Home Creators Posts Import Register Favorites Logout

Content

MiniMax H3 Image is a new 33.1B model that generates and edits 16 MP pictures in 6 steps on your own GPU; our ComfyUI V150 ships two ready presets for it.

Running locally in ComfyUI, it is ultra fast even at 16 MP and works with as low as 6 GB VRAM. The Text To Image 16 MP and Image Edit Up To 16 Images presets include MiniMax's local prompt enhancer, and Model Downloader V190 fetches every model in one bundle.

1 MP vs 16 MP: See Every Whisker With MiniMax H3 Image in ComfyUI, Text to Image in 6 Steps

Full tutorial link > https://www.youtube.com/watch?v=xCtDQOn2zWQ

1 MP vs 16 MP: See Every Whisker With MiniMax H3 Image in ComfyUI, Text to Image in 6 Steps

MiniMax H3 Image is a new 33.1B image model that generates and edits pictures at 16 megapixels, 4096 × 4096 or a matching wide or tall size, in only 6 sampling steps on your own NVIDIA GPU, with no upscaler. Our SECourses ComfyUI installer V150 ships two ready presets for it, Text To Image 16 MP and Image Edit Up To 16 Images, with every model and setting already chosen. MiniMax's official prompt enhancer runs locally inside them in three modes (reasoning, fast and off): it turns a short idea in any language into the detailed caption the model was trained on, picks the aspect ratio, and a box shows the exact prompt the model received. The SECourses Model Downloader V190 fetches every model file into the right folders from one bundle. In this mini tutorial a rusted, moss-covered Volkswagen Beetle is restored with one plain sentence, 9 typed words become a 16 MP photo of a fox, and you see a room furnished from 4 photos, letter-perfect posters and 1 MP vs 4 MP vs 16 MP.

Links:

You will learn how to open the MiniMax H3 Image text to image preset from the Presets folder with Ctrl+O, write a short idea in box 1 in any language, keep the recommended 16 MP output size, use the prompt enhancer in reasoning mode for the best captions or fast mode for quick tries, switch it off when you write a long caption yourself, read the exact prompt the model received, and inspect the result at full size. In the image edit preset you add your photo to the gallery as @image1, write the change as one plain sentence with no mask, say what must stay the same (the forest, the light, the camera angle), and name more reference images with @image2 and @image3. Finally you set up the route yourself: download the ComfyUI V150 zip from our Patreon post, extract it over your ComfyUI folder, run the update file, install bundle 100 with the bundles installer, then open the MiniMax-H3 Core Bundle in the Model Downloader (4 files for images, about 44 GB) or the Low VRAM Bundle, which brings a smaller version of the image model.

Main topics include MiniMax H3 Image, ComfyUI presets, text to image, AI photo restoration, multi-image editing with @image tags, the local prompt enhancer, automatic aspect ratio, 6-step sampling, native 16 MP without an upscaler, RTX 5090 speed and lower VRAM use.

Use the chapters to jump to the first image, the photo edit, the comparisons, the speed numbers or the downloads.

Chapters:

  • 00:00:00 A rusted wreck restored at 16 megapixels

  • 00:01:21 Where the two new MiniMax presets live

  • 00:01:37 Text to image: a 16 MP picture from words

  • 00:02:22 The prompt enhancer: MiniMax's own, running locally

  • 00:03:22 The exact prompt the model received

  • 00:03:49 Fast enhancer mode: a 16 MP image in real time

  • 00:04:37 Image edit: restore a photo with one sentence

  • 00:05:34 The restored car and why it moved into a showroom

  • 00:06:11 Many references, lettering, sizes, speed and lower VRAM

  • 00:06:42 1 vs 4 vs 16 MP: 16 MP recommended

  • 00:06:58 RTX 5090 speed, and with a 12 GB limit

  • 00:07:27 Get the V150 zip and the model bundle

  • 00:07:59 The MiniMax-H3 model bundle in the Model Downloader

Measured numbers and their conditions: on an RTX 5090 with the models loaded, 6 steps, prompt encoding and decoding included and the prompt enhancer not included, 1 MP took 3.4 s, 4 MP 5.7 s and 16 MP 15.7 s. With ComfyUI limited to 12 GB of the same card's memory, a 16 MP image still finished in 19.5 s, the rest streaming from system RAM; a real 12 GB card computes slower. On camera, the fast enhancer mode made a second 16 MP fox in under half a minute from the click, and reasoning mode adds about a minute for the best captions.

