Home Creators Posts Import Register Favorites Logout

Content

Qwen Image Edit 2511 is a free, open source image editor that challenges Nano Banana Pro, with native 2560x2560 output in 12 steps, even on 6 GB GPUs.

The tutorial shows how 2511 crushes Qwen Image Edit 2509 in 12 hard cases such as photo restoration, object removal and style transfer, then installs it in SwarmUI with the ComfyUI backend, the model downloader, the FP8 Scaled model and ready presets.

Full tutorial link > https://www.youtube.com/watch?v=YfuQuOk2sB0

Qwen Image Edit 2511 (Free & Open Source) Crushes Qwen Image Edit 2509 & Challenges Nano Banana Pro

Qwen Image Edit 2511 model just published and it is literally competing against Nano Banana Pro at image editing tasks. With native whopping 2560x2560 pixels image output capability and with only 12 steps it is next level. With our installers and specially made Quant FP8 Scaled model, you can run this amazing beast even as low as 6 GB GPUs. In this tutorial, I have compared Qwen Image Edit 2511 with previous successor model Qwen Image 2509 with 12 different unique and hard prompts and cases. Everything is step by step explained and provided.

📂 Resources & Links:

Video Chapters:

  • 00:00:00 Intro to Qwen Image Edit 2511: Replacing a Hat with a Sports Cap Demo

  • 00:00:47 Tutorial Roadmap: SwarmUI, One-Click Installer, FP8 Model, and Hardware Requirements

  • 00:01:43 Case 1 Comparison: Photo Restoration and Colorization (2509 vs 2511)

  • 00:02:36 Resource Info: How to Access the Zip File with All Case Prompts and Images

  • 00:03:05 Case 2 Comparison: Adding a Beard While Maintaining Facial Identity and Realism

  • 00:03:56 Case 3 Comparison: Converting a Real Person into Retro Style Pixel Art

  • 00:04:24 Case 4 Comparison: Combining Three Different Anime Heroes into One Epic Scene

  • 00:05:13 Case 5 Comparison: Removing an Object (Dog) While Preserving Background Details

  • 00:06:00 Case 6 Comparison: Transforming Day Lighting to Realistic Night Time

  • 00:06:38 Case 7 Comparison: Changing Specific Object Color (Rabbit) to Purple

  • 00:07:14 Case 8 Comparison: Changing Clothing Styles While Keeping Body Proportions

  • 00:07:54 Case 9 Comparison: Inpainting a Specific Object (Perfume Bottle) into a Hand

  • 00:08:52 Case 10 Comparison: Zero-Shot Style Transfer (Redrawing a Car Sketch)

  • 00:09:49 Case 11 Comparison: Converting Anime Characters into Realistic Human Renders

  • 00:10:55 Case 12 Comparison: Turning Real Photos into High-Quality Anime Style

  • 00:11:32 Installation Step 1: Updating ComfyUI to Support New Custom Nodes

  • 00:12:45 Installation Step 2: Setting up the SwarmUI Model Downloader Script

  • 00:13:08 Installation Step 3: Downloading the Qwen Image Core Bundle and Verification

  • 00:13:35 Installation Step 4: Updating SwarmUI to the Latest Version via Batch File

  • 00:13:52 Installation Step 5: Importing the "Amazing SwarmUI Preset Version 40"

  • 00:14:47 Configuration: Setting Base Resolution to 1920x1920 for Best Performance

  • 00:15:33 Live Workflow 1: Single Image Editing and "Closest Aspect Ratio" Strategy

  • 00:16:32 Hardware Monitoring: RAM Usage, SageAttention, and 6GB GPU Optimization

  • 00:17:36 Live Workflow 2: Combining Multiple Input Images with 16:9 Aspect Ratio

  • 00:18:35 Performance Analysis: Generation Speed (Steps/Sec) and Power Usage on RTX 5090

  • 00:19:44 Live Workflow 3: Fast Single Image Edit and Reference to Wan 2.2 Tutorial

  • 00:20:41 Tools: Installing and Using the Image and Video Slider Application

  • 00:21:56 High-Res Experiment: Pushing Resolution to 2560x2560 for Maximum Quality

  • 00:22:28 High-Res Monitoring: Analyzing VRAM Usage and Generation Time Increase

  • 00:23:18 Final Verdict: Why 2560x2560 is the Best Resolution for Qwen Image Edit 2511

In this comprehensive tutorial, I demonstrate the incredible power of the new Qwen Image Edit 2511 model, comparing it directly against the previous 2509 version across 12 distinct test cases. You will see how this model achieves "Google Nano Banana Pro" levels of quality in photo restoration, style transfer, object replacement, and multi-image composition.

