生成AIでIPチャレンジ (@GenAI_Creative) header
生成AIでIPチャレンジ (@GenAI_Creative) profile picture

生成AIの気になるニュース、ツイートをクリップしています。 ソニー株式会社で、生成AIによる広告制作、マイクロドラマ、ゲーム、生成画像/生成動画/空間生成サービスを開発・事業化しています。(ここでの発言、発信は、個人活動です) Sony MVP 2004, Sony MVP2009

Shibuya, Japan
Joined April 2023
Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)Photo by 生成AIでIPチャレンジ (@GenAI_Creative)
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…
28
672
56
3,563
134,062
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.
61
247
8
516
34,364
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…
26
1,911
192
9,044
2,734,161
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…
416
19,620
2,106
82,367
5,386,217
生成AIでIPチャレンジ retweeted
30초 AI 숏드라마 한 편 무료로 만드는 방법 1. OnSolo AI 로그인 2. 110 크레딧 받고 무료로 AI 영상 만들기 보통 가입할 때 주는 크레딧으로는 10초 정도 밖에 못 만드는데 여기는 얼마 전 테스트해 본 Wan 3.0으로 30초 영상 한 편 만들고도 크레딧이 남음 AI 영상이나 숏드라마 제작에 관심 있었던 분들은 먼저 무료로 가볍게 만들어 보세요!
24
78
3
296
14,132
生成AIでIPチャレンジ retweeted
AIへの指示用に、"カメラワークと演出の名前" 第2弾をまとめました! ClaudeやCodexで動画を作るとき、「映画っぽくカッコよくして」だけでは、狙った演出はまず出せない。 「フライスルー」「アイリスアウト」「モンタージュ」と名前で頼めば、思い通りの演出を再現できます。 保存推奨です🔖
15
232
22
2,597
130,270
生成AIでIPチャレンジ retweeted
New in Claude for Legal: a gallery of ready-made artifacts for contract review, regulatory horizon scans, cite checks, and more. Start from the built-in example, add your own documents and connectors, and share it with anyone across the business.
713
1,592
1,072
25,155
4,938,157
生成AIでIPチャレンジ retweeted
▼話題 商用AI生成プラットフォーム「Higgsfield」の機能を、オープンモデルのみを用いてComfyUI上で117種類のアプリとして完全再現したプロジェクト「Freefield」の公開。 ▼主な反応 ・単一機能の複製コンテストでプラットフォーム全体を再現した開発規模への驚嘆 ・全アプリへの実行テストと修正システムによる品質管理の徹底に対する高い評価 ・MITライセンス公開を歓迎し、自身の制作プロジェクトや環境へ導入・活用したいとする声 ▼受け止め 過剰達成とも言える圧倒的な開発量に対し批判や懸念はなく、コミュニティ全体から驚嘆と絶賛で受け止められている。 #Higgsfield #ComfyUI URLはリプ⬇️
1
13
2
118
6,394
すげー、1,400枚もポーズある! ちなみにデータの形式違うけどうちにも800ポーズあります!(便乗宣伝)(クリスタやBlenderで使えます) pose-loom.pages.dev/ たぶんCodexに作ってもらったからページのレイアウトが似てるw
AI美女「ポージング」データベース無料公開! 「このポーズに変えて」だけで使えるように 1,439枚のポーズ集をデータベース化しました ・無料 ・商用利用OK ・編集、二次利用OK 引用元の記事からお受け取り下さい
1
34
1
396
26,603
生成AIでIPチャレンジ retweeted
Excited to share Genie 4 today our most realistic and interactive world model: - steer dynamic environments in real time, shaping events, camera angles, and actions - generate native audio matched to the world, from realistic background sounds to characters who can converse in real time! - simulate photorealistic scenes and real-world physics - create more coherent multi-step events through reasoning from Gemini We've started to roll out as a research preview to trusted testers. Coming soon to Google AI Ultra subscribers in Project Genie and early access partners via the Gemini API and AI Studio.