This video is for ComfyUI users and AI image makers with an NVIDIA GPU who want the newest local image model at its full 16 megapixel quality without collecting files, nodes and settings by hand: open a preset, write one sentence and click Run. If ComfyUI is new for you, start with the installation tutorial linked above; if it is already installed, the update tutorial shows the zip update step by step.

For support, questions, feature requests or installation issues, see the pinned comment, our Patreon posts, our Discord and the video comments. Thank you for watching.

10 November 2026 Update V150

Presets Folder Content In Latest Zip File

MiniMax H3 Image is here: 16-megapixel images in 6 steps. Two new presets turn a few words into images up to 6272 pixels wide and edit your photos with up to 16 images at once. MiniMax's own prompt enhancer runs locally inside the presets: a short idea in any language becomes the detailed caption the model was trained on, and the enhancer even picks the best shape for your image.

Real runs of the new presets:

Every image in this post comes from a real run of the shipped presets with their default settings.

The complete Presets folder of V150, the new ones marked NEW:

To run them, download the MiniMax-H3 Core Bundle. It now includes MiniMax H3 Image, its VAE and the prompt enhancer model; the text encoder is the one MiniMax H3 video already uses, so H3 users download only the new files:

Both new presets use this one bundle. The MiniMax-H3 Low VRAM Bundle has the smaller W4A8 versions.

NEW PRESET — TEXT TO IMAGE AT 16 MEGAPIXELS

"MiniMax H3 Image - Text To Image 16 MP - 6 Steps - 261110"

Type an idea, press Run, get a 16-megapixel image. The prompt enhancer writes the full description and chooses the aspect ratio, from tall posters to 21:9 panoramas. A snow leopard from one sentence, at 5024 x 3360:

It writes text you can read. A travel poster with two exact lines of lettering, 3072 x 5472:

Panoramas come out in one piece, with no upscaler. Asked for a wide view, the enhancer chose 21:9, 6272 x 2688; below it, three details at their real pixels:

Fine detail at 4096 x 4096. Open it full size and read the screw slots and the jewels:

Where to find it: open the preset, write your idea in the gallery box and press Run:

The box under the result shows the exact prompt the model received. Set the enhancer to Off to use your own long caption; our new MiniMax H3 Image LLM guide in the zip makes ChatGPT, Claude or Gemini write one for you.

1 MP VS 4 MP VS 16 MP

Why 16 MP is the default. The same caption and seed at three sizes, with the face from each cropped to the same share of the frame:

16 MP has sixteen times the pixels of 1 MP, and it uses them: fur, whiskers and frost that 1 MP can only blur. It stays fast, too. Seconds per image on an RTX 5090, also with ComfyUI limited to 24, 16 or 12 GB of its memory:

A 16 MP image takes about 16 seconds with all memory and about 20 seconds when ComfyUI may use only 12 GB; the rest streams from system RAM. Lower the size in 02 OUTPUT SIZE whenever you want a quick draft.

NEW PRESET — IMAGE EDIT WITH UP TO 16 IMAGES

"MiniMax H3 Image - Image Edit Up To 16 Images - 6 Steps - 261110"

Edit your photo with one sentence. Add the image, write the change in any language and press Run. The prompt enhancer looks at your images and writes the full edit description, and the result keeps your photo's shape at 16 MP. A moss-covered wreck comes back to life, while the forest, the branches and the camera stay:

Combine many images. An empty room and three product photos, named @image1 to @image4 in the instruction: the exact armchair, lamp and plant land in the unchanged room:

Where to find it: open the preset, add your images to the gallery, write the change and press Run:

Leave the gallery empty and it works as a text to image preset, so both presets do both jobs.

BUILT IN, LIKE ALL OUR PRESETS

  • Batches: + Prompt adds more prompts in a row, and a folder of .txt files runs one image per file.

  • The prompt enhancer in three modes: official with reasoning (best), fast without reasoning, or off.

  • Optional LoRA stack, shared seed and images per prompt.

  • Less memory: pick the W4A8 model in the same loader; BF16 is there for original precision.