I have prepared a custom FP8 scaled version of the model that allows it to run on GPUs with as little as 6GB VRAM while maintaining near-BF16 quality. This guide covers everything from a full 12-case comparison to a complete step-by-step installation guide using SwarmUI and ComfyUI.

📂 In this video, you will learn:

  • How to install Qwen Image Edit 2511 with a one-click installer.

  • How to use the new "Amazing SwarmUI Preset v40" for optimal results.

  • A side-by-side comparison of 2509 vs. 2511 (Restoration, Pixel Art, Anime-to-Real, and more).

  • How to combine up to 3 images into a single generated scene.

  • Optimal resolution settings (1920x1920 vs 2560x2560) for maximum accuracy.

  • How to use the Image and Video Slider Application for professional comparisons.

Qwen Image Edit 2509 vs 2511 Comparisons

0

Related posts

All posts in this topic: AI Image Generation and Editing Apps · New to SECourses? Start Here: Best and Most Popular SECourses Posts

Files

Qwen Image Edit 2511 (Free & Open Source) Crushes Qwen Image Edit 2509 & Challenges Nano Banana Pro

Qwen Image Edit 2511 model just published and it is literally competing against Nano Banana Pro at image editing tasks. With native whopping 2560x2560 pixels image output capability and with only 12 steps it is next level. With our installers and specially made Quant FP8 Scaled model, you can run this amazing beast even as low as 6 GB GPUs. In this tutorial, I have compared Qwen Image Edit 2511 with previous successor model Qwen Image 2509 with 12 different unique and hard prompts and cases. Everything is step by step explained and provided. 📂 Resources & Links: SwarmUI Installer, Model Auto Downloader and Presets: [ https://www.patreon.com/posts/SwarmUI-Install-Download-Models-Presets-114517862 ] SwarmUI & ComfyUI Setup Guide for Windows: [ https://youtu.be/c3gEoAyL2IE ] ComfyUI Installer: [ https://www.patreon.com/posts/ComfyUI-Installers-105023709 ] Image and Video Comparison Slider App: [ https://www.patreon.com/posts/Compare-Images-Videos-Slider-App-133935178 ] Wan 2.2 Model Training Tutorial: [ https://youtu.be/ocEkhAsPOs4 ] SwarmUI & ComfyUI Setup Guide for RunPod & Massed Compute: [ https://youtu.be/bBxgtVD3ek4 ] Upload / Download Big Files Guide for RunPod & Massed Compute: [ https://youtu.be/X5WVZ0NMaTg ] ⏱️ Video Chapters: 0:00 Intro to Qwen Image Edit 2511: Replacing a Hat with a Sports Cap Demo 0:47 Tutorial Roadmap: SwarmUI, One-Click Installer, FP8 Model, and Hardware Requirements 1:43 Case 1 Comparison: Photo Restoration and Colorization (2509 vs 2511) 2:36 Resource Info: How to Access the Zip File with All Case Prompts and Images 3:05 Case 2 Comparison: Adding a Beard While Maintaining Facial Identity and Realism 3:56 Case 3 Comparison: Converting a Real Person into Retro Style Pixel Art 4:24 Case 4 Comparison: Combining Three Different Anime Heroes into One Epic Scene 5:13 Case 5 Comparison: Removing an Object (Dog) While Preserving Background Details 6:00 Case 6 Comparison: Transforming Day Lighting to Realistic Night Time 6:38 Case 7 Comparison: Changing Specific Object Color (Rabbit) to Purple 7:14 Case 8 Comparison: Changing Clothing Styles While Keeping Body Proportions 7:54 Case 9 Comparison: Inpainting a Specific Object (Perfume Bottle) into a Hand 8:52 Case 10 Comparison: Zero-Shot Style Transfer (Redrawing a Car Sketch) 9:49 Case 11 Comparison: Converting Anime Characters into Realistic Human Renders 10:55 Case 12 Comparison: Turning Real Photos into High-Quality Anime Style 11:32 Installation Step 1: Updating ComfyUI to Support New Custom Nodes 12:45 Installation Step 2: Setting up the SwarmUI Model Downloader Script 13:08 Installation Step 3: Downloading the Qwen Image Core Bundle and Verification 13:35 Installation Step 4: Updating SwarmUI to the Latest Version via Batch File 13:52 Installation Step 5: Importing the "Amazing SwarmUI Preset Version 40" 14:47 Configuration: Setting Base Resolution to 1920x1920 for Best Performance 15:33 Live Workflow 1: Single Image Editing and "Closest Aspect Ratio" Strategy 16:32 Hardware Monitoring: RAM Usage, SageAttention, and 6GB GPU Optimization 17:36 Live Workflow 2: Combining Multiple Input Images with 16:9 Aspect Ratio 18:35 Performance Analysis: Generation Speed (Steps/Sec) and Power Usage on RTX 5090 19:44 Live Workflow 3: Fast Single Image Edit and Reference to Wan 2.2 Tutorial 20:41 Tools: Installing and Using the Image and Video Slider Application 21:56 High-Res Experiment: Pushing Resolution to 2560x2560 for Maximum Quality 22:28 High-Res Monitoring: Analyzing VRAM Usage and Generation Time Increase 23:18 Final Verdict: Why 2560x2560 is the Best Resolution for Qwen Image Edit 2511 In this comprehensive tutorial, I demonstrate the incredible power of the new Qwen Image Edit 2511 model, comparing it directly against the previous 2509 version across 12 distinct test cases. You will see how this model achieves "Google Nano Banana Pro" levels of quality in photo restoration, style transfer, object replacement, and multi-image composition. I have prepared a custom FP8 scaled version of the model that allows it to run on GPUs with as little as 6GB VRAM while maintaining near-BF16 quality. This guide covers everything from a full 12-case comparison to a complete step-by-step installation guide using SwarmUI and ComfyUI. 📂 In this video, you will learn: How to install Qwen Image Edit 2511 with a one-click installer. How to use the new "Amazing SwarmUI Preset v40" for optimal results. A side-by-side comparison of 2509 vs. 2511 (Restoration, Pixel Art, Anime-to-Real, and more). How to combine up to 3 images into a single generated scene. Optimal resolution settings (1920x1920 vs 2560x2560) for maximum accuracy. How to use the Image and Video Slider Application for professional comparisons.

