宵月時雨

[qiyu @hakcinth]

i don't know about the language barrier but i'd highly recommend both DM袋喵 and i调调i on bilibili!!!
the former is incredible at posing/anatomy with a unique (and crazy efficient??) drawing method, while the latter does "art fixing" tutorials featuring a variety of skill levels

[1MAFX @pmargacz]

Put together a pack of 20+ tileable noise textures I actually use, the same ones behind a lot of the erosion in the materials and UV distortion effects in my tutorials.

Comes with a tutorial on how I use them when building VFX.

A good noise library does more for your materials than people think.

Gumroad - https://t.co/owuMrnbx1R

#vfx #unrealengine #techart #gamedev #realtimevfx #madewithunreal #vfxfriday

[✦ @MiseFX]

very good study for anyone getting into vfx

[MimikuWo @MimikuWo]

No lighting components
Baked GI + Shadowmask + Irradiance Volumes + SOF + PCSS Shadows + OGA + Mitoon
#MizuChronicles #水色戦記

[Superman @thesupermanmx]

China open-sourced a peanut-sized OCR that parses entire 100-page PDFs in one shot..

It's called Unlimited-OCR. Only 3B params. Runs locally.

Every other OCR tool chops your doc into pages and loses the thread. this one reads the whole thing in a single pass.

→ One-shot "long-horizon" parsing (32K context window)
→ Multilingual, out of the box
→ 93% on the standard parsing benchmark (+6 over baseline)
→ <0.11 error rate past 40 pages
→ Runs 100% locally on your own hardware
→ Works with Transformers, vLLM, SGLang, Docker, Ollama, llama.cpp

Traditional cloud OCR (Textract, Google Vision, Azure Doc Intelligence) costs $1.50–$15 per 1,000 pages.

This runs on your machine. For free. Forever.

Baidu built it explicitly to push DeepSeek-OCR one step further. Already at 1.9M downloads on Hugging Face and most people have no idea it exists yet.

100% open source.

[80 LEVEL @80Level]

This Godot map editor, showcased by developer samsfacee, auto-generates a stylized 3D world from simple tiles.

[uptoon(정보계정) @toonup2]

요약 정리

매번 그림 완성 후 납작해지는 이유와 해결 방법

① 색은 구분되지만, 명도가 비슷하면 그림이 납작해진다.

② 색 고를 때 명도도 꼭 함께 신경 쓴다.

③ 흑백으로 변환해 명도 대비를 확인하는 습관이 큰 도움이 된다.
https://t.co/5omDpFNgXP

[Superman @thesupermanmx]

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time.

one camera. no LiDAR. 10,000+ frames without falling apart.

just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps.

→ runs at ~20 FPS on a single GPU
→ Stable over 10,000+ frames
→ Beats optimization-based methods on benchmarks
→ Works on drone footage, driving videos, indoor walkthroughs

100% open source.

[Lunafloris @Lunaflorisi]

Watch how the shading brings out the fabric wrinkles 💪🎨✨
by akymdesign

[ezdraw @ezdrawps]

Build the shadows first, then add highlights for depth

[りふる🐰ﾃｨｱ西4/せ18ab @gothicrifuru]

·˚ ༘♡🎉7/31(金)発売✨·˚ ༘♡
୨୧┈┈┈┈┈┈┈┈┈┈┈┈୨୧
『えちおね♡
-えっちなおねーさんに愛されまくり-』

デザインもとても可愛くて
実物の本を手に取れる日が楽しみです⸜🙌♡⸝‍
୨୧┈┈┈┈┈┈┈┈┈┈┈┈୨୧

▼ご予約・詳細はこちら（GOT公式）
【　https://t.co/jghPJvOWla　】

🩷書店別特典は後日改めてお知らせします！

[Yowhza | Waitlist open! @realYowhza]

draw the effect not the object 🥹

[ふぁーすと @first3478]

今、世界中のエロい男が好きな人たちからの無言のブックマークが集まっている

[HOOD @hood_x_art]

Paint hair with me
https://t.co/kkEr82UoPB

[マツバ @matsuba_p]

2026年度の「深夜残業してる時に見たい光景大賞」が早くも決まってしまったが？？？？？

[hunny @Hunnyindapants]

This was the greatest art tip video I’ve ever watched wow 👏

[smile @dsuV4sW8qYWHQVL]

影から描きたくてぇ

←ラフ　　　　　　　　　　→完成

[DONTPANIC© @paniclightmate]

Better colors, better art 💙

[ʜᴇʏᴢ | ꜱɪɴᴀʟɪᴜᴍ ᴀᴄᴀᴅᴇᴍʏ @heyz_in_haze]

맞아요! 이런 스타일의 경우 명암은 정말 필요한 부분에만 넣고, 빛이 가장 돋보일 수 있게 하는 게 중요해요.
타래로 어떻게 그리는지 알려드릴게요!

[Zsolt Kacso @kaolti]

Always loved these topographic maps and wanted to create something similar with Three.js.

3 hours in Claude Code with Fable.