HOW TO UPDATE

  1. Download the latest ComfyUI_V150.zip from this post and extract it over your installer folder.

  2. Close ComfyUI, and SwarmUI too if it uses this ComfyUI, then run Windows_Install_Or_Update_ComfyUI.bat.

  3. Run Windows_Custom_Nodes_Bundles_Installer.bat and install bundle 100.

  4. Download the MiniMax-H3 Core Bundle (or the Low VRAM Bundle) with our SwarmUI Model Downloader V190 or newer.

  5. Restart ComfyUI and refresh the browser tab.

SwarmUI Installer and Unified Massive Models Downloader: https://www.patreon.com/posts/114517862

4 November 2026 Update V149

Presets Folder Content In Latest Zip File

Edit real videos with MiniMax H3, and let the presets do the work. Six new presets replace the background of any video from one image, relight a whole clip, put a new face on someone, move a subject along a path you draw, upscale your video and replace a person or object while every other pixel stays as filmed. The Pika H3 Flex presets now write their own prompt when you leave it empty, and a long video can follow a story, scene by scene.

Real footage and real runs of the shipped presets:

Every result in this post comes from a real run of the shipped presets.

The complete Presets folder of V149, the new ones marked NEW and the updated ones UPDATED:

To run them, download the MiniMax-H3 Core Bundle. It includes the FaceSwap LoRA and the H3 latent upscaler; if you already have the bundle, only the missing files download:

All the new presets and the updated Pika H3 Flex presets use this one bundle.

BUILT IN — OUR LIVE TOKEN COUNTER

See what a run needs before you press Run. Our gallery counts the tokens of your text, references, audio and video as you work and shows them against the MiniMax H3 limit, with the size, the length and the mode beside them. It moves from green to amber to red as you get close, so you can shorten a clip or lower the size first. With long video windows it counts per window, because each window is one run:

Beside it in every preset: Load + trim to pick the part of your clip, folder batch with optional merging, and Continue From Last Video Frames.

NEW PRESET — BACKGROUND REPLACE: YOUR VIDEO, A NEW BACKGROUND, NOTHING ELSE

"MiniMax H3 Background Replace - Pika H3 Flex 6 Steps - 261104"

Fully automatic: give it your video and a background image, and press Run. 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.

A talking man on a grey wall goes to a tropical beach, and a walking man in New York goes to a futuristic city:

There is nothing to write or set. Add your two files, press Run:

Long clips work too; we tested 31 seconds (736 frames). The video is made in overlapping windows, so a long clip needs no more GPU memory than a short one, only more time. The result is about 1 megapixel; run it through the Video Upscale preset below for a sharper video. 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. Add your clip and pick one of 20 looks such as neon noir, golden sunset backlight or blue hour, or design up to three lights yourself with their direction, softness and colour. The people, the motion, the camera and the set stay.

The same street clip in neon noir:

The look, the lights and a preview sphere of where the key light comes from:

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. Add your clip and a clear close-up of the new face. Clothes, setting and camera stay as in your clip, and the body motion follows it.

A selfie clip with a new red-bearded face:

Two inputs and Run:

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 target set to head.

NEW PRESET — PIKA H3 FLEX CUT AND DRAG MOTION

"Pika H3 Flex - Cut And Drag Motion To Video 6 Steps - 261104"

Draw a path on your photo and the subject follows it. Upload your photo and drag the path. The subject and the prompt are found and written for you. The subject is cut out and dragged along your path, and Pika H3 Flex turns that rough drag into a real video with moving light and sound.

From the photo, through the rough drag, to the finished drive:

Your photo, your path and Run:

Type a subject or a prompt whenever you want full control. Then the prompt model is not loaded at all.

NEW PRESET — VIDEO UPSCALE

"MiniMax H3 Video Upscale - Pika H3 Flex - 261104"

Fully automatic: give it your video and press Run. Your clip is encoded into MiniMax H3, enlarged by the H3 latent upscaler and refined by the last Pika H3 Flex steps, so the new detail is real video detail, not a sharpening filter. Your soundtrack stays exact.

Real footage reduced to 1280 x 704 and upscaled to 2560 x 1408, input on the left and result on the right, at the same moment:

Add your video and press Run:

What to expect: landscapes, animals and textures gain the most. H3 redraws fine detail, so small text and fine logos can change; on our harbor test a boat's small name came out garbled. One run makes the video at most twice as large.

