SwarmUI Full Tutorial: 1-Click Install, 4 MP Images, Full HD Video with Sound, Lip Sync & Edits
SwarmUI, set up with our one-click installers, our model downloader (35+ bundles, 517+ models) and 86+ ready presets, turns your own PC into a complete AI studio: 4-megapixel images, one-prompt edits, full HD MiniMax H3 videos with speech, sound effects and music, lip sync and Genjutsu person swaps. This tutorial installs everything from zero on Windows and teaches every feature step by step; the same installers run on RunPod, SimplePod, Massed Compute and Linux.
Links:
Links:
Download the SwarmUI installer, model downloader and presets (our SwarmUI post): https://www.patreon.com/posts/swarmui-auto-and-114517862
ComfyUI backend installer (our ComfyUI post): https://www.patreon.com/posts/105023709
One-time Windows requirements installer tutorial: https://youtu.be/ptuLL0C72Ms
SwarmUI + ComfyUI on cloud GPUs (RunPod, Massed Compute): https://youtu.be/bBxgtVD3ek4
SimplePod tutorial: https://youtu.be/yOj9PYq3XYM
SECourses Discord: https://discord.com/invite/software-engineering-courses-secourses-772774097734074388
You will learn the full route on a fresh Windows PC: download and extract both packages, install our ComfyUI backend and SwarmUI, connect them, import our presets, download models in one-click bundles and update everything, then every image, edit, video, lip-sync, audio and tool feature listed in the chapters below.
Main topics include MiniMax H3 and FastH3, Krea 2 Turbo, Qwen Image 2.1, FLUX 3 Klein, FLUX Fill and Kontext, Ideogram 4, Z Image, SDXL, LTX 2.3, SVI 2 Pro, Genjutsu, Long Lip Sync, RefMods and our LLM prompt kits. Every result was made on the fresh install with an RTX 5090.
Use the chapters to jump to any install step, feature, setting or comparison.
Chapters:
00:00:00 One prompt: H3 video with speech, effects and music
00:01:04 What our installers, downloader and presets add
00:02:23 Quick first image at 4 MP with Krea 2 Turbo
00:03:36 Download both zips from our posts
00:06:16 Create the folders and extract both packages
00:07:45 Install our ComfyUI backend: Torch 2.13, CUDA 13
00:09:10 Install SwarmUI with one double-click, first-run setup
00:11:32 Connect the ComfyUI backend and its arguments
00:13:22 Import our 86 presets with one bat file
00:14:10 The routine: reset, then Direct Apply a preset
00:15:09 Model downloader: the Krea 2 bundle in one click
00:18:24 More bundles, single models, URL downloads
00:20:38 First 4 MP image, bundle cards and model report
00:23:05 Update in six steps, verified models kept
00:27:58 What one preset click sets, our 11 extensions
00:29:50 Tour of the Generate page
00:32:43 Find the right preset for each job
00:34:35 Text in images: Ideogram 4 vs Qwen Image 2.1
00:36:59 Size, aspect ratio and our Megapixels option
00:38:09 Images, seeds and Variation Seed
00:39:56 Steps 4, 8, 16 compared; CFG, sampler, Sigma Shift
00:41:47 SDXL: negative prompt and CFG 3, 7, 12 compared
00:44:08 Z Image seed variety trick, Reuse Parameters
00:46:10 Prompt weights, alternate and from-to syntax
00:48:34 Regional prompt: a white wolf in one area
00:49:18 Random picks, wildcards and variables
00:52:21 Auto segment faces, more tags, LLM prompt kits
00:54:36 LoRAs: Skin Fix at weight 0.6 vs 1.0
00:57:06 FLUX Kontext edit and fixing model metadata
00:59:41 Refine and upscale a draft to 4 MP
01:02:32 Init Image creativity 0.3, 0.55 and 0.8
01:04:41 Inpaint a dragon: Image Editor and SAM 2 masks
01:07:35 Remove a watermark, every other pixel kept
01:10:12 Outpainting in small steps with FLUX Fill
01:13:53 Qwen Image 2.1: gold armor from one prompt
01:16:23 Combine images; FLUX 3 Klein vs Qwen edit
01:18:46 Layout boxes place every object exactly
01:21:46 ControlNet Canny and Redux style transfer
01:26:12 Attach media, trim clips, prompt batches
01:29:03 H3 references, @ tokens and the token meter
