Ra_m

[Olivier Poncet 🦝 @ponceto91]

Les entreprises en 2026.

[Adrien Rouquié @adri_flex]

Programming ladders is absurdly hard.

Kesh can now climb, open doors and smash clay pots in Ashenmoor, with a first pass of sound effects. I thought the ladder would be the easy part. It took longer than everything else in this clip 😅

#b3d #GodotEngine #IndieDev

[Adrien Rouquié @adri_flex]

#AutoRemesher 1.0 came out and I couldn't resist vibe-coding a tiny Blender bridge for it.

Nothing fancy, but it lets me send the selected mesh to AutoRemesher and bring the result back into Blender.

[亀井りく｜「RecGame」広報担当 @RecGame_RA]

【これ、リアルタイムで動いてます】
Overwatch 2に関わったPedro Borges氏がUE5で作ったトゥーンシェーダー。
セルシェーディングに手描き風のハッチングやモーションブラーを重ねて、
アニメがそのまま動いているような画になっています🎨
#UE5 #realtimeVFX

[Ra_m @Topsi37]

https://t.co/rhJmqecnEN

[ComfyUI @ComfyUI]

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal.

The highlights:

→ Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it

→ VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported

→ Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end

Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1

Learn more with our blog 👇

[Ra_m @Topsi37]

@adriflex Excellent

[Ra_m @Topsi37]

@adriflex @happy_modeling 👏👏

[ThinkerView @Thinker_View]

RIP mon ami
I/ https://t.co/gChmcfS2Uj

II/https://t.co/EP1gZRWqs5

[R@aiaicreate @aiaicreate]

Blenderの3Dレイアウトと手動カメラアニメーションをAI動画生成が1:1で正確に追従。建築比率や空間レイアウトを維持した高品質映像生成ワークフロー。Kling/Seedance活用事例。V2V手法やWan VACE等類似ツールの機能比較も論点。

#ComfyUI #AI動画生成

URLはリプ⬇️

[cocktail peanut @cocktailpeanut]

AI4AnimationPy 1-Click Launcher --- Every frame is generated, not authored.

An animation engine that uses AI to GENERATE every next pose in realtime, instead of human animators having to build frames manually. And it's FAST.

Wrote a UI that runs on ALL machines, 1click launch.

[はさまるスタジオ (Hasamaru Studio) @hasamaru_studio]

SeedanceやKlingなどの動画生成で、狙ったカメラワークにならない時は、
一度3Dモデルを作って、自分でカメラワークを組むのもかなり有効です。
3D未経験でも、Tripoなどを使えば画像から3Dモデルを生成できます。

流れはシンプルで、

参照画像
→ Tripoで3Dモデル生成
→ Blender等でカメラワーク作成
→ Kling 3.0 Omniで参照画像の質感を適用

「カメラワークが思い通りにならない」
という時の選択肢として、ぜひ試してみてください。

[Wildminder @wildmindai]

Clean design! This is exactly how it should look.
Kijai delivering again with a slick memory usage visualizer for ComfyUI.

https://t.co/AvAcSbRDSP

[ComfyUI @ComfyUI]

You can create split-stack videos like this in one click with the link below.👇

In the simple version, all you have to do is upload an image and it handles everything for you.

But if you want more control, you can jump into graph mode and tweak each parameter to get more detailed, custom results.

[Ostris @ostrisai]

AI Toolkit now supports fine tuning @Lightricks @ltx_model LTX 2.3. As always, let me know if you run into any issues. https://t.co/iQqi5JIKs3

[Eric @EricLevin77]

Having fun with GPU compute particles, fingertip attractors, and web audio for synths

[Alex @alexfredo87]

For the facial animations in my game, I use a technique that yields results similar to L.A. Noire. To keep it simple: I first generate a facial animation video using AI like LTX 2. Then, I create a video depth map from that animation and project it onto a face mask. Using vertex displacement, the depth map dynamically deforms the face as the character speaks. The result looks good in standalone VR. I actually created this workflow long time ago:

[LTX.io @ltx_io]

🚨 800 FREE CREDITS — 24 HOURS ONLY

We just launched LTX-2.3, our most powerful video model yet. High-res. Fast. Cinematic. Native lip-sync.

Follow + Retweet this post to get 800 credits sent to your DMs.

[Paroles d'auteurs @Paroles_auteurs]

"Je pense que l'humanité n'est pas nécessairement la favorite de la nature, que l'humanité peut très bien disparaître, que nous ne sommes pas une espèce sacrée, qu'il y a eu 10 millions d'espèces animales jusqu'ici, que neuf millions ont été éliminées... On n'est
pas l'espèce élue, comme on l'a cru pendant longtemps ; la nature peut très bien se passer de nous. Et elle ne nous éliminera pas ; c'est
nous qui pourrions nous éliminer. Et si nous nous éliminons, la nature ne fera pas particulicrement un deuil, mais elle continuera à développer d'autres espèces, en espérant que ces espèces seront plus en mesure de se préserver et de ne pas se détruire."
Hubert Reeves, Conteur d'étoiles

[ComfyUI @ComfyUI]

Hunyuan 3D 3.0 is now available in ComfyUI via Partner Nodes!

We are bringing more models & tools into ComfyUI, starting with state-of-the-art asset generation from text, images, or sketches.

Coming soon in ComfyUI:
- texture editing
- semantic UV unwrapping
- intelligent 3D part decomposition

The goal isn’t to replace 3D artists.
It’s to remove the non-creative friction so real creative moments can happen faster.