Forem: Furkan Gözükara

SECourses Upscaler Pro Beating Topaz AI by Far With Specalized FlashVSR+ & SeedVR2.5 - Local Windows

Furkan Gözükara — Wed, 25 Feb 2026 00:16:07 +0000

SECourses Upscaler Pro Beating Topaz AI by Far With Specalized FlashVSR+ & SeedVR2.5 - Local Windows

Full tutorial link > https://www.youtube.com/watch?v=_WT4C78j5-c

Download SECourses Upscaler Pro : https://www.patreon.com/posts/secourses-upscaler-pro-150202809

Tutorial Info

🚀 Welcome to the Ultimate SECourses Upscaler Pro & Trellis 3D Tutorial!

Greetings everyone! Today, I am incredibly excited to showcase the massive new improvements and brand-new features we have added to the SECourses Upscaler Pro application. I have been working non-stop to bring you a studio-level AI video and image enhancement tool that completely redefines what is possible running locally on your own PC.

In this video, we dive deep into side-by-side comparisons between our custom FlashVSR+ upscaler, original viral social media videos, and Topaz AI. As you will see in our live slider comparisons, the SECourses Upscaler Pro is adding 10x more detail than Topaz AI, generating breathtaking, high-definition results while running highly optimized on GPUs with as little as 8GB of VRAM!

We also explore the immensely powerful SeedVR2 model for flawless 4x image upscaling, and I give you an exclusive sneak peek at our upcoming Trellis Image-to-3D application featuring fully automated UniRig 3D character rigging!

🔗 Important Links & Resources:

📥 Download the Latest SECourses Upscaler Pro Installer: [ https://www.patreon.com/posts/secourses-upscaler-pro-150202809 ]

📥 Download Trellis Image-to-3D App: [ https://www.patreon.com/posts/trellis2-app-147686623 ]

Some Important Comparison Screenshots From Actual Upscaled Videos

Below videos are upscaled with FlashVSR+ and it is ultra optimized, fast and low VRAM (As low as 8 GB)

⚡ Key Features of SECourses Upscaler Pro Covered in This Video:

•• Unmatched AI Upscaling: Outperforms Topaz AI and other public repositories by adding massive amounts of true-to-life details to low-resolution inputs.

•• Optimized for Low VRAM: Run advanced models like FlashVSR+ and SeedVR2 on GPUs with 8GB VRAM using GGUF and FP8 models.

•• Scene-Based & Chunk-Based Processing: Automatically detects scene changes and processes videos in chunks. This maximizes quality and prevents VRAM crashes!

•• Full Resume Capability

•• Built-In Comparison Tools: Automatically generate custom, animated side-by-side comparison slider videos with custom text labels to showcase your upscales.

•• Advanced Video Output: Supports global RIFE frame interpolation, Face Restoration, H265 10-bit encoding, and custom audio codecs.

•• Easy Installation: 1-click install and update .bat files. No complicated coding required!

⏱️ Video Chapters & Timestamps:

00:00:00 Introduction to SECourses Upscaler Pro & Amazing New Features
00:00:29 Comparison: Original Video vs SECourses Pro Upscaled Video
00:00:50 Slider Tool Comparison: Original vs SECourses Upscaler
00:01:06 Comparison: Original Video vs Topaz AI Video Enhance
00:01:19 Slider Tool Comparison: Original vs Topaz AI Quality
00:01:35 Ultimate Comparison: SECourses Upscaler vs Topaz AI
00:02:07 Overview of FlashVSR+ Version and Custom Improvements
00:02:20 Live Studio Level Video Comparison Slider Tool Demonstration
00:03:02 Topaz AI vs Original Video Slider Demonstration in App
00:03:15 SECourses vs Topaz AI Massive Quality Difference Revealed
00:03:35 Running Locally vs Cloud GPUs (RunPod, MassedCompute)
00:03:56 Test Case 2: Viral AI Video Original vs SECourses Upscaled
00:04:17 How to Generate Custom Comparison Videos with Custom Titles
00:04:50 Test Case 2 Slider: Topaz AI vs SECourses FlashVSR+
00:05:25 Chunk-Based & Scene-Based Upscaling System Explained
00:05:50 How to Download, Install, and Update the Application Easily
00:06:34 SeedVR2 Model Tricks: Batch Size & Blocks to Swap Setup
00:07:00 Live Demonstration: 4x Image Upscaling with SeedVR2
00:07:36 Optimizing VRAM Usage with Max Blocks to Swap & GGUF Models
00:08:34 FlashVSR+ Video Upscaling Setup & Scene Detection Features
00:09:17 Downscale and 4x Upscale Resolution Configuration Explained
00:09:54 How to Use the Full Resume Capability for Long Video Upscales
00:10:15 Custom Target Resolution Settings & Target Pixel Dimensions
00:10:46 Frame Chunk Size Optimization for Maximum Speed & Quality
00:11:20 Enable DiT Tiling vs VAE Tiling for VRAM Management
00:11:58 Live FlashVSR+ Upscaling Process & Input Chunk Splitting
00:12:43 VRAM Usage Analysis: Upscaling to 4K on a 16GB GPU
00:13:18 Additional SeedVR2 Tricks: Sparse Ratio & Tile Size Limits
00:13:41 Canceling Upscale Jobs & Monitoring RAM/VRAM Release Live
00:13:53 App Features: Health Check, Global Settings & Light/Dark Theme
00:14:15 Queue System, Face Restoration & RIFE Frame Interpolation
00:14:50 Video Output Formats, Codecs & H265 10-bit Encoding Setup
00:15:17 Automatic Comparison Display & Run Metadata Saving Feature
00:16:03 Direct Video Compare Tool & Animated Slider Generation
00:16:34 Multi-Video Comparison Slider (Original vs Topaz vs SECourses)
00:17:32 Testing Default Settings for VRAM Memory Efficiency
00:18:15 FlashVSR Default Settings Setup & Upscale Demonstration
00:19:07 Verifying Low VRAM Usage Under 8GB for HD Video Upscaling
00:19:38 Upcoming Trellis Image to 3D Application Features Preview
00:19:51 UniRig 3D Rigging Integration for Character Skeletons
00:20:15 Compiling Custom 3D Libraries for Modern CUDA 13 GPUs
00:20:53 Trellis Output Formats: Skeleton FBX & Preview GLB Saves
00:21:14 Importing & Previewing 3D Models, Bones, and Textures
00:22:20 Future Updates: Multi-Stage Upscale Queue & SUPIR Integration

SECourses Upscaler Pro

Furkan Gözükara — Fri, 20 Feb 2026 14:35:49 +0000

SECourses Upscaler Pro

Download link : https://www.patreon.com/posts/150202809

SECourses Ultimate Video and Image Upscaler Pro - SeedVR2 - FlashVSR+ - Face Restoration - Gan Upscalers - Queue System - Fully Automated Movie Restoration and Upscale Studio - with so many amazing new features and full VRAM optimizations, can upscale a whole 120 minutes video fully properly with full resume capability

Fully working locally with SOTA public Open Source AI Models

Quick tutorial video 4K : https://youtu.be/bPWsg8DREiM?si=cMz5avk_etPlwlKY

Get the app from here : https://www.patreon.com/posts/150202809

Version 2.0 of the most awaited Pro Upscaler App published
Almost all of the features completed please test all and let me know if any broken or what new features you need
It has so many features
Fully automated installation and model download on Windows, RunPod, SimplePod, Massed Compute, Linux
It fully supports SeedVR2, FlashVSR+, Image Based Upscalers like Gan upscalers etc
Make sure to follow requirements tutorial fully for torch compile for SeedVR2 it is very requirements depended MSVC C++ Visual Studio CL
Watch demo video above I have uploaded and full tutorial hopefully coming soon

Check Below Screenshots to See All of The Features of The App So Far

🎬 SeedVR2

Features List

⚡ FlashVSR+

📐 Resolution & Scene Split

🖼️ Image-Based (GAN)