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. The street, the passers-by, the signs, the camera move and the sound stay untouched; only the target is regenerated and pasted back over your original frames.

A man on a New York street becomes a knight in armour, and the traffic behind him keeps moving:

Your clip and the new character are all it needs. The person is found and the prompt is written for you:

To replace something else, name it in target: a car, a dog, a man in a blue suit. For a face swap with your clip's exact timing and sound, set target to head and use a close-up of the new face.

UPDATED — PIKA H3 FLEX: LONG VIDEO THAT TELLS A STORY

"Pika H3 Flex - Text To Video 6 Steps - 261030"

A long video that develops instead of repeating. Switch on 9. LONG VIDEO, 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 from a meadow to a sunset over the mountains:

The switch and the prompt:

About 4 seconds per scene works well. Without --- the preset works as before: every window reads the same prompt, so motion can repeat. Scenes work in text runs, not with reference media.

UPDATED — PROMPTS WRITE THEMSELVES

"Pika H3 Flex - First Last Frame To Video 6 Steps - 261030"
"Pika H3 Flex - References To Video 6 Steps - 261030"

Leave the prompt empty and it is written for you. A local Qwen3-VL 8B looks at your frames or reference images and writes the MiniMax H3 prompt. Type your own whenever you want full control, and that model is not loaded at all.

UPDATED — PIKA H3 FLEX: 2K

Sharper video with one switch. In the Pika H3 Flex presets, turn on 8. 2K UPSCALE and the video is refined at 2560 pixels with the same sound. Same seed, without and with the 2K pass:

Where to find it: in any of the three Pika H3 Flex presets, switch on 8. 2K UPSCALE, or 9. LONG VIDEO for clips over 15 seconds:

Both switches start off, so your runs stay as before until you turn them on.

HOW TO UPDATE

  1. Download the latest ComfyUI_V149.zip from this post and extract it over your installer folder.

  2. Close ComfyUI, and SwarmUI too if it uses this ComfyUI, then run Windows_Install_Or_Update_ComfyUI.bat.

  3. Run Windows_Custom_Nodes_Bundles_Installer.bat and install bundle 100.

  4. Download the MiniMax-H3 Core Bundle with our SwarmUI Model Downloader V189 or newer.

  5. Restart ComfyUI and refresh the browser tab.

SwarmUI Installer and Unified Massive Models Downloader: https://www.patreon.com/posts/114517862

30 October 2026 Update V147

Presets Folder Content In Latest Zip File

Pika H3 Flex: cinematic video with synchronized sound in 6 steps. Three new presets bring Pika Labs' new Pika H3 Flex to ComfyUI: text to video, first + last frame to video and references to video, each with dialogue, sound effects and music made together with the picture.

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 on our RTX 5090.

The complete Presets folder of V147: 116 ready-to-use ComfyUI presets plus 3 API presets, the new ones marked NEW:

The presets cover Anima, AvatarForever, ERNIE Image, FastH3 Omni, Fibo 2.0, FLUX.1 Dev, Kontext and SRPO, FLUX 2, FLUX 3 Klein, Ideogram 4, Krea 2, LTX 2, LTX 2.3, LTX 2.5, MiniMax H3 with Genjutsu, MiniMax Music 3, MOSS-Image, Phantom Wan, Pika H3 Flex, Qwen Image, SDXL, Stable Video Infinity 2 Pro, Wan 2.1, Wan 2.2 and Z-Image.

NEW PRESETS — PIKA H3 FLEX: VIDEO WITH SOUND IN 6 STEPS

"Pika H3 Flex - Text To Video 6 Steps - 261030"
"Pika H3 Flex - First Last 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. Each preset switches by itself between the text and frames model and the references model.

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:

First + Last 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: Workflows → SECourses → Pika H3 Flex - First Last Frame To Video 6 Steps - 261030. Upload your first frame in INIT IMAGE and your last frame in LAST FRAME, describe what happens and press Run:

The timing line Pika H3 Flex expects is added for you with the real length of your clip. Leave LAST FRAME 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: our captain image and sky harbour image went in, a walking, talking scene came out, with his beard, goggles, green scarf and compass kept:

Prompt batches, .txt folder batches, Init Audio, an optional LoRA stack and face refinement are built in. The MiniMax H3 prompt guide now covers Pika H3 Flex, so ChatGPT, Claude or Gemini can write your prompts.