Comments

Hipno

You weren't kidding 25 11 smashes 25 09! Wow!!

Diggy Dre

I don't know why but mine is stuck at: User local requested 1 image with model 'Qwen_Image_Edit_2511_Quant_Scaled_FP8.safetensors'... I have a 4080 and I did a fresh Swarm install. My 4080 fans aren't even spinning up. I can do FLUX and SDXL just fine.

Raffaele Massaro

Hi Furkan, yesterday it was faster, I don't understand what I changed, but today it takes a long time. I have a 12 GB GTX 3060 and it takes 215.38 seconds for step.

SECourses

restart pc. somehow it fails to do proper block swapping. happens to me too. disable all startup apps

SECourses

did you download the model? checking your disk reading writing? did you make a fresh comfyui backend?

Diggy Dre

It eventually started going. It's just extremely slow, and I don't know why. It's like it isn't block swapping or something.

cool1

Thanks for the comparisons/video (I'll check the video later). But in the attached comparison images, in image 2 (of the old photo of a family), the top image says "qwen image edit 2509" at the top of it and the bottom image also says "qwen image edit 2509" at the top of it. I assume one of them (probably the bottom image) is supposed to show "qwen image edit 2511". The bottom image of image 2 shows less scratches so I assume that's the "better" image and so is probably "qwen image edit 2511" (and maybe mislabeled), but the prompt said "restore this old photo" and the top image removed some of the scratches but also coloured the man's jacket and the bottom image removed all/nearly all scratches and also (almost?) fully coloured the image. But recolouring the image isn't restoring it (to what it would have been like originally). It's altering it to look more like a modern photo. The lower image has also changed the dress (lengthened and position of the flowers changed) more on the right side of the image (so it's less accurate than the first image). So neither was fully correct. Though I assume the 2nd image could just be used and then converted to greyscale after if you want it to be more 'restored' rather than changed.

SECourses

restore also includes coloring so i say it is very accurate

cool1

Though the 2nd one altered things like the dress so that bit wasn't accurate. Dictionary.com for restore says "To bring back to a former, original, or normal condition, as a building, statue, or painting. ". Colourizing it isn't bringing it back to it's original (unscratched) condition. It's updating it to something new (even though it was taken before colour film probably existed) rather than restoring it to its original condition. Though maybe saying in the prompt something like "repair damage only, keep grayscale" might have helped to restore it to its original condition if enhancement (colourizing) wasn't wanted.