⏱️ Output & Comparison - Global RIFE

⏱️ Output & Comparison - Video Output

⏱️ Output & Comparison - Videos Comparison Slider

⏱️ Output & Comparison - Images Comparison Slider

⏱️ RIFE / FPS / Edit Videos

⏱️ Face Restoration

⏱️ Fully Automatic Queue System

⏱️ System App Health Check

⏱️ Automatic 1-Click Installers for Windows, RunPod, Massed Compute, Linux, SimplePod

SeedVR2 and FlashVSR+ Studio Level Image and Video Upscaler Pro Released

Furkan Gözükara — Wed, 11 Feb 2026 00:48:31 +0000

SeedVR2 and FlashVSR+ Studio Level Image and Video Upscaler Pro Released

Full tutorial link > https://www.youtube.com/watch?v=bPWsg8DREiM

It has been long waited to have a studio level video and image upscaler app. Today we have publishing the version 1.0 of SECourses Ultimate Video and Image Upscaler Pro. It is supporting SeedVR2, FlashVSR+, Gan based upscalers, RIFE frame interpolation, full queue system, full batch folder processing, scene / chunked based processing and many more. It is fully working on every cloud and consumer GPUs like RTX 2000, 3000, 4000, 5000 series and H100, H200, B200, RTX PRO 6000. We are installing app with latest Torch and CUDA versions atm all fully automatic with pre-compiled libraries. Even Torch compile is fully and automatically working.

📂 Resources & Links:

💻 SECourses Ultimate Video and Image Upscaler Pro Download Link : [ https://www.patreon.com/posts/Upscaler-Studio-Pro-150202809 ]

🚆 Requirements Tutorial : https://youtu.be/DrhUHnYfwC0

🛠️ Requirements Written Post : [ https://www.patreon.com/posts/Windows-AI-Requirements-Setup-Guide-111553210 ]

👋 SECourses Discord Channel for 7/24 Support: [ https://bit.ly/SECoursesDiscord ]

ℹ️ SimplePod Register : https://simplepod.ai/ref?user=secourses

ℹ️ SimplePod Template : https://dash.simplepod.ai/account/explore/100/ref-secourses/

ℹ️ RunPod Register : https://get.runpod.io/955rkuppqv4h

ℹ️ RunPod Template : https://get.runpod.io/SECourses_CU13

ℹ️ Massed Compute Register : https://bit.ly/SECoursesMassedCompute

⏱️ TIMESTAMPS

00:00:00 Announcing SECourses Ultimate Video & Image Upscaler Pro V1
00:00:22 Ultra-Fast High-Quality Image Upscaling Demo (1024 to 4096px)
00:00:40 Low GPU Usage & Prompt-Free Workflow Explained
00:01:00 Single Step Upscaling & Advanced Optimization (Torch Compile)
00:01:20 Introduction to Video Upscaling & Custom Live Comparison Tool
00:01:45 Video Quality Comparison vs Topaz Labs & Open Source Models
00:02:08 Cloud GPU Support (RunPod, Massed Compute) & Local Execution
00:02:20 Dynamic UI Features: Real-Time Input Analysis & Settings
00:02:59 Scene-Based Upscaling Workflow with PySceneDetect Integration
00:03:18 Advantages of Scene-Based Processing & Resume Functionality
00:03:48 Visualizing Processed Scene Chunks & Adjusting Split Settings
00:04:09 Automating Full-Length Movie Upscaling (120+ Minutes)
00:04:26 Analyzing Scene Detection Statistics & Frame Count Distribution
00:04:51 RIFE FPS Interpolation Support & Run Logs Interface
00:05:10 Visual Demonstration of Upscaled Video Details & Future Models
00:05:30 Extensive GPU Compatibility (RTX 2000-5000, H200, B200, CUDA 13)
00:05:52 VRAM Error Handling, Health Check & Recovery Tools
00:06:19 Comprehensive Queue System & Changing Parameters Live
00:06:48 Canceling Processes & Error Recovery Without App Restart
00:07:11 Output Folder Structure, Subfolders & Saving Processed Data
00:07:56 Debugging with Executed Command Logs & Run Summaries
00:08:18 One-Click Windows Installation, Auto-Updates & Model Hash Check
00:08:38 Critical Windows Requirements for Torch Compile & Python 3.10
00:08:57 Installation Instructions for RunPod & Massed Compute Cloud
00:09:21 Detailed Feature List: Face Restore, GANs, FlashVSR+ & More
00:09:55 System Diagnostics, Reliability, Safety & UX Features
00:10:28 Batch Processing Support for Image & Video Folders

Some Core Features - Hopefully More Features Coming Soon

Core features: Multi-tab, multi-pipeline app (SeedVR2 / GAN / RIFE / FlashVSR+ / Face Restore) with unified resolution strategy + global face restoration controls.
SeedVR2: Video/image/folder inputs, first-frame preview, smart model defaults/constraints, and advanced VRAM/performance options (offload/BlockSwap/VAE tiling/compile/attention backend/cache toggles).
GAN / RIFE / FlashVSR+: GAN upscaling for images/videos/folders w/ metadata-based model detection; RIFE interpolation (model, FPS modes, scale/precision, static-skip, recursion); FlashVSR+ diffusion upscaling (version/mode/scale + VRAM-aware tiling/unload options).
Output & comparison: MP4/PNG/sequence outputs, full ffmpeg encoding controls (codec/CRF/preset/pixfmt), audio copy/re-encode/remove, 2-pass, FPS override, global RIFE post-process (incl. chunk-safe), and rich comparison tools (slider/SxS/overlay + HTML slider + auto comparison videos + “compare any 2 videos”).
Long runs & batching: PySceneDetect chunking + fallback, lossless vs fast splitting, resume partial runs, per-chunk cleanup, batch processing across pipelines, and an app-wide FIFO queue with snapshot-isolated settings.
Presets & reliability: Universal presets + per-tab presets, migration/guardrails, persistent global settings/profiles, safe cancel/cleanup, OOM detection + guidance, partial output salvage, collision-safe naming, telemetry/command logs, and validation/fallbacks (ffmpeg/audio utilities).
Diagnostics & UX: Health checks (ffmpeg/CUDA/tools/disk), GPU-safe detection, model registries, env var integration, file upload/path entry, previews, auto input detection, estimators, quick links, progress/ETA, CUDA cache clear, and Gradio --share support.

LTX 2 & Z Image Base Full Tutorial + Audio to Video Lip Sync + ComfyUI + SwarmUI + Windows + Cloud

Furkan Gözükara — Sat, 31 Jan 2026 00:56:26 +0000

LTX 2 & Z Image Base Full Tutorial + Audio to Video Lip Sync + ComfyUI + SwarmUI + Windows + Cloud

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

Info

LTX 2 is the newest state of the art (SOTA) Open Source video generation model and tutorial will show you how to use it with very best and most performant way in ComfyUI and also in SwarmUI. Moreover, Z Image Base model published and I will show how to use Z Image Base with most amazing preset and workflow as well. Furthermore, this tutorial will show you how to install, update, setup, download ComfyUI and SwarmUI and models and presets and workflows both on Windows and on RunPod, Massed Compute and SimplePod. Linux users can use Massed Compute scripts and installers directly. This is a masterpiece entire lecture level complete tutorial. This video will kickstart your AI journey 100x. Both local Windows and Cloud.

