生成AIでIPチャレンジ retweeted
Basketball replays with our World Reconstruction Model: free viewpoint and full control over the camera trajectory. Rendered in near real time. 8 cameras as input.
The community support has been incredible, and we’ve been blown away by the creativity and amazing apps being submitted.
We’re extending the submission deadline to November 3rd at 9 AM PT to give everyone a little more time to participate.
We value this community and love seeing what you’re building.
If we win, we all win. 🫡
Replying to @higgsfield_ai
@higgsfield_ai sent us a cease and desist last night, asking us to shut down our Open Source Higgsfield challenge.
Our read on why they sent it. When the apps people pay for can be rebuilt in the open in two weeks, that’s an uncomfortable thing for a closed platform to watch.
So here’s us reiterating our promise to every builder in the challenge and community, and we’re keeping it:
• The challenge stays open
• Final submissions close tomorrow, Oct 30
• Winners are announced Nov 6, with prizes paid as promised
You showed up for each other. We’re showing up for you.
If we win, we all win!
Comfy out 🫡
生成AIでIPチャレンジ retweeted
AI-generated doesn’t mean copyright-free.
Introducing IP Safety Check on OpenArt!
Scan images and videos created anywhere for potential copyright and IP matches.
Check up to 32 files at once and get individual reports.
Create anywhere. Check before you publish.
Try it now. Link is in the replies!
🤖 Made with AI
生成AIでIPチャレンジ retweeted
Pikaが動画AI「MiniMax H3」の高速版「Pika H3 Flex」をオープンで公開したので、Colab(G4)で45本くらい作って検証してみました。
5秒の動画が1本だいたい1分ちょっと。元のH3(約3分半)の約3倍速くて、1本あたり3円くらい。
高速版の宿命の破綻や画質の劣化も少なくかなりいい仕上がりな気がします。
R2Vがなかなかの精度なのもいい感じです。
ただ、セリフの日本語のイントネーションなどはたまにおかしくなるので、そこは要注意そうです。
ツール
検証した動画AI
・Pika H3 Flex(MiniMax H3 + Pika LoRA、ComfyUI 公式ワークフロー)
・実行:Google Colab
動画
・検証/集計/構成/台本/コード:Claude Code(Opus 5.5)
・映像:HyperFrames
・解説のさくら&ミナ:GPT-Image-2.5
・ナレーション:ElevenLabs v4
・字幕タイミング:Soniox STT v5
・BGM:Python(NumPy/SciPy)で自作合成
・ミックス:Python + FFmpeg
Meet Pika H3 Flex, debuting today as the #1 open weight model on DesignArena’s t2v board.
It’s built for professional iteration, with exportable audio stems, resolutions up to 4k, and faster-than-realtime generation. It can produce a 15-second clip with soundtrack in as little as 7 seconds.
So, yeah. It’s kind of a flex 💅
生成AIでIPチャレンジ retweeted
綺麗!早い!音も良い!
Pika H3 Flexをローカルで動かしてみました!
▼Pika H3 Flex生成時間:864×480 6Step
・5秒版(864×480):約73秒
・15秒版(864×480):約5分24秒
添付は高速なし版との比較ですが、画質は維持しており音質と音ハメはPika H3 Flex優位かと思いました!
動きは一瞬怪しいかもですが、生成時間短いのでガチャればOKかと。
これは素晴らしいですね~~!次世代!
#動画生成
Today we’re launching the first AI modeling agency 💅 right inside Glif.
Cast hundreds of real AI models, drop your product, idea or brief and let Glif create super compelling content for you end to end.