865
1,460
603
19,185
1,791,206
【Opus 5.5とMiniMax H3によるTikTok向け音楽ビデオ量産ワークフロー】 👉 teapaw.org/servasyy_ai/stat… TikTok向けの中毒性の高い音楽ビデオ(MV)を1人で数十分程度で効率よく量産する手法が注目を集めています! 面倒なパラメータ調整やSeedance 2.5のような従来ツールを避け、「Opus 5.5 + MiniMax H3」のスタックを利用するのが特徴ですね。 具体的な手順としては、他人の動画を参照用に見せつつ、H3公式プロンプトのルールに従ってOpus 5.5で指示を出すパイプラインとなっています。 ローカル環境でMiniMax H3を自前構築する場合は電気代のみで無検閲の運用ができる一方、8GB VRAMのノートPC環境では実行が困難というハードルがあります! また、AIエージェントのベンチマーク「Terminal-Bench 4.0」では、Claude Codeを伴うOpus 5.5 (max)が64.8%で1位を記録しており、こうした上位モデルの圧倒的な性能優位性が開発現場で広く使われている背景にありますね。 #AI動画生成 #MiniMaxH3
4
51
3,752
【スマホ単体でMiniMax H3 (33B)のローカル動画生成を実現する「Gestura」】 モバイルデバイスのオンデバイス処理だけで音声付きの5秒間動画生成を約7分で完了させる、驚きの技術的実験が報告されました! クラウドや外部GPUを一切使わず、スマートフォン内部の演算処理のみで動くのが最大の特徴ですね。 33Bパラメータ級の巨大モデルを動かすために、NVFP4やQ3といった低ビット量子化や4ステップの蒸留手法が取り入れられています。 解像度は256x256に制限され高熱の発生も指摘されていますが、エッジAIの限界を押し広げる面白いアプローチですね! #エッジAI #動画生成
1
1
7
1,362
生成AIでIPチャレンジ retweeted
🌍 Introducing Echo-3, a new world model enabling the most accurate reconstructions of real spaces to date! From a quick phone video of my daughter’s room, Echo-3 built a 3DGS model and restyled the whole house with her favorite fairy tales 🚀✨. Get the app and try it out!
Introducing Echo-3. A state-of-the-art world model. Echo-3 turns phone captures into photorealistic, metric-scale 3D worlds. From a single room to multi-floor buildings, outdoor and public spaces. Available today.
50
231
24
2,505
149,034
生成AIでIPチャレンジ retweeted
With Google SynthID detection in Gemini, anyone can easily check if an image, video, or audio file was made with AI from Google. Just ask Gemini, “Is this AI generated?," so you can navigate the web with more confidence.
115
141
62
1,510
118,968
生成AIでIPチャレンジ retweeted
This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.
950
2,585
1,964
23,403
3,289,865
生成AIでIPチャレンジ retweeted
Had early access to Genie 4 from @GoogleDeepMind. This is a fully generated, interactive world from a single starting prompt (environment + character) 🤯 Feels like a massive step forward - you can now prompt to change the world and interact with it. With native audio!
151
185
72
2,353
197,363
1枚の絵からヌルヌル動くアバターが作れる『Mesh Avatar Studio』、イラストを渡してコマンドを1つ打てば、アバターの完成までCodexが進めてくれるようになりました! npm run create -- イラスト.png 閉じ目や口の形、驚きや悲しみの表情まで描き分けて、最後にエディタが開きます イラストの口が開いていたら、先に口を閉じた絵に直してくれるなど、地味に面倒な作業をAI側で対応してくれます😊 時間は数十分ほどかかるので、その間は待って、エディターが立ち上がったら調整していってください! github.com/shinshin86/mesh-a…
5
38
2
414
21,575
生成AIでIPチャレンジ retweeted
Introducing Genie 4 from @GoogleDeepMind, our most realistic and interactive world model yet 🌍 Now you can use natural language to dynamically steer the world and its soundscape in real-time, whether you're changing the weather, moving the camera, or introducing new elements to the environment. So, how does the model do that? Behind the scenes, Gemini acts as the "brain" of the simulation. It translates your requests into actions, plans out complex events, watches the scene unfold to keep track of what's happening, and adjusts as you change the story. Genie 4 also introduces ambient audio and real-time interactive human dialogue that adapts on the fly.