📂 Resources & Links:

🤖 ComfyUI Installer and Presets Zip File With CUDA 13: [ https://www.patreon.com/posts/ComfyUI-Installers-105023709 ]
💻 SwarmUI Installer and Presets Zip File: [ https://www.patreon.com/posts/SwarmUI-Install-Presets-114517862 ]
🚀 Model Downloader Zip File: [ https://www.patreon.com/posts/Model-Downloader-114517862 ]
🚆 SECourses Musubi Trainer (Model Quantize and Train App): [ https://www.patreon.com/posts/SECourses-Musubi-Trainer-137551634 ]
🛠️ Image Comparison Slider Tool: [ https://www.patreon.com/posts/image-video-comparison-slider-app-133935178 ]
👋 SECourses Discord Channel for 7/24 Support: [ https://bit.ly/SECoursesDiscord ]
ℹ️ SimplePod Register : https://simplepod.ai/ref?user=secourses
ℹ️ SimplePod Template : https://dash.simplepod.ai/account/explore/100/ref-secourses/
ℹ️ RunPod Register : https://get.runpod.io/955rkuppqv4h
ℹ️ RunPod Template : https://get.runpod.io/SECourses_CU13
ℹ️ Massed Compute Register : https://bit.ly/SECoursesMassedCompute

⏱️ TIMESTAMPS

00:00:00 Intro: ComfyUI + SwarmUI presets, Z-Image, model downloader, cloud installs
00:00:28 Free prompt enhancement with Google AI Studio (prepared prompt file)
00:01:26 Demo: 45s audio-driven lip-sync image→video (LTX 2)
00:02:25 Quick demos: ComfyUI image→video, text→video, Z-Image base
00:03:43 Quick demos: SwarmUI LTX 2 image→video + Z-Image base
00:04:46 Install/update presets zip (v78+): extract & overwrite everything
00:05:11 Upgrade to CUDA 13 safely: delete venv then run ComfyUI update/install
00:06:00 Windows prereqs + the always-updated setup guide referenced in description
00:06:42 Install required node bundles: (1) SwarmUI extra nodes + (100) LTX audio
00:07:29 VRAM-optimized launcher: no-VRAM / cache / smart-memory / precision choices
00:09:36 Share one model library: configure extra_model_paths.yaml (no duplicates)
00:10:25 Model Downloader overview: set base path + one-click bundles for SwarmUI/ComfyUI
00:11:43 Download LTX 2 core bundle: multi-connection download + merge + hash verify
00:12:12 Low-VRAM path: GGUF distilled models vs recommended FP8-scaled defaults
00:14:16 URL Downloader: Civitai/HF links, folder targeting, and optional API keys
00:14:54 ComfyUI preset pack tour: LTX2 (I2V/T2V/audio) + Z-Image (base/2× upscale)
00:15:16 ComfyUI audio lip-sync preset: image + resolution + audio setup
00:16:58 Frames & prompting: 24fps math, run/stop frame count, lyrics/subtitles prompts
00:17:59 Quality/perf knobs: CRF, VRAM monitoring, and low-VRAM args recap
00:20:22 Review result + move to LTX 2 image→video preset workflow
00:21:50 Prompt enhancer workflow: drag prompt file into AI Studio (optionally add image)
00:24:11 Z-Image troubleshooting: disable Sage Attention and restart
00:24:32 Z-Image base + 2× upscale preset: when to use it and what to expect
00:26:47 Outputs & reproducibility: where renders save + drag PNG to reload metadata
00:27:57 Update SwarmUI via zip: get latest presets + utilities
00:28:27 SwarmUI setup: ComfyUI backend, passing args, and pointing to model folders
00:30:21 SwarmUI image→video: direct apply + init image workflow
00:31:17 Fix model load/caching issues: add --use-cache-none when needed
00:32:51 SwarmUI text→video + upscale: duration/frames, half-res then upscale rules
00:33:52 SwarmUI outputs: output_local/raw + metadata saved with generations
00:35:05 SwarmUI Z-Image: base vs 2× upscale comparison + speed notes
00:36:58 Image comparison slider tool: quick before/after inspection
00:37:51 RunPod start: template choice, CUDA/driver constraints, optional storage volume
00:43:30 RunPod Jupyter: upload ComfyUI zip, extract, install bundles (1+100)
00:46:28 RunPod: run Model Downloader, start ComfyUI, connect via exposed port
00:52:05 RunPod: switch to SwarmUI, map folders (case-sensitive), import presets
00:55:43 RunPod: download outputs as archive + stop vs terminate cost control
00:57:55 SimplePod: cheaper/faster alternative + persistent volume setup highlights
01:03:52 Massed Compute: deploy with coupon + connect via ThinLinc (shared folder setup)
01:08:17 Massed Compute: install bundles + download models (disk speed advantage)
01:10:48 Massed Compute: start ComfyUI, connect from PC, run lip-sync preset
01:14:26 Massed Compute: hook SwarmUI to ComfyUI backend + text→video demo
01:17:02 Wrap-up: recap providers + next steps

BF16 vs GGUF, FP8 Scaled, NVFP4 Speed & Quality Compared + ComfyUI CUDA 13 Gains + FLUX 2 Klein 9B

Furkan Gözükara — Sat, 17 Jan 2026 20:40:03 +0000

BF16 vs GGUF, FP8 Scaled, NVFP4 Speed & Quality Compared + ComfyUI CUDA 13 Gains + FLUX 2 Klein 9B

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

Compared Quality and Speed Difference (with CUDA 13 & Sage Attention) of BF16 vs GGUF Q8 vs FP8 Scaled vs NVFP4 for Z Image Turbo, FLUX Dev, FLUX SRPO, FLUX Kontext, FLUX 2

Video Info

It was always wondered how much quality and speed difference exists between BF16, GGUF, FP8 Scaled and NVFP4 precisions. In this tutorial I have compared all these precision and quantization variants for both speed and quality. The results are pretty surprising. Moreover, we have developed and published NVFP4 model quant generator app and FP8 Scaled quant generator apps. The links of the apps are below if you want to use them. Furthermore, upgrading ComfyUI to CUDA 13 with properly compiled libraries is now very much recommended. We have observed some noticeable performance gains with CUDA 13. So for both SwarmUI and ComfyUI solo users, CUDA 13 ComfyUI is now recommended.

📂 Resources & Links:

📥 Download ComfyUI CUDA 13 Installer: [ https://www.patreon.com/posts/ComfyUI-Installers-105023709 ]
📥 SwarmUI & ComfyUI Unified Model Downloader: [ https://www.patreon.com/posts/SwarmUI-Install-Download-Models-Presets-114517862 ]
🤖 NVFP4 Model Quantizer App: [ https://www.patreon.com/posts/nvfp4-quantizer-app-148217625 ]
🤖 SECourses Musubi Trainer (FP8 Scaled Quantization App): [ https://www.patreon.com/posts/nvfp4-quantizer-app-148217625 ]
🛠️ Image Comparison Slider Tool: [ https://www.patreon.com/posts/image-video-comparison-slider-app-133935178 ]
☁️ SimplePod AI: [ https://simplepod.ai/ref?user=secourses ]
New Model FLUX 2 Klein 9B: [ https://huggingface.co/black-forest-labs/FLUX.2-klein-9B ]
🎥 FLUX 1 Kontext Dev Tutorial (inpaint - outpaint - image fix): [ https://youtu.be/XWzZ2wnzNuQ ]
🎥 Previous ComfyUI Installation Tutorial: [ https://youtu.be/yOj9PYq3XYM ]
How to Use SwarmUI Presets & Workflows in ComfyUI + Custom Model Paths Setup for ComfyUI & SwarmUI Tutorial: [ https://youtu.be/EqFilBM3i7s ]
SECourses Discord Channel for 7/24 Support: [ https://discord.com/invite/software-engineering-courses-secourses-772774097734074388 ]
SECourses Musubi Tuner Tutorial: [ https://youtu.be/DPX3eBTuO_Y ]
NVIDIA NVFP4 Blog Post to learn More: [ https://developer.nvidia.com/blog/introducing-nvfp4-for-efficient-and-accurate-low-precision-inference/ ]

⏱️ Video Chapters:

00:00:00 Introduction: GGUF Q8 vs NVFP4 vs BF16 vs FP8 Precision Comparison
00:00:38 FP8 Quantization & New NVFP4 Model Quantizer App in Musubi Trainer
00:01:08 The New FLUX SRPO Mixed NVFP4 Model & FLUX 2 Klein 9B Announcement
00:01:56 Speed Comparison Setup: ComfyUI CUDA 13 & Compiled Libraries
00:02:41 Z Image Turbo Speed Test: GGUF Q8 vs NVFP4 (87% Faster)
00:03:09 Z Image Turbo Speed Test: BF16 vs FP8 Scaled vs GGUF Improvements
00:03:32 Installing & Using Image Comparison Slider Tool for Quality Check
00:03:55 Z Image Turbo Quality: BF16 vs GGUF Q8 vs FP8 Scaled
00:04:13 Z Image Turbo Quality: NVFP4 Degradation Analysis
00:04:27 FLUX 2 Dev Speed Test: GGUF Q8 vs NVFP4 (100% Faster)
00:04:43 FLUX 2 Dev Speed Test: FP8 Scaled vs BF16 Performance
00:05:12 FLUX 2 Dev Quality: BF16 vs GGUF Q8 vs Mixed FP8 Scaled
00:05:38 FLUX 2 Dev Quality: NVFP4 Mixed Precision Analysis
00:05:54 Benchmark Settings: 2048px Resolution & Quality 1 Preset Details
00:06:25 FLUX 1 Dev Speed Test: GGUF Q8 vs NVFP4 (118% Faster)
00:07:21 FLUX 1 Dev Speed Test: BF16 & FP8 Scaled Performance Stats
00:07:42 FLUX 1 Dev Quality: BF16 vs GGUF Q8 vs FP8 Scaled
00:07:55 FLUX 1 Dev Quality: NVFP4 Visual Degradation Review
00:08:06 FLUX 1 Kontext Dev: Model Intro & Outpainting Tutorial Reference
00:08:40 FLUX 1 Kontext Dev Speed: GGUF Q8 vs NVFP4 (93% Faster)
00:08:59 FLUX 1 Kontext Dev Speed: BF16 & FP8 Scaled Comparisons
00:09:12 FLUX 1 Kontext Dev Quality: Original vs Edited Image (Hair Change)
00:09:36 FLUX 1 Kontext Dev Quality: BF16 vs GGUF Q8 vs FP8 Scaled
00:09:51 How to Use SwarmUI Unified Model Downloader & Bundles
00:10:36 Downloading Models via URL from CivitAI & Hugging Face to Cloud
00:11:45 SECourses Musubi Trainer: Creating Custom FP8 Quantized Models
00:12:44 The New FLUX SRPO NVFP4 Mixed Precision Model Overview
00:13:15 Live Demo: FLUX SRPO NVFP4 Speed Test on RTX 5090 (5.7s)
00:13:52 VRAM Usage Analysis: NVFP4 on RTX 5090 (14GB Usage)
00:14:16 Live Comparison: BF16 Speed & VRAM Test on RTX 5090
00:15:15 Troubleshooting: Fixing Low RAM/VRAM Issues with Arguments
00:16:25 Why You Should Upgrade to ComfyUI CUDA 13 Version
00:16:51 SimplePod AI: Updated Instructions & Template Setup
00:17:29 RTX 6000 Blackwell Fix & nvitop Utilization Verification
00:18:18 Conclusion, Contact Info & Support Channels
In this video, you will learn:
Speed differences between GGUF Q8, NVFP4, BF16, and FP8.
Visual quality analysis using the Image Comparison Slider.
How to use the new NVFP4 and FP8 Quantizer tools.
How to fix Low VRAM/RAM issues with specific arguments.
Performance benchmarks on RTX 5090 and RTX 6000.

Comparison Screenshots

NVFP4 With CUDA 13 Full Tutorial, 100%+ Speed Gain + Quality Comparison & New Cheap Cloud SimplePod

Furkan Gözükara — Mon, 12 Jan 2026 00:26:22 +0000

Full tutorial: https://www.youtube.com/watch?v=yOj9PYq3XYM

Finally NVFP4 models has arrived to ComfyUI thus SwarmUI with CUDA 13. NVFP4 models are literally 100%+ faster with minimal impact on quality. I have done grid quality comparison to show you the difference on FLUX 2, Z Image Turbo and FLUX 1 of NVFP4 versions. To make CUDA 13 work, I have compiled Flash Attention, Sage Attention & xFormers for both Windows and Linux with all of the CUDA archs to support literally all GPUs starting from GTX 1650 series, RTX 2000, 3000, 4000, 5000 series and more.

In this full tutorial, I will show you how to upgrade your ComfyUI and thus SwarmUI to use latest CUDA 13 with latest libraries and Torch 2.9.1. Moreover, our compiled libraries such as Sage Attention works with all models on all GPUs without generating black images or videos such as Qwen Image or Wan 2.2 models. Hopefully LTX 2 presets and tutorial coming soon too. Finally, I introduce a new private cloud GPU platform called as SimplePod like RunPod. This platform has all the features of RunPod same way but much faster and cheaper.

📂 Resources & Links:

ComfyUI Installers: [ https://www.patreon.com/posts/ComfyUI-Installers-105023709 ]
SimplePod: [ https://simplepod.ai/ref?user=secourses ]
SwarmUI Installer, Model Auto Downloader and Presets: [ https://www.patreon.com/posts/SwarmUI-Install-Download-Models-Presets-114517862 ]
How to Use SwarmUI Presets & Workflows in ComfyUI + Custom Model Paths Setup for ComfyUI & SwarmUI Tutorial: [ https://youtu.be/EqFilBM3i7s ]
SECourses Discord Channel for 7/24 Support: [ https://discord.com/invite/software-engineering-courses-secourses-772774097734074388 ]
NVIDIA NVFP4 Blog Post More: [ https://developer.nvidia.com/blog/introducing-nvfp4-for-efficient-and-accurate-low-precision-inference/ ]

⏱️ Video Chapters:

00:00:00 New ComfyUI installer (CUDA 13, Torch 2.9.1, Triton + attention libs)
00:00:19 NVFP4 speedup claims vs real tests; why CUDA 13 enables new models
00:00:34 Prebuilt FlashAttention/SageAttention/xFormers for many GPUs (Windows + Linux)
00:01:00 Quality roadmap: FLUX2 Dev, Z Image Turbo, FLUX Dev (BF16/FP8/GGUF/NVFP4)
00:01:23 Downloader adds NVFP4: FLUX2 Dev, FLUX Dev (Context/Dev), Z Image Turbo
00:01:51 SimplePod AI intro: RunPod-style pods, cheaper rates, permanent storage
00:02:36 Musubi Tuner FP8 Scaled: quality myths vs GGUF + why scaled matters
00:03:10 Quantization & precision (FP32/BF16/FP8/GGUF) + Qwen3 low-VRAM encoders
00:03:34 ComfyUI v73 zip: CUDA 13 included; update NVIDIA drivers only (v72 deprecated)
00:04:13 Update steps: overwrite zip, delete venv, run install/update .bat
00:05:02 Python: 3.10 recommended (supports 3.10-3.13); fresh vs update
00:06:02 New installer flow: uv speed, standalone use, backend libs detected
00:07:12 Stability flags: --cache-none vs --disable-smart-memory (OOM/stuck fixes)
00:07:54 SwarmUI presets: 32 presets supported; drag/drop + auto model downloader
00:08:25 Update SwarmUI model-downloader zip (extract + overwrite)
00:08:49 Download bundles/models (Z Image Turbo Core + NVFP4 options)
00:09:25 Update/launch SwarmUI; point to updated ComfyUI backend + set args
00:10:32 Live gen test: Z Image Turbo BF16 @1536x1536
00:11:29 Switch to NVFP4: VRAM cache behavior; 1024x1024
00:12:36 FLUX2 Dev quality: FP8 Scaled vs NVFP4 side-by-side comparisons
00:13:33 Speed chart: FLUX2 NVFP4 about 193% faster than FP8 Scaled
00:14:10 Z Image Turbo quality: BF16 vs NVFP4 vs FP8 Scaled (quant method)
00:15:25 FLUX Dev: FP8 Scaled approx GGUF Q8; NVFP4 currently shows degradation
00:16:45 What precision means + model size examples (FP32/BF16/FP8 Scaled/NVFP4)
00:18:07 Practical recommendations: BF16 best; avoid FP16; raw FP8 vs FP8 Scaled
00:19:43 GGUF explained: block quant, slower runtime; use only when RAM is too low
00:21:36 Precision hierarchy recap + when to pick FP8 mixed/scaled over GGUF
00:21:58 SimplePod setup: register, add credits, open template link
00:22:31 Template config + RunPod price comparison (disk, ports, GPU selection)
00:24:02 Persistent volume: create + mount to /workspace
00:25:11 Launch RTX Pro 6000 pod; SimplePod vs RunPod pricing differences
00:26:29 Temp vs persistent disk: deleting instance wipes temp data - backup!
00:26:55 JupyterLab: upload zips, apt install zip, unzip ComfyUI in workspace
00:27:48 Run install script; unzip SwarmUI; start the model downloader
00:29:02 Downloader path for ComfyUI + folder structure; download Z Image Turbo bundle
00:30:08 Start ComfyUI; confirm CUDA 13 + Torch 2.9.1; connect via port 3000 Direct
00:31:08 Preset demo: Z Image Turbo Quality 1; fix VAE path; monitor VRAM
00:33:18 File Browser Direct: download outputs/models fast; upload files back
00:34:41 Restart server; install/start SwarmUI; open Cloudflared URL
00:36:26 SwarmUI backend: /workspace/ComfyUI/main.py + args; import presets
00:37:27 Download FLUX2 Core + NVFP4; share model paths between SwarmUI & ComfyUI
00:39:27 FLUX2 NVFP4 generation @2048x2048; VRAM usage + step speed
00:40:43 Cloud GPU pitfall: diagnosing a power-capped GPU
00:41:28 Resume: re-run template w/ volume; reconnect fast
00:45:02 Wrap-up: SimplePod pros (direct/secure, cheaper storage)