If you still think AI models aren’t ready for real work, watch this 👇
🤖 Made with AI
生成AIでIPチャレンジ retweeted
先日のOLさんダンスのデモ、裏ではこんなことしてました
Museで作ったダンス動画を3Dオフィスにビルボードで表示して、ノーマルで光の影響を受けるようにし、ディレクショナルライトの方角や高さも自由に変えられ、リムライトの設定逆光になるとキャラが暗くなったりレンズフレアも起こる。
時間によって背景も変わる
カメラは望遠と広角の設定もできる
この動画ではやってませんが、ポイントライトの設定(光の色変更)もできます
生成AIでIPチャレンジ retweeted
▼概要
動画生成モデルMiniMax-H3向けに、Pikaの動きと少数ステップ蒸留技術を統合した「Pika-H3-Flex-Turbo-LoRA」が公開。カスタムノード不要の単一LoRAファイルで、音声同期動画の高速生成を実現。
▼ポイント
・カスタムノードやモデルパッチを必要とせず、標準LoRAとしてComfyUIやDiffusersへ導入可能
・公式Pikaアダプター(6ステップ)に対し、4ステップ生成で高速化と高画質を両立
・2ステップ(試作)、4ステップ(高速)、8ステップ(最高画質)の各設定に対応
▼使い所
2ステップで構図や動きの試作・確認を素早く行い、4〜8ステップで本番映像を出力する制作フローに有用。
#MiniMaxH3 #ComfyUI
URLはリプ⬇️
生成AIでIPチャレンジ retweeted
Introducing XMAX X2.1, a real-time interactive video model by @XmaxAIOfficial, now on Reactor.
• Drag to move and pose subjects.
• Control multiple subjects at once with multi-touch.
• Swap characters, outfits and backgrounds.
Try it: reactor.inc/models/xmax-x2-1
生成AIでIPチャレンジ retweeted
Want to keep your characters consistent across scenes? Here is how to use Google Flow's character feature:
1️⃣ Click the Character button, prompt their look (or upload a reference photo), and give them a name.
2️⃣ Pick or customize a pre-built voice.
3️⃣ Type @ in the prompt box (or drag them in) to add them to your scene.
4️⃣ Select Omni 1.1 Flash and describe the action, like walking, jumping, or a dynamic camera sweep!
Pro Tip: Generate a full-body shot including clothing and surroundings! This provides helpful context for consistent generation across images and videos.
Head over to Google Flow and try the characters feature today!
生成AIでIPチャレンジ retweeted
背景ガチャに住宅14種類を追加しました!!
日本式8種、アメリカ式6種。
それっぽいマイホームを建てて遊べます。
また、Vroidを使って背景の中を歩く機能も実装。
よかったら、遊んでみてください!!
tools.oyasumi-gamedev.com/ha…
生成AIでIPチャレンジ retweeted
Try Pika H3 Flex for yourself on the Pika API Club. Prices start at $0.01/sec, and we’re giving away 15 generations per day, for the next two weeks.
pika.art/pika-h3-flex?utm_so…
生成AIでIPチャレンジ retweeted
Everything we put into this model was designed to give creators the flexibility and speed to explore with precision.
In that spirit, we’re making Pika H3 Flex open source from day 1. You can find the code on GitHub, the weights on @huggingface, and start playing with it in @ComfyUI and diffusers right now.
Code: github.com/Pika-Labs/Pika-H3…
Weights: huggingface.co/Pika-Labs/Pik…
Diffusers:
huggingface.co/docs/diffuser…
ComfyUI: docs.comfy.org/tutorials/vid…
生成AIでIPチャレンジ retweeted
Meet Pika H3 Flex, debuting today as the #1 open weight model on DesignArena’s t2v board.
It’s built for professional iteration, with exportable audio stems, resolutions up to 4k, and faster-than-realtime generation. It can produce a 15-second clip with soundtrack in as little as 7 seconds.
So, yeah. It’s kind of a flex 💅
生成AIでIPチャレンジ retweeted
MiniMax-H3用の6step LoRA「Pika H3 Flex」をComfyUIで検証
Base 25stepと比較しても画質はほとんど変わらない印象。低ステップ特有の映像の薄さも感じられず、かなり良い結果
RTX 5090 / 10秒
左:Base 25step(768×1376)20分34秒
右:Pika 6step 約4分55秒
約4.18倍高速化
#MiniMaxH3 #ComfyUI
🤖 Made with AI
Meet Pika H3 Flex, debuting today as the #1 open weight model on DesignArena’s t2v board.
