It combines Qwen3-VL 8B conditioning, a dedicated Qwen-Image-2.1 VAE, and an additional PE model with an image-to-image designation.

INT8 quantization helps reduce memory requirements for selected model components. The workflow is configured with the Euler sampler, 25 sampling steps, a simple scheduler, and a CFG scale of 1.0.

Generation Settings

CFG Scale

1.0

Sampling Steps

25

Sampler

Euler

Scheduler

Simple

Width

1024

Height

1024

Custom Size

Disabled

Cache Device

Auto

Model Configuration

Image Generation Model (UNet)

INT8

Comfy-Org/Qwen-Image-2.1 - qwen_image_2.1_int8_convrot

The primary image generation model responsible for the denoising process. This INT8-quantized version helps reduce memory consumption compared with higher-precision model weights.

Text / Vision Conditioning Model

Qwen3-VL 8B

Comfy-Org/Qwen3-VL - qwen3vl_8b_int8_convrot

The Qwen3-VL 8B model provides conditioning information for the image generation process, helping interpret input instructions and visual context.

Variational Autoencoder (VAE)

BF16

Comfy-Org/Qwen-Image-2.1 - qwen_image_2.1_vae_bf16

The VAE converts generated latent representations into visible images. This workflow uses the BF16 Qwen-Image-2.1 VAE.

Additional PE Model

INT8 / I2I

Comfy-Org/Qwen-Image-2.1 - qwen3.5_9b_qwen_image_2.1_pe_i2i.int8_convrot

An additional INT8-quantized PE model is included in the configuration. Its identifier suggests an image-to-image component, although its exact function depends on the connected ComfyUI nodes.

Additional Parameters

Seed 891836227295375
Data Type Default
Cache Device Auto
Custom Size Disabled

Workflow Highlights

  • ✓ Qwen-Image-2.1: Uses the Qwen image generation architecture.
  • ✓ Memory Efficiency: INT8-quantized components can help reduce model memory requirements.
  • ✓ Vision-Language Conditioning: Integrates Qwen3-VL 8B for conditioning.
  • ✓ Euler Sampling: Uses 25 sampling steps with a simple scheduler.
  • ✓ Additional I2I Component: Includes a PE model with an image-to-image designation.

Workflow Summary

This ComfyUI workflow configuration combines Qwen-Image-2.1 with Qwen3-VL 8B conditioning, INT8-quantized model components, and a BF16 VAE. It uses 25 Euler sampling steps, a simple scheduler, and a CFG scale of 1.0.

The width and height fields display 1024 × 1024 pixels. However, since custom sizing is disabled, the effective output resolution may be controlled elsewhere in the workflow.