109
238
95
2,187
174,516
生成AIでIPチャレンジ retweeted
Forget diamonds. Liquid metal is stealing the spotlight. Shiny metallics are turning the human silhouette into a moving piece of contemporary sculpture. ➜ Image Prompt: Photography & Cinematography Create a hyper-realistic, head-to-toe high-fashion editorial portrait of a stunningly beautiful adult blonde woman with refined, model-like features, sculpted cheekbones, expressive blue eyes, full natural lips, and a confident, alluring expression. Her platinum-blonde hair is sleek, straight, and center-parted, with long face-framing strands and the remaining hair tucked neatly behind her shoulders. Spectacular fashion photography, captured on a full-frame camera with a 50mm portrait lens, sophisticated studio lighting, crisp metallic reflections, exceptional fabric detail, and striking editorial composition. Preserve authentic skin pores, natural complexion variations, realistic anatomy, and subtle skin imperfections. No fake skin, plastic skin, excessive smoothing, CGI, or animated appearance. Environment Place her inside a minimalist high-fashion photography studio with a seamless cool slate-gray backdrop and subtle blue undertones. The background transitions naturally through soft gradients, creating depth without distracting from the subject. Controlled directional lighting produces luminous silver reflections across her metallic outfit, while a soft frontal fill preserves realistic facial detail. Subtle cyan-blue edge lighting enhances the futuristic fashion aesthetic. The floor is smooth, matte gray with natural contact shadows beneath her shoes. The overall atmosphere resembles a luxury European fashion campaign with a bold, futuristic Y2K aesthetic. Pose Full-body portrait, completely visible from head to toe, including both platform heels. She stands facing the camera with her hips subtly angled, her weight resting on one leg and the opposite leg extended slightly forward. Her shoulders remain relaxed, with a gentle asymmetry through her torso. One forearm crosses naturally in front of her waist, with her hand resting lightly near her opposite hip, while her other arm hangs loosely beside her body. Her chin is slightly lowered, her head tilted subtly, and her eyes look directly into the camera with a composed, confident expression. Maintain elegant feminine proportions, natural posture, anatomically accurate hands, and realistic body structure. Outfit Preserve the reference's striking futuristic silver metallic ensemble. She wears a fitted, strapless chrome-silver bandeau crop top with a straight neckline, structured seams, and a highly reflective liquid-metal finish. Pair it with a matching ultra-short, low-rise metallic silver mini skirt featuring a smooth, body-skimming silhouette and subtle natural fabric creasing. Her midriff remains exposed. Add matching detached, elbow-length metallic silver arm sleeves with fitted construction, subtle gathering at the wrists, and a glossy chrome finish. Complete the outfit with sheer smoky-gray thigh-high stockings featuring broad, contrasting pale-gray bands around the upper thighs. Her footwear consists of dramatic silver platform high heels with transparent straps, substantial mirrored block platforms, and tall heels. Keep accessories minimal to emphasize the futuristic styling. The overall aesthetic combines early-2000s futuristic fashion, contemporary luxury editorial photography, and metallic runway styling. Ultra-high-resolution photographic detail, physically accurate metallic reflections, realistic skin texture, natural garment folds, authentic sheer stocking material, accurate hands and feet, anatomically correct proportions, no warped limbs, no artificial skin, no cartoon styling, no exaggerated CGI effects, and no image quality degradation.