HOW TO UPDATE

  1. Download the latest ComfyUI_V147.zip from this post and extract it over your installer folder.

  2. Close ComfyUI, and SwarmUI too if it uses this ComfyUI, then run Windows_Install_Or_Update_ComfyUI.bat.

  3. Run Windows_Custom_Nodes_Bundles_Installer.bat and install bundle 100.

  4. Download the MiniMax-H3 Core Bundle with our SwarmUI Model Downloader V187 or newer.

  5. Restart ComfyUI and refresh the browser tab.

SwarmUI Installer and Unified Massive Models Downloader: https://www.patreon.com/posts/114517862

28 October 2026 Update V146

Presets Folder Content In Latest Zip File

Anima character transfer, MOSS-Image layout control and stronger MiniMax H3 Genjutsu. Put one character into any scene with Anima, place and pose people with simple color and depth maps in MOSS-Image, decode FastH3 videos faster with LightVAE, and swap characters in your clips more convincingly with the new Genjutsu task adapters.

MOSS-Image Color + Depth Control turned the adapter author's two-person example maps into photos, and MOSS Image Edit then added snow and autumn without touching the two men:

Every result in this post is a real run of the shipped presets on our RTX 5090.

The complete Presets folder of V146: 113 ready-to-use ComfyUI presets plus 3 API presets, new ones marked NEW and updated ones UPDATED:

The presets cover Anima, AvatarForever, ERNIE Image, FastH3 Omni, Fibo 2.0, FLUX.1 Dev, Kontext and SRPO, FLUX 2, FLUX 3 Klein, Ideogram 4, Krea 2, LTX 2, LTX 2.3, LTX 2.5, MiniMax H3 with Genjutsu, MiniMax Music 3, MOSS-Image, Phantom Wan, Qwen Image, SDXL, Stable Video Infinity 2 Pro, Wan 2.1, Wan 2.2 and Z-Image.

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 SwarmUI Bundles tab of our model downloader:

Our example: one character made with text to image, then four new scenes from that single image in one prompt batch:

Where to find it: Workflows → SECourses → Anima - Reference Character And Style - 261028. Add your character with + Add references, write the new scene, add more scenes with + Prompt and press Run:

Prompt batches, .txt folder batches and an optional LoRA stack are built in. 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 AND POSE PEOPLE WITH SIMPLE MAPS

"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. The Turbo preset makes a 1024 × 1024 image in about 7 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:

The 50-step preset after the run that made the park photo at the top of this post:

Load your maps with choose file to upload in each map node. Part 8 of the MOSS-Image prompt guide writes the prompt for your maps.

UPDATED PRESETS — MOSS IMAGE EDIT: NOW ON COMFYUI'S NATIVE EDIT SUPPORT

"MOSS Image Edit - Advanced Image Edit - 261022"
"MOSS Image Edit - Turbo 8 Steps - 261022"

Both edit presets now run on ComfyUI's own MOSS-Image edit support and open with an empty gallery: add your photo, type the instruction, press Run. Up to 4 images, and the Turbo edit takes about 6 seconds. They use the same MOSS-Image Core Bundle.

NEW PRESET — FASTH3 OMNI REFERENCES TO VIDEO WITH THE LIGHTVAE DECODER

"FastH3 Omni - LightVAE References To Video 8 Steps - 261027"

The same FastH3 Omni video, decoded faster. LightVAE, a lighter video decoder from LightX2V, decoded and saved our 5-second video in under 6 seconds instead of over 8, with nearly the same picture.

To run it, download the FastH3 Omni Core Bundle. It now includes the LightVAE decoder and the Genjutsu adapters:

The preset after a real run:

Switch the decoder node to Original video VAE and press Run to compare: ComfyUI only decodes again.

UPDATED PRESETS — MINIMAX H3 GENJUTSU: CHARACTER SWAP AND MOTION TRANSFER ADAPTERS

"MiniMax H3 Genjutsu - FastH3 Omni 8 Steps - 261024"
"MiniMax H3 Genjutsu - Ref2VA 20 Steps - 261024"

Swap the person in any clip for your character, now with adapters trained for exactly this job. Genjutsu keeps the clip's motion, timing, camera and sound; the new Character Swap and Motion Transfer adapters by Alisson Anjos make the transfer much stronger. Clips with mono sound now work too.

