Un Fastidio

A lot of "AI assisted artists" seem to think they can wish this away. They'll insist no one cares about AI use despite the polling, public scandals, etc. (But then they tend to refuse to label their AI art as such because they know it will turn off customers...)

🚨 Professional 3D artists are going to hate this. Tencent open sourced an AI that turns a single photo into a production-ready 3D model with full PBR textures. The kind that ships in AAA games. The kind that renders in Unreal Engine without post-processing. The kind that takes a senior 3D artist 3 to 5 days to build by hand. It's called Hunyuan3D 2.1. The first fully open source production-ready 3D generation model. Full weights. Full training code. Free. Upload one photo of anything. Get a complete 3D model with Albedo, Normal, Roughness, and Metallic maps. Ready for Blender. Ready for Unity. Ready for Unreal Engine. No 3D modeling skills required. Not a toy. Not a research demo. Production-ready assets that work in real game engines and film pipelines. No Maya license. No Substance Painter subscription. No $125/hour artist retainer. Here's what it does: → Image to 3D. Upload one photo, get a full 3D mesh in seconds. → Text to 3D. Describe any object in words, get a 3D model. → PBR texture synthesis. Metallic reflections, subsurface scattering, physically accurate materials. → Outperforms every open source AND closed source 3D generation model in benchmarks. → Full model weights released. Fine-tune it for your own use case. → Full training code released. First time ever for a model at this level. → Runs on 10GB VRAM for shape generation. → Supports macOS, Windows, and Linux. → Blender addon included. ComfyUI integration available. Here's the wildest part: This solves the "Janus problem." Where AI-generated 3D models have a different face on every side. Hunyuan3D 2.1 generates a clean mesh first, then projects PBR textures from multiple angles simultaneously. Coherent geometry. Seamless textures. Every angle looks correct. 3D artists charge $500 to $5,000 per model. Game studios pay $50,000 to $200,000 per year for 3D asset pipelines. Film VFX houses spend millions on modeling teams. Indie developers can't afford professional 3D assets at all. This generates them from a photo. On your GPU. For free. 3.1K GitHub stars. 447 forks. Built by Tencent. Published on arXiv. Models on Hugging Face. 100% Open Source. Apache 2.0 License.

seedance2.0で、フェイシャルテスト。 ①アングル変わっても2Dキャラ、3D顔にならない！ →3Dキャラは、アングルによって、顔を変形させないと2Dにできないのですが、それが完全に必要なくなっている、、、😱😱😱 ②大まかな表情芝居もprevisで指定できる →瞬き、ハーフブリンク、口のちょっとした開け閉め、口角の引きなどは効く。ただ、瞼の微妙な動きとかは来ない(ちょっとアニメーター泣かせかも) →デフォルト表情は、リファレンス画像から来てるっぽい ③コマ打ちも、ほぼそのままきてる！ →２コマ打ちと３コマ打ち混ぜたのですが、それぞれ反映できている アニメーター側で、どこまでコントロールするか、どこからはしないか。 まずは、そのラインを見極めたい🥹 ※右下が、previsとしてつくったフェイシャルアニメーションです。フェイシャル仕込んだモデルは、仕事でしかなくて、10年前くらいに個人でつくったモデルをひっぱりだしてきました、、、🤣

De verdad que son infumables hermano, en serio