LAT𐌄NT ƝOTHING ✦

✨𝕏 Creator✨Weaving visual stories with traditional and AI tools.✨ Creator partner @lumalabsai ✨ @nimvideo ✨ 🎨🖌️🌿✨🎧

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

Our bodies are living stories, shaped by emotions, experiences, and the weight of our journeys.

Through my art, I reshape the human form to reflect these untold tales. 🖤 Every posture, stretch, or curve is a narrative of resilience, pain, and hope. ✨

Tell me what does your body say about your story? 🤔

#ArtThatSpeaks #HumanStory #EmotionsInArt

[World Labs @theworldlabs]

Atlas is our scalable foundation model that can perceive, generate, reason, and interact with virtual and physical worlds.

We're opening up early access in the coming weeks.

Learn more and sign up here:
https://t.co/SHjFaNWedP

[AI Search @aisearchio]

This is crazy. This Minimax H3 finetune can generate videos in realtime (15s in 13s), up to 14x speedup

Fully open source with training code coming soon

https://t.co/YKFVJYyZwH

[Antoine Guédon @antoine_guedon]

We've just released code+model for Surflo!🚀
Turn any number of photos into a 3D surface with Flow Matching.

Our latent representation encodes the full scene and can be queried for downstream applications like 3D segmentation.

🔗https://t.co/lBcJRgpfdg
💻https://t.co/XpHQtmZHXJ

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

@mickmumpitz @SlipperyGem Noice!

[Nekodificador 💬 @Nekodificador]

Nuevo juguetito en mi set de herramientas para ComfyUI. Esta tecnología dio bastante de qúe hablar hará un año y medio, pero se quedó algo obsoleta al no actualizarse a las nuevas resoluciones. Sin embargo, siempre la he usado para obtener una base controlada de expresión para cualquier rostro. Después, con modelos más modernos como Klein puedo recuperar el detalle y hacerla viable.

Era un coñazo de utilizar, pero ahora funciona directamente en tiempo real y con los controles que tendríamos con un rig facial.

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

@ingi_erlingsson Super!

[Purz.ai @PurzBeats]

imagine..

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

@PurzBeats Siiiick 🔥🔥🔥

[CiaraRowles @CiaraRowles1]

We're excited to be releasing the model weights for our paper Stable Layers!

It's an RL finetune of Qwen-image-layered for drastically improved image decomposition and editability.

Model files: https://t.co/ip96Wz3tVX

Project Page: https://t.co/WnEV76afQp

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

@Machinedelusion @MiniMax_AI When will you reveal it for us? Can't wait 😜

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

@Machinedelusion @EMostaque @MiniMax_AI Doooppeee

[Pruna AI @PrunaAI]

Today, we open-source PrunaVAED, a faster drop-in replacement decoder for video generation with LTX-2.3!

- 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? ~1.7-2.1x faster decoder & ~50% lower peak VRAM
- 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? Near-original visual quality & no changes to the latent encoding
- 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸? We pruned, trained & distilled video decoders to maximize efficiency of the LTX-2.3 series from @Lightricks

Want to try the fast open-source integration? Check it here on Diffusers: https://t.co/gJLged4ezV
Want to try the fastest video generation endpoint? Check p-video here on API: https://t.co/fbzM9gs7s8

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

@fableshowrunner @Gossip_Goblin @Variety @IndieWire @Forbes @DEADLINE God

[R@aiaicreate @aiaicreate]

ローカル環境で動作するAIモデル群をまとめた「Local AI Toolkit」が公開。
RTX 3060等の一般向けGPU向けに最適化されたモデルを収録。LLMや音声認識、RAG等に対応し個人PCでのAI活用を支援。画像生成等は準備中。

#LocalAIToolkit #ローカルAI

URLはリプ⬇️

[Lovis Odin @OdinLovis]

I made the workflow for comfyui to use Ltx 2.3 render to real Ic-lora !

If you want to go fast you can just use our endpoint :
https://t.co/CL1jObaymK

workflow available here :
https://t.co/OjnAg7hLgQ

[Lovis Odin @OdinLovis]

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: https://t.co/JjMWZzYYX8
Live endpoint : https://t.co/nICV5HJXXd
Full tutorial, all three prompts included: https://t.co/F41QVVY6sk

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

@PJaccetturo @bennash The AI not the winner here, the one who think, write & direct. See who did the best AI video? A director, who generate the best AI image? A photographer & who write the best AI script? A writer.

[Ingi Erlingsson 🪄 @ingi_erlingsson]

nature vs nurture 🌺

made in @ComfyUI with @krea_ai 2 + @Alibaba_Wan 2.2 I2V/T2V/Vace + @thesystms HUD + @suno 🎹

[ハカセ アイ(Ai-Hakase)🐾生成AI・ComfyUI @ai_hakase_]

【Images-to-3D-Head APIで写真からMetaHuman準拠の3D顔モデルを自動生成！】
👉 https://t.co/m8f4iKS5Q7
通常の2D写真から、なんと商用クオリティの3D頭部モデルを自動生成できる驚きのAPI技術が登場しました！

最大の強みは、業界標準である「MetaHuman」のトポロジー（3Dモデルを構成する網目状の設計図）にしっかり準拠している点です。これにより、生成後すぐにUnreal Engine 5などのゲームエンジンや3Dツールに取り込んで、高度な表情アニメーションを動かすことができますよ！

特殊なセンサーによるスキャンや、手動でのデータ修正（クリーンアップ作業）は一切不要。AIが写真から見えない部分（後頭部など）を賢く推論し、360度全方位のきれいなテクスチャを自動で作ってくれます。

API形式なので、システムに組み込めば大量のユーザーの顔データを一括で3D化するような仕組みも構築可能です。

ゲーム内へのプレイヤー自身の顔の移植や、映画・VFXでのデジタルダブル（デジタル上の身代わり）作成、さらには医療用のシミュレーションまで、制作コストを劇的に削減できる実用的な神アップデートですね！

#MetaHuman #3Dモデル

[LAT𐌄NT ƝOTHING ✦ @iSaif_ai]

@ostrisai @ComfyUI 🎉