The FastH3 Omni 8 Steps preset uses the FastH3 Omni Core Bundle above. The Ref2VA 20 Steps preset uses the MiniMax-H3 Core Bundle, which now includes the three Genjutsu adapters:

Our armoured warrior in a shadowboxing clip, made by both updated presets:

The FastH3 Omni Genjutsu preset after that run, with the new parts numbered:

Pick video background to keep the clip's scene or image to keep your character's background. Low VRAM mode is on by default with the same output.

HOW TO UPDATE

  1. Download the latest ComfyUI_V146.zip from this post and extract it over your installer folder.

  2. Close ComfyUI, and SwarmUI too if it uses this ComfyUI, then run Windows_Install_Or_Update_ComfyUI.bat.

  3. Run Windows_Custom_Nodes_Bundles_Installer.bat and install bundle 100.

  4. Download the core bundles shown above with our SwarmUI Model Downloader V186 or newer: Anima, MOSS-Image, FastH3 Omni or MiniMax-H3.

  5. Restart ComfyUI and refresh the browser tab.

SwarmUI Installer and Unified Massive Models Downloader: https://www.patreon.com/posts/114517862

Related posts

All posts in this topic: ComfyUI: 1-Click Installer, Presets and Tutorials · New to SECourses? Start Here: Best and Most Popular SECourses Posts

Files

1 MP vs 16 MP: See Every Whisker With MiniMax H3 Image in ComfyUI, Text to Image in 6 Steps

MiniMax H3 Image is a new 33.1B image model that generates and edits pictures at 16 megapixels, 4096 × 4096 or a matching wide or tall size, in only 6 sampling steps on your own NVIDIA GPU, with no upscaler. Our SECourses ComfyUI installer V150 ships two ready presets for it, Text To Image 16 MP and Image Edit Up To 16 Images, with every model and setting already chosen. MiniMax's official prompt enhancer runs locally inside them in three modes (reasoning, fast and off): it turns a short idea in any language into the detailed caption the model was trained on, picks the aspect ratio, and a box shows the exact prompt the model received. The SECourses Model Downloader V190 fetches every model file into the right folders from one bundle. In this mini tutorial a rusted, moss-covered Volkswagen Beetle is restored with one plain sentence, 9 typed words become a 16 MP photo of a fox, and you see a room furnished from 4 photos, letter-perfect posters and 1 MP vs 4 MP vs 16 MP. Links: Download the ComfyUI installer zip V150 with both MiniMax H3 Image presets (our ComfyUI post): [ https://www.patreon.com/posts/105023709 ] SECourses Model Downloader V190 with the MiniMax-H3 Core and Low VRAM bundles (our SwarmUI post): [ https://www.patreon.com/posts/114517862 ] Full ComfyUI installation tutorial: [ https://youtu.be/nxsCBTcCVp4 ] How to update ComfyUI (mini tutorial): [ https://www.youtube.com/watch?v=sdD3--WbHZk ] ComfyUI mini tutorials playlist: [ https://www.youtube.com/playlist?list=PLABQ076bsdXU ] SECourses Discord: [ https://discord.com/invite/software-engineering-courses-secourses-772774097734074388 ] You will learn how to open the MiniMax H3 Image text to image preset from the Presets folder with Ctrl+O, write a short idea in box 1 in any language, keep the recommended 16 MP output size, use the prompt enhancer in reasoning mode for the best captions or fast mode for quick tries, switch it off when you write a long caption yourself, read the exact prompt the model received, and inspect the result at full size. In the image edit preset you add your photo to the gallery as @image1, write the change as one plain sentence with no mask, say what must stay the same (the forest, the light, the camera angle), and name more reference images with @image2 and @image3. Finally you set up the route yourself: download the ComfyUI V150 zip from our Patreon post, extract it over your ComfyUI folder, run the update file, install bundle 100 with the bundles installer, then open the MiniMax-H3 Core Bundle in the Model Downloader (4 files for images, about 44 GB) or the Low VRAM Bundle, which brings a smaller version of the image model. Main topics include MiniMax H3 Image, ComfyUI presets, text to image, AI photo restoration, multi-image editing with @image tags, the local prompt enhancer, automatic aspect ratio, 6-step sampling, native 16 MP without an upscaler, RTX 5090 speed and lower VRAM use. Use the chapters to jump to the first image, the photo edit, the comparisons, the speed numbers or the downloads. Chapters: 0:00 A rusted wreck restored at 16 megapixels 1:21 Where the two new MiniMax presets live 1:37 Text to image: a 16 MP picture from words 2:22 The prompt enhancer: MiniMax's own, running locally 3:22 The exact prompt the model received 3:49 Fast enhancer mode: a 16 MP image in real time 4:37 Image edit: restore a photo with one sentence 5:34 The restored car and why it moved into a showroom 6:11 Many references, lettering, sizes, speed and lower VRAM 6:42 1 vs 4 vs 16 MP: 16 MP recommended 6:58 RTX 5090 speed, and with a 12 GB limit 7:27 Get the V150 zip and the model bundle 7:59 The MiniMax-H3 model bundle in the Model Downloader Measured numbers and their conditions: on an RTX 5090 with the models loaded, 6 steps, prompt encoding and decoding included and the prompt enhancer not included, 1 MP took 3.4 s, 4 MP 5.7 s and 16 MP 15.7 s. With ComfyUI limited to 12 GB of the same card's memory, a 16 MP image still finished in 19.5 s, the rest streaming from system RAM; a real 12 GB card computes slower. On camera, the fast enhancer mode made a second 16 MP fox in under half a minute from the click, and reasoning mode adds about a minute for the best captions. This video is for ComfyUI users and AI image makers with an NVIDIA GPU who want the newest local image model at its full 16 megapixel quality without collecting files, nodes and settings by hand: open a preset, write one sentence and click Run. If ComfyUI is new for you, start with the installation tutorial linked above; if it is already installed, the update tutorial shows the zip update step by step. For support, questions, feature requests or installation issues, see the pinned comment, our Patreon posts, our Discord and the video comments. Thank you for watching.