Screenshots and Info

Qwen Image 2512 Is The Very Best Model To Train - New King Absolutely

Furkan Gözükara — Mon, 05 Jan 2026 21:27:26 +0000

Qwen Image 2512 & 2511 Training Results Are Next Level + 33 ComfyUI Presets for Image & Video Gen

Full tutorial: https://www.youtube.com/watch?v=RcoXd9v1t_c

Qwen Image 2512 Text to Image model is a massive upgrade in quality just as Qwen Image Edit 2511 was for image editing tasks based on commands. I have trained both Qwen Image older Base, Qwen Image 2512 new base, Qwen Image 2509 older edit model and Qwen Image 2511 newer edit model and compared them in this video. The results are astonishing. Moreover, we have converted all of our premium SwarmUI image and video generation presets into ComfyUI workflows. Just drag and drop the workflow and start using immediately. All models are downloaded with our premium 1-click to use model downloader app. ComfyUI and SwarmUI are also installed with 1-click installers and our ComfyUI fully supports Sage Attention, Flash Attention, xFormers, Triton and more with RTX 5000 series and all GPUs like 3000, 2000, 4000 series, etc for both Linux and Windows.

📂 Resources & Links:

ComfyUI Installer: [ https://www.patreon.com/posts/ComfyUI-Installers-105023709 ]
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 ]
SwarmUI & ComfyUI Setup Guide for RunPod & Massed Compute: [ https://youtu.be/bBxgtVD3ek4 ]
Qwen Image Models Training Tutorial: [ https://youtu.be/DPX3eBTuO_Y ]
Wan 2.2 Model Training Tutorial: [ https://youtu.be/ocEkhAsPOs4 ]
Z Image Turbo Model Training Tutorial: [ https://youtu.be/ezD6QO14kRc ]
FLUX Models Fine Tuning / DreamBooth Training Tutorial: [ https://youtu.be/FvpWy1x5etM ]
FLUX Models LoRA Training Tutorial: [ https://youtu.be/nySGu12Y05k ]
Upload / Download Big Files Guide for RunPod & Massed Compute: [ https://youtu.be/X5WVZ0NMaTg ]

⏱️ Video Chapters:

00:00:00 Introduction to Qwen Image Base & 2512 Model Training Findings plus Qwen Image Edit 2509 & 2511 News
00:00:16 Announcement of Training Support for Qwen Image Edit Models & Upcoming Training Guide Overview
00:00:32 New FP8 Quantization Feature in SECourses Musubi Tuner & Full ComfyUI Preset Support Announcement
00:00:48 Converting All SwarmUI Presets into Drag-and-Drop ComfyUI Workflows & HTML Helper File Introduction
00:01:10 How to Use the New HTML File to Identify and Download Necessary Model Bundles via SwarmUI Downloader
00:01:24 Qwen Image Base Model Training Analysis: Observing Overfitting and Quality Degradation at 240 Epochs
00:02:04 Qwen Image 2512 Model Training Results: Massive Quality Boost & Reduced Noise Compared to Base Model
00:02:38 Showcasing New Qwen Image 2512 UHD Realism Presets Available in Both ComfyUI and SwarmUI
00:03:01 Visual Comparison: The Massive Leap in Realism Quality Between Previous Models and New 2512 Model
00:03:38 Instructions on Updating the Training Application via Bat File to Unlock New Qwen Model Support
00:04:03 Selecting Specific Model Versions in the Trainer: Text-to-Image vs Image Edit Plus 2509/2511 Variants
00:04:24 Using the Updated Model Downloader Application to Fetch New Qwen 2512 & 2511 Checkpoints Automatically
00:04:40 Wan 2.2 Training Tutorial Reference & Overview of Recently Updated High-Quality Pr- sets for All Models
00:05:05 Training Dataset Configuration: Using Medium Quality Settings & OHWX Caption St- ategy for Best Results-
00:05:22 Testing Qwen Image Edit 2509 vs 2511 Models with GTA 5 Style Transfer Training on 120 and 180 Epochs
00:05:46 Analyzing GTA 5 Style Reproduction Accuracy on Both Edit Models Without Using Any Control Images
00:06:11 Style Transfer Experiment: Converting Input Image to Learned Style Using Edit Models Without Image-to-Image
00:06:40 Critical Findings on Edit Models: Lower Epoch Requirements & How Overtraining Alters Input Image Fidelity
00:07:09 Resolution Limitations for Style Transfer: Why 1328x1328 is the Optimal Sweet Spot for Editing Tasks
00:07:30 Reviewing Specific Presets Used for Qwen Image Edit Text-to-Image Generation vs Image Editing Tasks
00:08:02 How to Install and Update ComfyUI with the Latest Standalone Installer Script & Overwriting Old Files
00:08:15 Downloading Model Bundles for ComfyUI Presets Using the SwarmUI Downloader Tool & HTML Guide
00:08:39 Navigating the HTML Guide to Select Correct Model Bundles like Flux 2, Z Image Turbo or Qwen Core
00:09:12 Understanding Preset Limitations: Why Inpainting & Outpainting Workflows Require SwarmUI Editing Tab
00:09:57 Live Demonstration: Dragging and Dropping Flux SRPO Preset into ComfyUI Interface for Instant Setup
00:10:11 Configuring the Model Downloader to Target Your Specific ComfyUI Installation Path for Direct Downloads
00:10:47 Handling Potential VAE Subfolder Issues & Verifying High-Speed Downloads with 100% Hash Verification
00:11:06 Generating Images in ComfyUI: Python 3.10-3.13 Support, RTX 5000/4000/3000 Compatibility & Speed
00:11:54 Recommendation to Use SwarmUI with ComfyUI Backend for Best Experience & Access to All Features
00:12:20 Upcoming Tutorials Teaser: Trellis 2 3D Models & Video/Image Upscaler Guides Coming Soon

Some Generated Images

How to Use SwarmUI Presets & Workflows in ComfyUI + Custom Model Paths Setup for ComfyUI & SwarmUI

Furkan Gözükara — Mon, 29 Dec 2025 23:47:45 +0000

How to Use SwarmUI Presets & Workflows in ComfyUI + Custom Model Paths Setup for ComfyUI & SwarmUI

Full tutorial link > https://www.youtube.com/watch?v=EqFilBM3i7s

Info

Generating workflow inside SwarmUI and using in ComfyUI is literally 1-click. In this tutorial I will show you how to use our 40+ amazing generative AI presets made for SwarmUI in ComfyUI with most easy way. You will be able to get very best outcomes of all AI models such as SDXL, FLUX, Z Image Turbo, Wan 2.1, Wan 2.2, FLUX 2, Qwen Image, Qwen Image Edit, FLUX Kontext, Image Outpainting, Image Inpainting and many more. Moreover, I will show how to use custom model paths in ComfyUI and SwarmUI to unify your models in same folder and avoid model duplication and save massive amount of disk space.

