Joined June 2026
MiniMax-H3 🙂X2-Detail-VAE in ComfyUI contains a 2-in-1 MiniMax H3 X2 VAE, an optional ComfyUI detail-enhancement node -Mode 1 — 2X VAE Decode -Mode 2 — Reference Detail Enhancement custom node+model+workflow:👇 huggingface.co/speach1sdef17…
2
16
1
193
20,063
Ps V retweeted
To think that anyone can generate videos like these is incredible! Prompt ⤵️
🤖 Made with AI
As incredible as it gets! Imagine how much it would cost to make this video without AI. Here is the prompt to generate this ⤵️
11
17
1
178
11,905
Ps V retweeted
MiniMax H3's video VAE is now ~2x faster in ComfyUI on @nvidia GPUs Encode: up to ~2.2x faster Decode: ~1.4–2.7x faster 1344x768, 129-frame round trip: 24.3s → 12.7s Full breakdown from @Kijaidesign ⬇️
37
79
5
898
117,774
ControlNetっぽく使えるものと、Upscaleのworkflowを追加しました
たまには即日でお届け! Qwen-Image-2.1 の ComfyUI workflow です t2iから画像編集、切り抜き、パノラマまでご用意しておりますm(_ _)m 普通の生成は正直怪しいなという感じですが、ほぼピクセルパーフェクトで編集できるのは嬉しい。とても嬉しい comfyui.nomadoor.net/ja/basi…
7
132
12,262
Qwen-Image-2.1 は上手に切り抜きが出来るので、切り抜いたオブジェクトを画像から消して、次に手前にあるものをまた切り抜いて… というのを繰り返せばレイヤー分けが出来るね(-ω☆) というのでやってみました workflow : comfyui.nomadoor.net/ja/basi… ループ処理で出来ることが増えたけど難しすぎる!
1
10
1
78
8,566
Ps V retweeted
MiniMax H3 Character Detail Montage This prompt turns your character reference into a fast-paced detail montage: clean background, dynamic movement, sharp cuts, and explosive camera moves. The face stays hidden until the final shot. MiniMax H3 prompt in the replies.
79
239
53
3,281
513,656
Custom nodes for YuE2 in ComfyUI. This allows you to train loras and also micro edit the notes of a song. github.com/filliptm/ComfyUI-…
7
22
2
245
8,345
さらにこれにこれを入れたらこれになりました MiniMax H3
🤖 Made with AI
OiiOiiのMinimax H3 Max Turboでスタートとエンドにこれ入れたらできました
5
16
1
154
8,547
Han añadido Marigold V2 en ComfyUI y evidentemente la primera tarea era testear a ver qué tal se comportan los mapas con mi NKD Relight. Sigue necesitando una segunda pasada de refinement para recuperar textura, pero nada mal para un primer pase, la verdad.
13
37
3
410
29,623
Minimax H3 😃 All workflow types listed at one place -Basic/apis -FastH3 -VFX control -VSA/VDA -upscaler etc.... Source HF repo:👇 huggingface.co/datasets/stab…
3
13
250
14,800
Ps V retweeted
Less than a minute to generate this shot with MiniMax H3 Max via Partner Nodes. It works quite well for fast video-to-video experiments, especially when starting with a basic blockout + reference images. The workflow also includes an option to upscale to 2K. To try this workflow, link below 👇
24
85
5
811
44,954
Topaz alternative 🤏 SeedVR2+TensorRT faster VAE Processing. VRGDG SeedVR2 TensorRT Studio turns the SeedVR2 pipeline into a practical Windows workflow: load a video, test preview, compare the result frame by frame, and complete long renders 👇 github.com/vrgamegirl19/VRGD…
2
11
148
9,945
Ps V retweeted
MiniMax H3 - Text to Video, Burger Ad You can easily adapt this prompt for any food. Prompt: Create a high-end cinematic burger commercial in portrait format, designed like a premium restaurant campaign. Open on an extreme macro shot of a golden toasted bun, revealing tiny bake-specks, soft flour dusting and rich surface texture under warm directional light. The camera glides smoothly across the bun, then pulls back as the burger ingredients separate into a perfectly aligned exploded stack above a matte wooden tabletop. The full burger floats on a single vertical axis: toasted top bun, crisp ruffled lettuce, glossy tomato slices, translucent purple-red onion rings, melted cheddar, a thick char-grilled beef patty and toasted bottom bun. Each layer moves with elegant controlled motion, subtle rotation and realistic weight. Use premium food-commercial camera movement throughout: macro tracking shots, smooth dolly pushes, slow orbital moves, shallow-focus passes between ingredients and precise rack focuses. Add occasional speed ramps into slow-motion beauty moments. Let tiny crumbs, droplets and subtle steam move through the light for additional depth. Integrate bold hand-lettered white typography directly into the composition. Words appear between the floating burger layers, following the camera movement with kinetic typography. Letters can slide behind ingredients, reveal through depth, stretch slightly during transitions and lock cleanly into place. Add minimal white doodle strokes and graphic accent lines that animate around key ingredients. Lighting is luxurious and appetizing: soft directional key from upper-left, controlled fill, warm highlights, deep dimensional shadows and glossy specular detail on tomato, cheese and meat. Background is a refined warm brown gradient with subtle cinematic falloff. Build toward a final satisfying moment where all ingredients rapidly assemble into one perfect burger. The camera performs a fast controlled push-in, then settles into a polished hero shot. Steam rises gently from the patty, cheese settles over the edges and the typography resolves beside the burger. Final frame: centered premium burger hero shot, clean composition, elegant white campaign typography and subtle animated graphic accents. Visual style: luxury food advertising, modern restaurant campaign, cinematic macro photography, rich warm tones, high contrast, shallow depth of field, highly detailed food textures, sophisticated motion design, premium typography, smooth dynamic camera choreography, polished commercial finish.