The best thing about Buenos Aires is that it refuses to look manufactured. The Palermo Soho neighborhood can turn one ordinary block into five completely different moods before you reach the corner. In Palermo Soho, even a walk to nowhere feels like the beginning of something. ➜ Image Prompt: Photography & Cinematography Create a hyper-realistic, head-to-toe contemporary streetwear fashion portrait of a stunningly beautiful adult woman with refined, model-like features, sculpted cheekbones, expressive almond-shaped eyes, full natural lips, and a confident, effortlessly cool expression. Her long, tousled auburn-brown hair falls loosely past her shoulders, with natural waves and individual strands catching the sunlight. Spectacular cinematic street photography, captured on a full-frame camera with a 35mm lens, exceptional architectural detail, rich natural colors, realistic skin texture, and crisp editorial composition. Preserve authentic skin pores, natural complexion variations, and realistic facial proportions. No fake skin, plastic skin, excessive smoothing, CGI, or animated appearance. Environment Place her on a lively street corner in Palermo Soho, Buenos Aires, Argentina, on a bright, sunny afternoon. Surround her with colorful independent cafés, bookstores, vintage clothing shops, and art galleries featuring authentic Argentine architecture, painted storefronts, striped awnings, and vibrant street art. A black-and-yellow Buenos Aires taxi passes nearby, while pedestrians socialize outside cafés and walk along the sidewalks. Purple jacaranda blossoms frame the upper portion of the scene. Include a clearly legible street sign reading "Honduras" and storefront signs reading "LIBROS," "CAFÉ," and "GALERÍA PALERMO SOHO." All visible signage, storefront lettering, posters, and background text must be correctly spelled, legible, and meaningful, with no gibberish text. Warm afternoon sunlight creates strong but natural shadows, highlighting the textures of the buildings, pavement, and clothing. The atmosphere feels authentic, energetic, artistic, and distinctly Buenos Aires. Pose Full-body portrait, completely visible from head to toe, including both shoes. She stands casually beside a sticker-covered street pole, with her body angled slightly in a relaxed three-quarter stance. Her weight rests naturally on one leg, while the other extends slightly forward. Her shoulders remain relaxed, her arms hang loosely at her sides, and her hands are naturally positioned with anatomically correct fingers. Her head turns slightly toward the camera, maintaining confident, understated eye contact. Her expression is composed, independent, and effortlessly fashionable. Maintain realistic feminine anatomy, natural body proportions, and an authentic street-style editorial pose. Outfit Preserve the reference's relaxed, contemporary Y2K-inspired streetwear styling. She wears a cropped, slightly oversized faded charcoal-blue denim jacket with a structured collar, dropped shoulders, long sleeves, metal buttons, and subtle woven texture. Beneath the jacket is a fitted dark chocolate-brown asymmetrical top with delicate ruching and an exposed midriff. Her oversized, low-rise, wide-leg blue jeans feature a faded vintage wash, exaggerated loose silhouette, subtle tonal patterns, and naturally frayed hems. A brown leather belt with a silver rectangular buckle sits loosely around her hips. Complete the outfit with chunky black leather sneakers featuring rounded toes and substantial soles. A brown patterned shoulder bag hangs naturally from one shoulder, complemented by a delicate gold chain necklace and understated rings. The overall aesthetic combines contemporary Buenos Aires street fashion, relaxed Y2K influences, and high-end editorial photography. Ultra-high-resolution photographic detail, authentic denim textures, natural garment folds, realistic skin imperfections, accurate hands and feet, physically correct anatomy, no artificial skin, no distorted proportions, and no image quality degradation.
10
2
19
2,018
生成AIでIPチャレンジ retweeted
イラストから3Dイラストアニメーション作成の進捗 イラストからLoRAで360度動画を生成→ 基準角度ごとにSee-throughでイラスト分解→ さらに髪の毛を房ごとに画像生成で分解→ パーツをメッシュ化してIDを付与。3D空間で一意にする→ パーツに分解したイラストを対応づけ→ 動かす 本当、See-throughニキが神すぎる
27
347
25
3,394
169,283