📂 Resources & Links:

ComfyUI Installer: [ https://www.patreon.com/posts/ComfyUI-Installers-105023709 ]
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 ]
SwarmUI & ComfyUI Setup Guide for RunPod & Massed Compute: [ https://youtu.be/bBxgtVD3ek4 ]
Qwen Image Models Training Tutorial: [ https://youtu.be/DPX3eBTuO_Y ]
Wan 2.2 Model Training Tutorial: [ https://youtu.be/ocEkhAsPOs4 ]
Z Image Turbo Model Training Tutorial: [ https://youtu.be/ezD6QO14kRc ]
FLUX Models Fine Tuning / DreamBooth Training Tutorial: [ https://youtu.be/FvpWy1x5etM ]
FLUX Models LoRA Training Tutorial: [ https://youtu.be/nySGu12Y05k ]
Upload / Download Big Files Guide for RunPod & Massed Compute: [ https://youtu.be/X5WVZ0NMaTg ]

⏱️ Video Chapters:

00:00:00 Introduction to SwarmUI Presets in ComfyUI & Z Image Turbo Showcase
00:00:50 How to Update ComfyUI to the Latest Version Manually
00:01:24 Running the Windows Install or Update ComfyUI Script
00:01:45 Installing SwarmUI Extra Nodes for ComfyUI Compatibility
00:02:06 How to Update SwarmUI to the Latest Version
00:02:38 Importing the Newest SwarmUI Presets & Clearing History
00:03:00 Downloading Z Image Turbo Models & ControlNet Union via Script
00:03:40 Configuring Z Image Turbo Workflow with ControlNet in SwarmUI
00:04:11 Setting ControlNet Preprocessor, Aspect Ratio & Preview
00:04:43 Exporting the SwarmUI Workflow to ComfyUI JSON Format
00:05:16 Configuring extra_model_paths.yaml to Share SwarmUI Models
00:05:46 Editing the YAML File to Point to SwarmUI Directories
00:06:01 Understanding YAML Keys, Relative Paths & Checkpoint Folders
00:06:30 Loading the Exported SwarmUI Preset into ComfyUI
00:06:50 Replacing SwarmUI Load Image Node with ComfyUI Node
00:07:33 Adding ComfyUI Save Image Node for Output Storage
00:07:55 Running the Z Image Turbo Workflow & Performance Check
00:08:37 Reviewing the Generated Image & Z Image Turbo Training Tutorials
00:09:23 Preparing Wan 2.2 Image to Video Workflow in SwarmUI
00:09:52 Exporting the Video Generation Workflow to ComfyUI
00:10:17 Adjusting Load Image & Upscale Nodes for Video Workflow
00:10:40 Adding Create Video & Save Video Nodes for Output
00:10:54 Setting FPS & Connecting Video Save Sequence with RIFE
00:11:18 Executing the Video Workflow & VRAM Optimization Info
00:12:17 High/Low Noise Generation & RIFE Frame Interpolation Process
00:13:02 Using SwarmUI & ComfyUI on Cloud GPUs (RunPod & Massed Compute)
00:13:33 How to Use ComfyUI Models Inside SwarmUI (Reverse Setup)
00:14:02 Adjusting Folder Names (LoRAs) in Server Configuration
00:14:23 Upcoming Trellis 2 Premium 3D Generation Application
00:15:33 Upcoming Ultimate Video & Image Upscaler Application

Some Artworks

More Info

In this comprehensive tutorial, I demonstrate how to seamlessly use high-quality SwarmUI generated workflows and presets directly inside ComfyUI. If you love the ease of SwarmUI's presets but need the flexibility of ComfyUI, this guide covers the entire process from start to finish.
I showcase complex workflows, including Z Image Turbo with ControlNet Union and the new Wan 2.2 Image to Video generation (4 steps). You will learn how to export these presets as JSON files and properly configure the necessary custom nodes to get them running perfectly in ComfyUI.

Key Topics Covered:

Workflow Migration: Step-by-step guide on exporting SwarmUI presets and importing them into ComfyUI, including fixing "Load Image" and "Save Video" nodes.
Model Unification: A crucial guide on using the extra_model_paths.yaml file. I explain how to point ComfyUI to your SwarmUI model folders (and vice versa) so you never have to duplicate massive checkpoint or LoRA files again, saving huge amounts of disk space.
Installation & Updates: How to manually update both ComfyUI and SwarmUI to the latest versions and install the required "SwarmUI Extra Nodes."
Cloud Usage: Tips for running these workflows on cloud GPU services like Massed Compute and RunPod.

Featured Workflows:

Z Image Turbo: High-quality image generation with ControlNet integration.
Wan 2.2: Image-to-Video generation with RIFE frame interpolation for smooth results.
Upcoming Tools Teased:
Trellis 2 Premium: An insane 3D generation app for high-quality meshes and textures.
Ultimate Upscaler: A new application for image and video upscaling supporting SeedVR 2 and Flash VSR.

Qwen Image Edit 2511 Free and Open Source Crushes Qwen Image Edit 2509 and Challenges Nano Banana Pro

Furkan Gözükara — Thu, 25 Dec 2025 18:31:31 +0000

Qwen Image Edit 2511 Free and Open Source Crushes Qwen Image Edit 2509 and Challenges Nano Banana Pro

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

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:

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

Wan 2.2 Complete Training Tutorial - Text to Image, Text to Video, Image to Video, Windows & Cloud

Furkan Gözükara — Sun, 21 Dec 2025 17:37:00 +0000

Wan 2.2 Complete Training Tutorial - Text to Image, Text to Video, Image to Video, Windows & Cloud

Full tutorial link > https://www.youtube.com/watch?v=ocEkhAsPOs4

Wan 2.2 training is now so easy. I have done over 64 different unique Wan 2.2 trainings to prepare the very best working training configurations for you. The configurations are fully working locally with as low as 6 GB GPUs. So you will be able to train your awesome Wan 2.2 image or video generation LoRAs on your Windows computer with easiness. Moreover, I have shown how to train on cloud platforms RunPod and Massed Compute so even if you have no GPU or you want faster training, you can train on cloud for very cheap prices fully privately.

