Disagreement enjoyer. Unpopular opinion. Usually take an opposing stance. I believe I'm right so you don't have to.
Joined October 2009
- Tweets16.4K
- Following337
- Followers152
- Likes18.7K
Pinned Tweet
Z-Image Turbo as the photo generator
Flux 2 Klein as the style transfer
Totally random prompt.
Control by concept slider loras on ZIT and the self train style transfer loras blend on Klein to get this specific style consistently. 80-120 sec for the real-stylize pair on RTX3060.
เห็นส่วนมากที่แนะนำตัวว่าเป็นลูกครึ่ง จะมีแต่ที่พ่อเป็นสวิต แม่เป็นปลั๊ก
ไม่ใช่แค่เชื้อจีน
ดารา เชื้อสาย west เช่น ญาญ่า มาริโอ้ เค้าก็แนะนำตัวเองเป็นคนไทย(Nationality) มีคนถามถึงค่อยบอกว่าตัวเองเป็นลูกครึ่ง (Ethnicity) อะไร
สัญชาติ= Nationality = ไทย
เชื้อชาติ = Ethnicity = จีน , จีน-ไทย
คนไทยส่วนมากถือสัญชาติเป็นหลัก ไม่ใช่เชื้อชาติ
1
3
343
RYOUGI Ilakya retweeted
Introducing AutoRig for Spine2D, a tool I’ve been working on for a while!
This video gives you a quick look at my updated workflow. Setting up rigs directly in Spine felt slow to me, so I built a companion tool that still works with Spine. The controls are similar, so if you know Spine, you’ll feel right at home.
I’ve added some handy features and integrated mesh generation, including batch meshing that I’ve found more accurate than Spine’s.
Then I let Claude handle the binding. After a few rounds of refining the skill, a simple “bind this for me” was enough. Maybe it’s already familiar with my Spine workflow and rigging habits after all this time, lol.
The weights still need a human eye and some manual cleanup, but Claude can handle multiple variants and masking issues in one go. For the character shown here, going from setup to an animation-ready rig took around two hours—several times faster than my usual process!
I think tools like this could help our industry work more efficiently. I’m not looking to squeeze money out of everyone, and I’m sure more people will build similar tools, so I’m planning to release a free trial version!
Join my Discord server to get access when it’s ready! There will also be special tool offers for students.
The trial might have a few bugs—you can’t expect me to hand over my overpowered build, right? Or you can try fixing it yourself (๑•̀ㅂ•́)و✧
Thanks, everyone!
Illustration: @rikuto_lin
#spine2D #spinetool #animation #animationtool #autorig
RYOUGI Ilakya retweeted
Compatible
#studiowrong #StellasMaterialism
RYOUGI Ilakya retweeted
Pixel Art Lighter is out now! ✨
I first made this tool for my game, but am releasing it free and open source for everyone.
Generate and edit normal maps and light masks, while keeping your sprites pixel perfect.
Hope it helps with your art or gamedev!
RYOUGI Ilakya retweeted
Just released a new pixel art model for game development:
- Exact size control
- Style consistency using reference sprites
Use it with Claude or Codex: spritefusion.com/pixel-art-g…
RYOUGI Ilakya retweeted
ของดี เไ วันนี้ — IconMCP
iconmcp.com/
เว็บแจกไอคอนเวกเตอร์ ที่ใช้ เไ ค่อยๆวาดทั้งวันทั้งคืน (อันไหนที่วาดอยู่ น้องก็จะวาดให้เห็นเลย เป็นแอนิเมชัน 555) ตั้งเป้าว่าจะแจก 1 แสนแบบ
ไอคอนสามารถปรับแต่งขนาด ความหนา สี มุมมน ฯลฯ ต่างๆ ได้หมด และฟรี (MIT licence)
RYOUGI Ilakya retweeted
UniRig
Automatic skeleton and skinning for any 3D model, from SIGGRAPH 25
UniRig predicts a skeleton and skinning weights for a 3D mesh so it is ready to animate.
It was built by Tsinghua University and Tripo.
One model handles humans, animals and unusual shapes. You run skeleton prediction, then skinning, then merge the result back into your file.
The authors now also point to SkinTokens, a successor that does both steps in one pass.
github.com/VAST-AI-Research/…
RYOUGI Ilakya retweeted
また、ローカルPCで動く謎の技術が公開されてる…
写真一枚からガウシアン・スプラット（Gaussian Splats）の3Dモデルにしてくれるんだけど、結構いい感じに生成できる模様。
github.com/speridlabs/idol-s…
🤖 Made with AI
RYOUGI Ilakya retweeted
Qwen3.5-4B-GLB-3D-Coder
Renderable 3D assets from a 4B model.
Following its earlier 3D Coder project, CCORE has released a new Qwen3.5 fine tune focused on generating 3D assets for game development.
The model turns text prompts into standalone HTML and JavaScript scenes using Three.js.
Each scene includes a GLB export button, allowing generated assets to be imported into Godot.
Examples include a mana potion, goblin, desert merchant and detailed environment props.
The developer reports most generations work on the first attempt, especially with English prompts.
Q4_K_M and Q8_0 GGUF checkpoints are available.
Full model weights and the training dataset are planned for release after training finishes.
huggingface.co/ccore/Qwen3.5…
RYOUGI Ilakya retweeted
もしかして Tripo Canvas 凄い？
Making a character with the new "Tripo Canvas"
I'm not sure if I should use more nodes
I've tried out the new Tripo Canvas, which is still in beta, and it was very easy to work with nodes, just like in other 3D programs. The Tripo Canvas workflow lets you work with Tripo much faster than the conventional way—creating multiple references at the same time, separating parts of the model, and creating different views for the body and head, as well as accessories.
Although I found all of this extremely useful, I think the most useful feature is the AI Lab node, which lets you interact with an AI agent to separate meshes, close gaps, eliminate distortions, merge meshes, and set up or build a scene using various 3D models or images you provide (it also gives you all the results in a Blender file so you can continue working on them in Blender if you like).
I’ll keep testing the tool to see what else I can create🐋 #blender