21
49
4
419
28,281
Ps V retweeted
How to Train a MiniMax H3 Ref2VA LoRA with AI Toolkit In this tutorial, I train a vid2vid LoRA on @MiniMax_AI MiniMax H3 that makes everyone super jacked 💪 Links and more in 🧵
19
31
3
359
17,607
出たばかりのLTX-2.5をローカルで動かしてみました。同じ1枚の絵から「横を向いて『なーに言ってんだか』と言う」という同じ指示で、ローカルMiniMax H3とクラウドSeedance 2.5と並べてみました(2026年8月時点)。 480×640・約5秒で揃えました。生成時間は LTX-2.5が45秒、H3が63秒。ですがモデルのロードやキャッシュの効き方で前後するので、厳密に比べた数字ではないです。 Seedance 2.5はキュー込みで2〜3分でした。LTX-2.5は蒸留版の8ステップ、H3は20ステップです。 LTX-2.5もいいですね。アニメ絵はもう少し苦戦するかと思っていたけれども。 いずれにしてもローカル動画生成界隈が盛り上がるのはいいことです。
🤖 Made with AI
6
85
4
708
61,686
MiniMax H3 🤓Fast Gen Tip Add these nodes for faster gen time: EasyCache + Patch-Sol-Attn + Patch Sage Attention KJ From Kijai: Patch Sol Attention github.com/kijai/ComfyUI-Sol… Patch Sage Attention KJ: github.com/kijai/ComfyUI-KJN…
Will Smith x Spaghetti remix 🤪 MiniMax-H3 on RTX 3060 6GB & 64GB RAM (A 5s 480p T2V clip took around 4–5 mins using EasyCache + SageAttention)
4
33
4
447
50,341
▼話題 画像生成ツール「KREA 2 Turbo」の多様なスタイルとプロンプトを探索できるギャラリーサイトが公開され、注目を集めている。 ▼主な反応 ・画像のプロンプトをコピーして自身のワークフローに流用できる機能が実用的であるとの評価 ・ギャラリーをブックマークし活用する動き ・自身でスタイルを追加できるかという質問と、今後の拡張計画への関心 ・サイトのデザインの良さに対する称賛 ▼受け止め 実用性の高いギャラリーとして歓迎されており、コミュニティ全体で非常に好意的に受け止められている。 #KREA2Turbo #画像生成 URLはリプ⬇️
1
15
1
230
19,829
▼話題 画像から動画を生成するAIツール「Bernini」による出力結果や忠実度が、既存モデルより極めて優れているとして注目を集めている。 ▼主な反応 ・他の手法と比べて品質や再現性が非常に高いとする称賛 ・音声対話の再現ができない制限に対する指摘 ・プロンプトの生成方法や具体的な記述内容の共有を求める要望 ・ツールの動作仕様に対する疑問や詳細なワークフローの開示を求める声 ▼受け止め 機能制限やワークフローに関する疑問はあるものの、生成動画の質の高さから全体的に好意的な評価が優勢。 #Bernini #StableDiffusion URLはリプ⬇️
2
5
2
43
5,176
I just released 3DREAL Strong V2 with @fal : our LoRA for LTX 2.3 that turns a blocky 3D render into photoreal footage, keeping the exact camera, layout and timing. Fable + Blender + fal ltx 2.3 render-to-real Weights opensource: huggingface.co/fal/LTX-2.3-3… Live endpoint : fal.ai/models/fal-ai/ltx-2.3… Full tutorial, all three prompts included: blog.fal.ai/from-clay-3d-ren…
12
70
5
446
32,815