01:30:48 Write an H3 prompt with our kit and Gemini
01:31:52 Text to video with sound: MiniMax H3 at 1080p
01:33:35 8-step turbo LoRA vs 20 steps, RIFE smoothing
01:36:14 Image to video: the portrait moves and speaks
01:37:42 First and last frame: black armor to gold
01:39:02 Video to video with LTX 2.3: anime style
01:40:15 Genjutsu: swap the person, keep every move
01:43:12 Longer videos: continue a clip, SVI 2 Pro
01:46:21 Long Lip Sync: a portrait speaks in full HD
01:49:39 References to video: face, dragon and voice
01:51:15 Save a character and voice as a RefMod
01:53:44 Sound only with H3, Foley for a silent clip
01:57:19 Grid Generator: samplers by steps
01:59:51 Compare results, History and the video editor
02:02:18 The ComfyUI workflow behind a preset
02:04:16 Speed overrides and a second GPU backend
02:06:04 Server, user settings, Utilities and the API
02:09:20 Recap and where to download everything
4 November 2026 Update V189
Edit real videos with MiniMax H3 in SwarmUI. Five new presets: replace the background of any video from one image, relight a whole clip, put a new face on someone, replace a person or object while every other pixel stays as filmed, and make long Pika H3 Flex videos that follow a story, scene by scene.
Amazing SwarmUI Presets moves to V88 with 99 presets: 5 new since V86, every earlier preset unchanged.
Real footage and real runs of the shipped presets:
Every result in this post comes from a real run of the shipped presets in SwarmUI.
All 99 presets in the Presets tab, the new ones marked NEW:
The new presets up close, each with its own animal thumbnail:
Windows_Preset_Delete_Import.bat brings all of them into your SwarmUI; the steps are in How to update at the end.
To run them, download the MiniMax-H3 Core Bundle. It includes the FaceSwap LoRA; if you already have the bundle, only the missing files download:
All the new presets use this one bundle.
Our live token counter is above the prompt: it counts your text, references, audio and video as you work and shows them against the MiniMax H3 limit, in green, amber and red, so you know what a run needs before you click Generate.
NEW PRESET — BACKGROUND REPLACE: YOUR VIDEO, A NEW BACKGROUND, NOTHING ELSE
"MiniMax H3 Background Replace - Pika H3 Flex 6 Steps - 261104"
Fully automatic: attach your video and a background image, and click Generate. The person is found by itself and stays exactly as filmed: every pixel of the face, hair, clothes and hands, the lip movements, the timing and the sound. Everything around them becomes the place in your image and moves with your camera.
Where to find it: Presets tab → filter 261104 → apply the preset, attach both files beside the prompt and click Generate. There is nothing to write or set. Long clips work too: the video is made in overlapping windows, so a long clip needs no more GPU memory, only more time. The result is about 1 megapixel. People of similar size all stay, and distant passers-by go.
NEW PRESET — VIDEO RELIGHT
"MiniMax H3 Video Relight - Pika H3 Flex 6 Steps - 261104"
Relight a whole video. Attach your clip and click Generate: the prompt already holds a complete neon noir lighting plan. The people, the motion, the camera and the set stay.
Where to find it: Presets tab → filter 261104. Change the colours or directions in the Lighting plan lines of the prompt. H3 follows the plan through the prompt, so it is not pixel-exact light control; try two or three seeds.
NEW PRESET — FACE SWAP
"MiniMax H3 Face Swap - Ref2VA 8 Steps - 261104"
Put a new face on the person in your video. Attach your clip and a clear close-up of the new face, leave the prompt empty and click Generate. Clothes, setting and camera stay as in your clip.
H3 makes the whole clip anew, so the timing of the motion can drift a little. For your clip's exact timing and sound, use the Masked Edit preset below with Genjutsu Target set to head.