It’s built for professional iteration, with exportable audio stems, resolutions up to 4k, and faster-than-realtime generation. It can produce a 15-second clip with soundtrack in as little as 7 seconds.
So, yeah. It’s kind of a flex 💅
Replying to @higgsfield_ai
@higgsfield_ai sent us a cease and desist last night, asking us to shut down our Open Source Higgsfield challenge.
Our read on why they sent it. When the apps people pay for can be rebuilt in the open in two weeks, that’s an uncomfortable thing for a closed platform to watch.
So here’s us reiterating our promise to every builder in the challenge and community, and we’re keeping it:
• The challenge stays open
• Final submissions close tomorrow, Oct 30
• Winners are announced Nov 6, with prizes paid as promised
You showed up for each other. We’re showing up for you.
If we win, we all win!
Comfy out 🫡
Last night, @higgsfield sent @ComfyUI a cease and desist (attached)
They want the Open Source Higgsfield challenge taken down within 48 hours.
Their argument is that our use of the Higgsfield name and that using their CEO's likeness is an infringement violation (man, the irony). Claiming that it makes the event look like Higgsfield is associated with it.
This couldn't be farther from the truth, which is that Higgsfield made a promise to open source its product and never did.
For the past two weeks, builders have been recreating popular closed apps as open workflows anyone can run.
So we asked our community to deliver where Higgsfield failed: apps in the open, built by the community, for the community. We've made it clear that the challenge is organized by ComfyUI and not affiliated with or endorsed by Higgsfield.
When we started Comfy, we made the community a promise. Our product stays open, free, and yours. We’ve kept it every day since, and one letter isn’t going to change that.
The challenge stays up. Comfy and open source will win!
生成AIでIPチャレンジ retweeted
【どこでもロケハン・大型アップデート!】
公開から約2週間で、ここまで進化しました!!
・検索できる地名 約179万→約1,350万か所
・夜景・霧・グラデーション機能を追加し、表現力を向上
・米、仏、中、韓、台の5カ国にユニークな建物を追加し、建物を100種以上追加
・日本も町家・蔵・茅葺き・お寺・お城などの作り分けを追加
・最適化を行いスマホでもサクサク動きます
皆様のご支援のおかげでここまで来れました。
引き続き開発頑張ってまいります。
地図情報から漫画背景を作成できるツールを作成しました。地名や座標を入力すれば地球のどこでも再現可能です。無料で使えるので、ぜひ使ってみてください!
tools.oyasumi-gamedev.com/ro…
生成AIでIPチャレンジ retweeted
We're starting Higgsfield Selected, our pick of the best work made on Higgsfield.
The first one is MADSEASON by our creator @dinitrobenzoll
The entire project is open source. All prompts and assets are public.
生成AIでIPチャレンジ retweeted
プロットに合わせて漫画のネームを作れるツールを公開しました。
ガチャで色々試したり、ポーズやカメラ、演出を指定できます!無料なので、ぜひ使ってみてください! tools.oyasumi-gamedev.com/co…
漫画キャラクターのポーズを簡単に付けられるポーズガチャを実装しました。ネームのコマを選択し、ポーズを簡単に変更できます!使ってみてください!
tools.oyasumi-gamedev.com/na…
生成AIでIPチャレンジ retweeted
地図情報から漫画背景を作成できるツールを作成しました。地名や座標を入力すれば地球のどこでも再現可能です。無料で使えるので、ぜひ使ってみてください!
tools.oyasumi-gamedev.com/ro…
プロットに合わせて漫画のネームを作れるツールを公開しました。
ガチャで色々試したり、ポーズやカメラ、演出を指定できます!無料なので、ぜひ使ってみてください! tools.oyasumi-gamedev.com/co…






