📂 Resources & Links:

Download the One-Click Installer & Configs: [ https://www.patreon.com/posts/Musubi-Tuner-Trainer-App-Configs-137551634 ]

Qwen Image Model Training Tutorial (Prerequisite): [ https://youtu.be/DPX3eBTuO_Y ]

SwarmUI & ComfyUI Setup Guide for Windows: [ https://youtu.be/c3gEoAyL2IE ]

SwarmUI Installer and Model Downloader : [ https://www.patreon.com/posts/SwarmUI-Install-Download-Models-114517862 ]

ComfyUI Installer : [ https://www.patreon.com/posts/ComfyUI-Installers-105023709 ]

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:

00:00:00 Introduction to Wan 2.2 Training & Capabilities

00:00:56 Installing & Updating Musubi Tuner Locally
00:02:20 Explanation of Optimized Presets & Research Logic
00:04:00 Differences Between T2I, T2V, and I2V Configs
00:05:36 Extracting Files & Running Update Batch File
00:06:14 Downloading Wan 2.2 Training Models via Script
00:07:30 Loading Configs: Selecting GPU & VRAM Options
00:09:33 Using nvitop to Monitor RAM & VRAM Usage
00:10:28 Preparing Image Dataset & Trigger Words
00:11:17 Generating Dataset Config & Resolution Logic
00:12:55 Calculating Epochs & Checkpoint Save Frequency
00:13:40 Troubleshooting: Fixing Missing VAE Path Error
00:15:12 VRAM Cache Behavior & Training Speed Analysis
00:15:51 Trade-offs: Learning Rate vs Resolution vs Epochs
00:16:29 Installing SwarmUI & Updating ComfyUI Backend
00:18:13 Importing Latest Presets into SwarmUI
00:19:25 Downloading Inference Models via Script
00:20:33 Generating Images with Trained Low Noise LoRA
00:22:22 Upscaling Workflow for High-Fidelity Results
00:24:15 Increasing Base Resolution to 1280x1280
00:27:26 Text-to-Video Generation with Lightning LoRA
00:30:12 Image-to-Video Generation Workflow & Settings
00:31:35 Restarting Backend to Clear VRAM for Model Switching
00:33:45 Fixing RAM Crashes with Cache-None Argument
00:35:13 Dual Model (High & Low Noise) Training Setup
00:36:54 Preparing Hybrid Datasets (Images + Videos)
00:37:40 Manually Editing Dataset TOML for Resolution Control
00:39:53 Setting High Noise Model Paths for Dual Training
00:41:50 Optimization: Block Swap vs CPU Offload
00:43:10 Generating Video with Dual-Model Trained LoRA
00:45:35 Massed Compute: Server Setup & Coupon Code
00:47:00 Connecting via ThinLinc & File Transfer Methods
00:49:12 Massed Compute: Fast UV Installation & Downloads
00:50:27 Loading Configurations on Massed Compute
00:52:18 Troubleshooting: Fixing Config Version Error
00:53:20 Dual Model Training Speed Analysis on Cloud
00:55:40 RunPod: Selecting the Correct Template & GPU
00:57:45 RunPod: Uploading Files & Extracting Archive
00:58:38 RunPod: Terminal Installation & Model Downloads
01:00:26 RunPod: Correct Pathing Syntax & Backslash Fix
01:01:28 Setting Dataset Paths on RunPod
01:03:34 Installing nvitop on RunPod Terminal
01:03:54 Speed Hack: Disabling Numpy Memory Mapping
01:06:00 Terminating Instances & Final Remarks

Greetings everyone! Today I am presenting an epic tutorial on how to train the Wan 2.2 model to generate extremely high-quality, realistic images and videos. This is currently the most advanced model for generating life-like textures and details.

In this comprehensive guide, I cover everything you need to know to train Wan 2.2 on your local Windows computer, as well as on cloud platforms like RunPod and Massed Compute. We utilize the SECourses Musubi Tuner with fully optimized, 1-click presets designed for every GPU range (from 6GB to 192GB VRAM).

🚀 What You Will Learn in This Tutorial:

Wan 2.2 Text-to-Image Training: How to train the Low Noise model for massive detail and realism.

Wan 2.2 Text-to-Video Training: Mastering Dual Model training (Low Noise + High Noise) for superior video consistency.

Image-to-Video Workflow: How to use your trained LoRAs to animate static images.

Cloud Training: Step-by-step guides for Massed Compute (ultra-fast disk speeds) and RunPod.

Performance Optimization: Using FP8 scaling, Block Swapping, and CPU offloading to train on consumer GPUs.

Inference & Upscaling: Using SwarmUI and ComfyUI to generate and upscale content to 4K resolution.

💡 Key Features of Our Workflow:

Auto-Resume & Speed: New UV package installers for lightning-fast setup.

Presets for All GPUs: Configurations included for 6GB, 12GB, 24GB, 48GB, and 80GB+ cards.

Dataset Automation: Auto-resizing and captioning for both image and video datasets.

Z-Image Turbo LoRA training with AI Toolkit and Z-Image ControlNet Full Tutorial for Highest Quality

Furkan Gözükara — Thu, 04 Dec 2025 23:23:10 +0000

Z-Image Turbo LoRA training with AI Toolkit and Z-Image ControlNet Full Tutorial for Highest Quality

Full tutorial: https://www.youtube.com/watch?v=ezD6QO14kRc

Z-Image Turbo LoRA training with Ostris AI Toolkit + Z-Image Turbo Fun Controlnet Union + 1-click to download and install the very best Z-Image Turbo presets. In this tutorial, I will explain how to setup Z-Image Turbo model properly in your local PC with SwarmUI and download models and use them with highest quality via ready presets. Moreover, I will show to install Z-Image Turbo Fun Controlnet Union to generate amazing quality images with ControlNet preprocessors. Furthermore, I will show how to 1-click install AI Toolkit from Ostris and train Z-Image Turbo model LoRAs with highest quality configs made for every GPU like 8 GB GPUs, 12 GB GPUs, 24 GB GPUs and so on. I did a massive research to prepare these Z-Image Turbo model training configurations.

👇 Links & Resources Mentioned:

Download SwarmUI & Models: [ https://www.patreon.com/posts/Download-SwarmUI-Models-114517862 ]

Ostris AI Toolkit (SECourses Version): [ https://www.patreon.com/posts/Ostris-AI-Toolkit-140089077 ]

Ultimate Batch Image Processing App: [ https://www.patreon.com/posts/Ultimate-Batch-Image-Processing-App-120352012 ]

SwarmUI with ComfyUI Backend Windows Tutorial: [ https://youtu.be/c3gEoAyL2IE ]

SwarmUI with ComfyUI Backend RunPod and Massed Compute Cloud Tutorial: [ https://youtu.be/bBxgtVD3ek4 ]

⏱️ Video Chapters:

00:00:00 Introduction to Z-Image Turbo Model

00:00:54 FP8 Scaled Version 5.7GB for Low VRAM

00:01:10 ControlNet Union with Z-Image Turbo

00:01:30 LoRA Training with Ostris AI Toolkit

00:02:00 Default vs Custom Training Preset Quality Comparison

00:03:00 RunPod Cloud Training Preview

00:03:40 MassedCompute Cloud Training Preview

00:04:16 Downloading Z-Image Models via SwarmUI

00:05:00 Z-Image Turbo Core Bundle & ControlNet Files

00:05:58 FP8 Scaled Model & Musubi Tuner Converter

00:07:13 Updating ComfyUI for Sage & Flash Attention

00:08:13 Updating SwarmUI & ControlNet Preprocessors

00:08:52 Updating & Importing Latest SwarmUI Presets

00:09:20 Generating with Quality 2 Fast Preset

00:10:48 Generating with Quality 1 Upscale Preset

00:11:35 Quality 1 vs Quality 2 Visual Comparison

00:12:13 Setting up ControlNet Input & Aspect Ratio

00:13:41 ControlNet Strength Settings & Canny Test

00:15:26 Using Depth Preprocessor with Z-Image

00:15:58 Coloring Lineart Drawings with ControlNet

00:16:58 Lineart Preprocessing Comparison

00:17:50 Ostris AI Toolkit Installation Prerequisites

00:19:12 Installing Ostris AI Toolkit on Windows

00:20:02 First Time UI Setup & Launching Interface

00:21:04 Loading Custom Training Configs

00:21:38 Creating a New Dataset Structure

00:22:24 Ultimate Batch Image Processing App Install

00:23:17 Dataset Prep Stage 1: Auto-Zooming with SAM2

00:26:08 Dataset Prep Stage 2: Resizing to Exact Resolution

00:28:12 How to Select Best Training Images

00:30:24 Importance of Emotions & Angles in Datasets

00:31:44 Z-Image Resolution & Aspect Ratio Rules

00:33:21 Configuring Training Parameters & Epochs

00:36:52 Resolution Impact on Training Speed

00:37:46 Starting the Training Job on Windows

00:38:39 Monitoring Training Progress & VRAM

00:39:43 Checkpoint Generation Settings

00:40:40 Resuming Training from Last Checkpoint

00:42:09 Training Speeds on RTX 5090 vs 4090 vs 3060

00:43:01 Training Quality: Default vs Custom Preset Comparison

00:44:21 Testing LoRAs with SwarmUI Grid Generator

00:46:04 Fixing ControlNet Error in Grid Generation

00:47:09 Comparing Generated LoRA Checkpoints

00:47:38 Using Trained LoRA with ControlNet Union

00:48:10 RunPod: GPU Selection & Template Setup

00:50:32 RunPod: Port 8675 Config & Initialization

00:51:36 RunPod: Uploading Installation Files

00:52:01 RunPod: One-Click Installation Command

00:54:07 RunPod: Starting AI Toolkit & Proxy Connection

00:54:38 RunPod: Uploading Dataset via Interface

00:55:32 RunPod: Starting the Training Job

00:56:24 RunPod: Speed & Cost Analysis

00:57:28 RunPod: Auto-Stop Command Setup

00:58:24 MassedCompute: GPU Selection & Coupon Code

01:00:16 MassedCompute: ThinLinc Client Setup

01:01:21 MassedCompute: Transferring Files to Shared Folder

01:02:55 MassedCompute: Installation Command

01:05:49 MassedCompute: Connecting via Public URL

01:06:54 MassedCompute: Starting Training Job

01:08:43 Downloading Checkpoints & Stopping Instance

🚀 Master Z-Image Turbo & LoRA Training: The Ultimate Guide!

In this comprehensive tutorial, I show you how to generate ultra-realistic images in seconds using the lightweight Z-Image Turbo model. We cover everything from 1-click installation on SwarmUI (ComfyUI backend) to mastering ControlNet Union for precise image control.

But that’s not all! I also reveal how to train your own high-quality Z-Image Turbo LoRAs using the Ostris AI Toolkit. I have developed a custom training preset that significantly outperforms the default settings—you have to see the comparison to believe it! Whether you are on a local PC, RunPod, or MassedCompute, this guide has you covered.

🔥 What You Will Learn:

Z-Image Turbo Setup: How to run this fast, 6GB model (FP8 included) on almost any GPU.

ControlNet Mastery: Use Canny, Depth, and Lineart to control your generations perfectly.

LoRA Training: Step-by-step guide

FLUX 2 vs FLUX SRPO, New FLUX Training Kohya SS GUI Premium App With Presets & Features

Furkan Gözükara — Tue, 25 Nov 2025 23:40:41 +0000

FLUX 2 vs FLUX SRPO, New FLUX Training Kohya SS GUI Premium App With Presets & Features

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

Info

FLUX 2 has been published and I have compared it to the very best FLUX base model known as FLUX SRPO. Moreover, we have updated our FLUX Training APP and presets to the next level. Massive speed up gaings with 0 quality loss and lots of new features. I will show all of the new features we have with new SECourses Kohya SS GUI Premium app and compare FLUX SRPO trained model results with FLUX 2.

Necessary Resources

Get the SECourses Premium Kohya Trainer DreamBooth / Fine Tuning : [ https://www.patreon.com/posts/Kohya-FLUX-DreamBooth-Trainer-App-112099700 ]
Get the SECourses Premium Kohya Trainer LoRA : [ https://www.patreon.com/posts/Kohya-FLUX-LoRA-Trainer-App-110879657 ]
DreamBooth Training Tutorial: [ https://www.youtube.com/watch?v=FvpWy1x5etM ]
LoRA Training Tutorial: [ https://www.youtube.com/watch?v=nySGu12Y05k ]
Qwen Image Realism Tutorial: [ https://youtu.be/XWzZ2wnzNuQ ]
Join our Discord Community: [ https://discord.com/servers/secourses-Discord-772774097734074388 ]

Some FLUX SRPO Generations With Medium Quality Training Images Dataset (28) vs FLUX 2 PRO Generations — BFL Website Playground Used — 2048x1152 px

First images are FLUX SRPO, second images are FLUX 2 PRO

This below image blocked on BFL site so only exists in local image as comparison

Official BFL Playground Link

https://playground.bfl.ai/image/generate

⏱️ Video Chapters:

00:00:00 Introduction to New FLUX Training Improvements and Local Training Showcase

00:00:24 Understanding FLUX SRPO Model: High Realism with Minimal VRAM Requirements

00:00:38 Updated Configurations for Training Realism on 6GB VRAM GPUs Locally

00:01:07 FLUX 2 Announcement and Setting Up Comparisons with BFL Playground

00:01:45 FLUX 2 Dev Model Technical Specs: 32 Billion Parameters and Hardware Challenges

00:02:11 Overview of Changes in SECourses Premium Kohya Trainer Version 35

00:02:46 Development Updates: GUI Improvements and Full Torch Compile Support

00:03:13 LoRA Presets Update: VRAM Optimization and Speed Improvements via Torch Compile

00:03:27 Introducing On-the-Fly FP8 Scaled LoRA Training Support

00:03:42 Quality Comparison Analysis: BF16 vs FP8 Scaled Weights LoRA

00:04:24 VRAM Usage and Speed Analysis: Block Swap Count Reduction with FP8 Scaled

00:05:12 Why 32GB GPUs Don't Need FP8 Scaled: Fitting Completely with Torch Compile

00:05:36 DreamBooth Training Specifics: BF16 Mixed Precision and Tab Selection

00:06:18 New 80GB GPU Configuration: Significant Training Speed Up and Cost Analysis

00:07:39 New Feature: FLUX FP8 Converter Tool for DreamBooth Models

00:08:10 Verifying Quality of Converted FP8 Scaled Models vs Original BF16

00:09:03 New Image Pre-processing Tool: Visualizing How Kohya Sees Your Dataset

00:09:34 Demonstration of Pre-processing: Identifying Padding and Orientation Issues

00:10:38 Additional Features: Memory Efficient Loading and CPU Text Encoder Caching

00:11:23 New Automated Model Downloader Tool: Installation and Model Selection Guide

00:12:35 FLUX 2 vs FLUX 1 Context: Can the New Model Replace Existing Workflows?

00:13:03 Setting Up the Generation Comparison: SRPO Fine-tune vs Base vs FLUX 2 Pro

00:14:13 Analyzing First Comparison Results: Portrait Quality and Realism Assessment

00:15:02 Second Comparison Test: Handling Unrealistic Elements and Animals in Prompts

00:15:33 Importance of Resolution and Platform Choice for FLUX 2 Quality

00:16:24 Analyzing Second Results: Prompt Adherence and Realism in FLUX 2 vs SRPO

00:17:07 Testing the Prompt on Nano Banana Pro: Quality Assessment

00:17:39 Comparison with Seedream 4 Model and Final Thoughts on FLUX 2 Potential

00:18:50 Current Recommendation: Why Qwen Image Realism is the Temporary King

More Info

In this video, I demonstrate the newest improvements and features added to our SECourses Premium Kohya Trainer (v35). We have achieved massive performance gains and VRAM reductions, allowing for high-quality FLUX training on GPUs with as little as 6GB of VRAM using the FLUX SRPO model.
I also break down the brand new FLUX 2 announcement! We perform a side-by-side comparison between my locally trained FLUX SRPO model, the base FLUX 1 Dev, and the newly released FLUX 2 Pro model to see if it’s time to switch workflows.

🚀 Key Updates Covered:

Full Torch Compile Support: Now enabled across all presets for faster training speeds.
FP8 Scaled LoRA Training: On-the-fly conversion that drastically reduces VRAM usage (0 block swaps on 24GB cards) with zero quality loss.
New Tools: Introducing the "FLUX FP8 Converter" to shrink DreamBooth models to 11.1GB and a new "Image Pre-processing" tool to visualize exactly how Kohya sees your dataset.
Hardware Optimization: New presets ranging from 6GB VRAM consumer cards up to 80GB A100/H100 configurations for lightning-fast training.
FLUX 2 Analysis: A realistic look at the 32-billion parameter giant and how it compares to our optimized FLUX 1 workflow.