SECourses

well that wasnt my aim but yes you can work on prompting

sapheswim (edited)

Comment edits

2026-09-07 10:00 could u please up the comfyui workflow for someone dont need install swarmui.thx a lot
2025-12-27 22:07

SECourses

I really recommend to get swarmui. Make it work there. Then you can export swarmui generated workflow and use it in comfyui. Best way. I can make a tutorial for this hopefully tomorrow

SECourses

i am working on a tutorial right now. yes few nodes will be needed like load image but you can do them

SECourses

yep will show. our latest comfyui installer auto installs it

Lee

I may be going slightly mad, but having overwritten swarmui files with the latest download (v115) I see no Qwen 2511 models in the core bundle, which is a total size of 38.13 GB and 16 models, not 56.68 GB and 18 models as per the video.

SECourses

it is there 🖼️ Qwen Image Core Bundle (Total: 56.68 GB, 18 models) ▼ make sure to overwrite all especially utilities folder you can delete all files except swarmui installation folder and extract to be sure

Lee

Thank you, my bad - I didn't overwrite utilities

Diggy Dre

It takes almost 30 minutes for an image with this model on my RTX 4080. That's if it is even using my 4080. The fans aren't coming on on it when I use this model, but if I switch to FLUX or SDXL, my GPU fans do engage, and I get an image quickly. I even went into my bios and disabled my iGPU since I am always plugged into my nVidia card, and that made no difference.

SECourses

how much RAM you have? go to advanced sampling and find preferred dtype and make it FP8 e4m3fn (8 bit) restart pc try and let me know

Diggy Dre

My setup is the 9950x with 64GB of RAM and the RTX4080. I will go change the dtype to FP8 and get back to you. THank you for the reply.

Diggy Dre

I tried, but it will not allow me to change it. The button won't activate, and the drop-down menu is stuck on: Automatic (decide by model)

Diggy Dre

UPDATE: I was able to change the DType. It is still going slow... although I feel it is a tad faster. I am wondering why this is the only model that I have that my GPU fans don't engage when I am running it.

Diggy Dre

I figured it out! --use-sage-attention was the key! The only reason I wasn't already using it is I had some problems with it in the past, but it seems this models like it. It is moving very fast now! Thank you so much for your patience!

SECourses

ok edit your backend and add this and try --no-cache and let me know . like --use-sage-attention

SECourses

ok edit your backend and add this and try --no-cache and let me know . like --use-sage-attention

SECourses

true. i made the very best special 2512 FP8 quantized. took my whole day. currently testing best inference preset

Ngoc Ngo

Can I outpaint/expand images?

Ec Jep

I have same issue with my 4090 setup, 24g vram, 128 ram running either 2509 or 2511 edit just sits with memory full and does nothing. 2509 used to work. I'm on fresh install of swarm 121 and comfyui 73 and use --use-sage-attention. Other flux or qwen models work fine. I have also restarted computer.. also --no-cache gives backend error

SECourses

easy try these 2 1 by 1 and see which one works better : 1st : --disable-smart-memory 2nd : --cache-none

Ec Jep

I have same issue as "Diggy Dre" below with my 4090 setup, 24g vram, 128 ram running either 2509 or 2511 edit (with recommended LORA applied) and just sits with memory full and does nothing. 2509 used to work. I'm on fresh install of swarm 121 and comfyui 73 and use --use-sage-attention. Other flux or qwen models work fine. I have also restarted computer.. also --no-cache gives backend error. **update from 1/16. I can get both models to work fine but 2511-12step & image edit plus (2509) presets cause the problem. I have not discovered what in the presets is causing issues

SECourses

it is --cache-none. try it and let me know if fixes

Ec Jep

I’ve tried —cache-none, —gpu-only, —disable-smart-memory, and —lowvram None fixed the issue. It occurs when I use a Lora preset. Without preset it works fine. I can apply preset and remove Lora and it works. Both 2509 and 2511 lightning Lora’s cause the issue

SECourses

which preset exactly what is name of it? i never had this issue

Ec Jep

The Lora’s that are set by these presets : Qwen image edit 2511 12 step and qwen image edit plus (for 2509 image model) When I remove the Lora, image editing works as normal. It’s like the Lora feature is broken. I also rarely use Lora’s. I can try to reload the presets and redownload the Lora’s next week