NEW PRESET — GENJUTSU MASKED EDIT: CHANGE ONE THING, KEEP EVERYTHING ELSE
"MiniMax H3 Genjutsu - Masked Edit - Pika H3 Flex 6 Steps - 261104"
Replace a person or an object and keep the rest of your clip exactly as filmed. Attach your clip and the new character and click Generate: the person is found and the prompt is written for you. The street, the traffic, the signs and the camera move stay untouched.
Where to find it: Presets tab → filter 261104. To replace something else, name it in Genjutsu Target: a car, a dog, a man in a blue suit.
NEW PRESET — PIKA H3 FLEX LONG VIDEO THAT TELLS A STORY
"Pika H3 Flex - Long Text to Video 20 Seconds - 261104"
A long video that develops instead of repeating. Write your description, then a line with ---, then one scene, another ---, the next scene. Each part of the video follows its own scene.
Five scenes in one prompt, one continuous 20-second flight:
Where to find it: Presets tab → filter 261104. About 4 seconds per scene works well; set Text2Video Frames for other lengths (481 = 20 s, 719 = 30 s). Without --- every window reads the same prompt, so motion can repeat. Scenes work in text runs, not with reference media.
HOW TO UPDATE
- Download SwarmUI_Model_Downloader_v189.zip from this post and extract it over your downloader folder.
- Close SwarmUI and run Windows_Install_or_Update_SwarmUI.bat.
- Update the ComfyUI backend. With our ComfyUI installation, close SwarmUI again (step 2 starts it) and run Windows_Install_Or_Update_ComfyUI.bat from our ComfyUI V149. With SwarmUI's own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start.
- Restart SwarmUI, then run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v88.json. It backs up your current presets first, then replaces them all, your own presets too.
- Run Windows_Start_Download_Models_App.bat and download the MiniMax-H3 Core Bundle.
ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709
30 October 2026 Update V187
Pika H3 Flex: cinematic video with synchronized sound in 6 steps. Three new presets bring Pika Labs' new Pika H3 Flex to SwarmUI: text to video, beginning and ending frame to video and references to video, each with dialogue, sound effects and music made together with the picture.
Amazing SwarmUI Presets moves to V86 with 94 presets: 3 new, every earlier preset unchanged.
Our three examples: a ship in a bottle that sails out onto a stormy ocean, a blacksmith whose golden eagle lands on his anvil, and an airship captain made from just two images:
Every result in this post is a real run of the shipped presets in SwarmUI on our RTX 5090.
All 94 presets of Amazing SwarmUI Presets V86 in SwarmUI's Presets tab, the new ones marked NEW:
The 3 new presets up close, each with its own animal thumbnail:
Windows_Preset_Delete_Import.bat brings all of them into your SwarmUI; the steps are in How to update at the end.
NEW PRESETS — PIKA H3 FLEX: VIDEO WITH SOUND IN 6 STEPS
"Pika H3 Flex - Text to Video 6 Steps - 261030"
"Pika H3 Flex - Beginning and Ending Frame to Video 6 Steps - 261030"
"Pika H3 Flex - References to Video 6 Steps - 261030"
Pika's tuned MiniMax H3, in 6 steps. A 5-second 1344 × 768 clip with stereo sound takes about a minute on an RTX 5090. Init Audio, face inpainting and your own MiniMax H3 LoRAs stay available, as in every MiniMax H3 preset.
To run them, download the MiniMax-H3 Core Bundle. It now includes the two Pika H3 Flex LoRAs; if you already have the bundle, only those 3.6 GB download:
Beginning and Ending Frame: give it two images and it makes the shot between them. Our ship in a bottle becomes the real ship on the open sea in one continuous camera move:
Where to find it: Presets tab → filter Pika → Direct Apply Pika H3 Flex - Beginning and Ending Frame to Video 6 Steps - 261030. Put the beginning frame in Init Image, tick Display Advanced Options and put the ending frame in Image To Video → Video End Image, then click Generate:
Start the prompt with Pika's timing line; the preset description has it ready to copy. Leave Video End Image empty for first frame to video.