Comments

Kieran Hawk

It great for landscapes, but not for people or objects. It's SDXL-esque; you will get body horror like deformed fingers, hands, and faces very frequently.

Vik An

Спасибо. Буду тестировать!

SECourses

interesting did you try MiniMax_H3_Image_Enchance_Prompt_Feed_For_LLMs.txt ?

Kieran Hawk

No, I used the prompt enhancer in the workflow like you did in the video.

SECourses

ye that one is fast but weak. try that txt file on google ai studio with gemini and let me know

Kieran Hawk

Unfortunately didn't help. Are you getting good results with people?

Kieran Hawk

Here's the prompt I used (LLM enhanced) on your "MiniMax H3 Image - Text To Image 16 MP - 6 Steps - 261110.json" with the built in enhancer off: "A detailed cinematic photograph captures a young man jogging along a sunny tropical beach at mid-morning, his athletic figure moving with fluid dynamism as he runs parallel to the waterline where wet sand meets shallow turquoise surf. He is positioned in the left-center of the frame, facing rightward toward the distant horizon, his body caught in a dynamic forward stride with his right leg extended behind him and his left foot pushing off from the damp shoreline. The man wears a fitted white athletic tank top with thin straps that sit on his broad shoulders, paired with black compression running shorts ending above mid-thigh, and his feet are bare against the warm sand. His short dark brown hair is slightly dampened by light perspiration, swept back from his forehead by the ocean breeze, and small silver hoop earrings glint in the sunlight on his ears. The camera uses a telephoto lens with shallow depth of field to compress the vast beach behind him, keeping his face and upper body in sharp focus while softening the background into a painterly wash of blue sky, pale sand, and distant palm tree silhouettes lining the shore. Warm golden light bathes his skin from the front-left, creating subtle highlights along his cheekbones and shoulders, while the sun's position slightly behind him casts a soft rim glow along his hair and back. The turquoise ocean water reflects the bright sky with small wavelets catching the light, and clusters of smooth pale driftwood and scattered seashells dot the dry sand in the foreground right."

Kieran Hawk

No, that is not excellent. Zoom in on the hands and feet. Too bad; it was a promising model.

SECourses

try 32 mega pixels and see if improves.