Text to Video: one prompt gives the whole scene, with the blacksmith's line, the hammer, the hiss of steam and the eagle's wingbeats in the soundtrack:
References to Video: attach a character image and a place image beside the prompt; our captain walks his sky harbour with his beard, goggles, green scarf and compass kept:
The MiniMax H3 prompt guide now covers Pika H3 Flex, so ChatGPT, Claude or Gemini can write your prompts.
ALSO IN V187
- The MiniMax-H3 Low VRAM Bundle includes the two Pika H3 Flex LoRAs too.
- SwarmUI's scheduler list gains pika_h3_flex, Pika's official 6-step schedule, after the update below.
HOW TO UPDATE
- Download SwarmUI_Model_Downloader_v187.zip from this post and extract it over your downloader folder.
- Close SwarmUI and run Windows_Install_or_Update_SwarmUI.bat.
- Update the ComfyUI backend. With our ComfyUI installation, close SwarmUI again (step 2 starts it) and run Windows_Install_Or_Update_ComfyUI.bat from our ComfyUI V147. With SwarmUI's own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start.
- Restart SwarmUI, then run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v86.json. It backs up your current presets first, then replaces them all, your own presets too.
- Run Windows_Start_Download_Models_App.bat and download the MiniMax-H3 Core Bundle.
ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709
28 October 2026 Update V186
Anima character transfer, MOSS-Image layout control, stronger MiniMax H3 Genjutsu and faster FastH3 decoding. Put one character into any scene with Anima, place and pose people with simple color and depth maps in MOSS-Image, swap characters in your clips more convincingly with the new Genjutsu task LoRAs, and decode FastH3 Omni videos faster with LightVAE.
Amazing SwarmUI Presets moves to V85 with 91 presets: 5 new, 2 updated, and 24 others now switch the new options off when you apply them.
With the adapter's example maps, both new MOSS-Image presets put the two men where the mannequins stand, in their poses; without maps, the same prompt and seed picks its own layout:
Every result in this post is a real run of the shipped presets in SwarmUI on our RTX 5090.
All 91 presets of Amazing SwarmUI Presets V85 in SwarmUI's Presets tab, the new ones marked NEW and the updated ones UPDATED:
The 5 new and 2 updated presets up close:
Windows_Preset_Delete_Import.bat brings all of them into your SwarmUI; the steps are in How to update at the end.
NEW PRESETS — ANIMA: TAKE YOUR CHARACTER INTO A NEW SCENE
"Anima - Advanced Text To Image - 261028"
"Anima - Reference Character And Style - 261028"
One image of your character, any new scene. The Anima reference adapter carries the face, hair and outfit, and part of the drawing style, from your image, while your prompt picks the pose, place and light. Every final image is a clean 2048 × 2048.
To run them, download the Anima Core Bundle (3.84 GB) from the model downloader:
Our example: one character made with text to image, then four new scenes from that single image with one click on Generate prompt batch:
Where to find it: Presets tab → filter Anima → Direct Apply Anima - Reference Character And Style - 261028. Upload your character in Anima Reference Image, add your scene prompts and click Generate prompt batch:
The new Anima_Enchance_Prompt_Feed_For_LLMs.txt lets ChatGPT, Claude or Gemini write your prompts or a whole scene series.
NEW PRESETS — MOSS IMAGE COLOR + DEPTH CONTROL: PLACE YOUR PEOPLE WITH A MAP
"MOSS Image - Color + Depth Control - 261027"
"MOSS Image - Turbo 8 Steps Color + Depth Control - 261027"
Draw the layout, MOSS-Image follows it. A color map marks where each person or object goes, a depth map shows what is near and far, and your prompt says who they are. Turbo makes a 1024 × 1024 image in about 4 seconds.
To run them, download the MOSS-Image Core Bundle. It now includes the color + depth adapter; if you already have the bundle, only that 0.29 GB file downloads:
Where to find it: Quick Tools → Reset Params to Default, then Presets tab → filter Color + Depth → Apply. Add your maps with the Upload buttons of MOSS Image Color Map and MOSS Image Depth Map, describe each person and press Generate:
