Edelises Quaresma

Computer Forensics _ Portuguese_London_contentCreator

[Chiro Visuals @chirovisuals]

I've extended my open source VFX playground built with @threejs. New 10 fully real-time customizable abilities. 3 Radial abilities, 3 boosts, 3 portals & 1 Linear casted ability.

For this project I used Minimax-M3, one of the cheapest models around & impressive for what it costs.

Everything you see is generated: no textures, no sprite sheets, no baked meshes.hand-written GLSL, GPU-simulated instanced particles, world position resolved in the vertex shaders...

Source code : https://t.co/dNKjM2hviN

[Stable Diffusion Tutorials @SD_Tutorial]

Control Face exp in ComfyUI-NKD-Basic-Tools

👇
https://t.co/PNgKoGpAfh

[Snow Brave @Sn0wbrave]

لو تستخدم أدوات الصوت بالذكاء الاصطناعي، هذا المشروع يستحق التجربة. 🔥

VoiceStudio مفتوح المصدر ويعمل محليًا، ويدعم استنساخ الأصوات، الدبلجة، التفريغ الصوتي وإنشاء الكتب الصوتية.

https://t.co/k2U882Du17

[Stable Diffusion Tutorials @SD_Tutorial]

ComfyUI 📸Photoshoot

Describe a person once, then vary camera, pose, mood and ratio across 40 images with 44 fields — body, face, hair, make-up, clothing — and saves them under a name.

Supported on Krea 2, Flux, SD 3.5, SDXL, SD1.5 Qwen-Image

👇🧐
https://t.co/aaLfctlnDr

[Tom Dörr @tom_doerr]

Curates a list of essential technical concepts including algorithms, data structures, and distributed systems for software developers.

https://t.co/iI6JdFY5JR

[Vladimir Bayandin @vovudebosh]

🚨 NO CLIENTS? 6 MONTHS BUILDING, STILL $0 REVENUE.

THE PROBLEM WAS NEVER THE PRODUCT — IT WAS SALES.

DROP YOUR LINK: THIS AI FINDS YOUR BUYERS, WRITES THE EMAILS, BOOKS THE CALLS.

$30 FREE CREDITS, ONLY 9 LEFT — GONE TONIGHT 👇

https://t.co/kJ57WtkMOK

[FC CONCEPTS @EAFCconcepts]

🚨EA are looking at the possibility of adding kit changes to Career Mode 👕

While there's obvious licensing challenges, EA are talking to clubs to figure out a way to bring this feature to the game 👀 #FC27

ℹ️@dico_tv

[TechHalla @techhalla]

made with Midjourney + H3

prompts below 👇

[Olatunde AI @OlatundeAI]

STEP 3: Generating the Location Sheet. Copy the prompt below into ChatGPT, then add the Location Description from STEP 1 to the prompt and run it.

Below is the prompt. Kindly remember to add the Location Description in the box below the prompt.

"Create a professional AI Video Production: Location, Props, and Recurring Objects Sheet using the provided reference images.
Create a polished 4:5 production reference sheet containing:
1. LOCATION — show the establishing view, key angles, spatial layout, entrances, exits, architecture, furniture, fixtures, surfaces, signage, lighting, atmosphere, and defining environmental details.
2. PROPS AND RECURRING OBJECTS — show every important object associated with the location or story, including furniture, tools, equipment, containers, documents, devices, decor, and character-related items. Include front, side, back, 3/4, functional, and close-up views where relevant.
3. SCALE AND CONTINUITY — document approximate dimensions, object placement, orientation, condition, use, ownership, and relationship to the environment.
4. COLOR AND MATERIALS — include 4–6 key colors with HEX codes, plus accurate references for architectural, environmental, and object materials.
5. DO NOT CHANGE — lock the location’s architecture, layout, proportions, furniture, lighting, materials, colors, signage, props, object dimensions, branding, markings, condition, and defining details. Do not redesign, add unrelated objects, create variants, or alter proportions.
Use a clean neutral presentation background, cinematic environment photography, premium object photography, soft controlled lighting, realistic materials, sharp details, subtle shadows, clean typography, thin dividers, balanced spacing, and a sophisticated editorial grid.
The sheet must function as a visual continuity bible for AI image and video production. Keep the location identical in every view and each recurring object physically consistent across all views and scenes. Clearly separate the LOCATION and PROPS / RECURRING OBJECTS sections. Do not include characters, decorative filler, or unrelated background elements.

LOCATION DESCRIPTION:
(Paste the Location Description ChatGPT gave you here)"

[Richard Palethorpe @jichiep]

kimodo.cpp is up on GitHub! It allows you to animate a skeleton by describing what you want it to do.

[Edelises Quaresma @IamEdelises]

@TerminalWarGame How did build the characters customisation?
Did you use Character Creator 5 ?

[TERMINAL WAR @TerminalWarGame]

We built a fully custom character customization system, It's early but there is a lot more on the way!

You'll be able to create a unique character for each of three factions!

[Meng To @MengTo]

I open-sourced ThreeUI, my library of three.js components and landing pages.

160+ are free, and the tool is free too. It includes procedural 3D hero sections, icons, and motion designs. Copy the prompt or source, give it to your agent, then change the theme, lighting, motion or layout.

Live site: https://t.co/rtCfqeZnOP

Repo: https://t.co/B66ahgxHVl

I'm adding a lot more soon. Pro comes with 50+ extra components, MCP, and skills. Early adopters get 50% off right now.

[Jessy Leite @jessylte]

Skinning a character properly is still one of the most annoying parts of 3D.

Adaptive Auto Skinning does it in one click. The next update improves weight propagation on organic shapes, and increases voxel precision in tight zones.

Out in a few days. How to get AAS below
#b3d

[Olatunde AI @OlatundeAI]

STEP 2: Open ChatGPT and upload the Character Image alone. Add the below prompt and run it.

Create a professional AI Video Production — Character Reference Sheet for the provided character image. Create a polished 4:5 portrait continuity sheet focused exclusively on the character:
1. CHARACTER PROFILE — name, role, approximate age, height, body type, personality, distinctive traits, and signature colors.
2. FULL-BODY TURNAROUND — front, 3/4, side, and back views of the exact same character at matching scale, with identical facial features, hairstyle, body proportions, costume, colors, and accessories.
3. FACE AND IDENTITY DETAILS — front, profile, and 3/4 head-and-shoulder close-ups showing facial structure, eyes, eyebrows, nose, lips, hairstyle, skin tone, makeup, scars, tattoos, and other defining features.
4. EXPRESSION SHEET — neutral, happy, angry, sad, surprised, worried, confident, and determined expressions. Preserve the exact same facial structure and identity in every expression.
5. POSE AND BODY LANGUAGE — neutral standing, walking, sitting, relaxed, tense, and action-ready poses. Maintain consistent anatomy, proportions, posture, and silhouette.
6. COSTUME DETAILS — close-ups of clothing layers, fabrics, seams, fasteners, footwear, jewelry, eyewear, markings, logos, and other character-defining wardrobe elements.
7. COLOR AND MATERIAL PALETTE — include 4–6 key colors with HEX codes, plus references for skin, hair, fabric, leather, metal, plastic, armor, or other visible materials.
8. DO NOT CHANGE — lock the character’s face, identity, skin tone, age, hair, eye color, body shape, proportions, costume, accessories, markings, colors, and defining features. Do not redesign, beautify, age, stylize, simplify, or create alternate versions.
Use a clean white or neutral studio background, soft controlled lighting, realistic materials, sharp details, subtle shadows, clean typography, thin dividers, balanced spacing, and a sophisticated editorial production-design grid.
Every panel must depict the exact same character with absolute visual consistency. Focus only on the character. Do not include props, additional characters, environments, unrelated objects, or alternate outfits."

[Stefan 3D AI @Stefan_3D_AI]

Hi3D V3.0 is out today, and it is the most detailed and realistic 3D generator I have run. And its first model to build geometry at 2048³ voxels.

The materials were the surprise. PBR output is well ahead of V2.1, and fine surface relief survives where the other frontier models smooth it flat.

I compared it against the current top models across a wide spread of objects, textures on and textures off. It lands at number 2 in my ranking. For 3D printing I think it takes first outright.

Also, they opened 48 hours of free access for the launch, which almost nobody does.

Full breakdown: https://t.co/2LpRtd2S9x

[小宇Chengzi @Chengzilhy]

这个OOTD换装玩法其实很简单：
其实是分开生成，再剪到一起的。👇

每一套穿搭都单独生成一段视频： 换 Look + 换咖啡店场景 + 换杯子 + 换表情。
每段结尾都让杯子贴近镜头完全遮满画面， 下一段再用新的杯子从镜头前拿开。
最后把几段直接卡点拼起来，就有这种连续换装效果。
Seedance 2.5 制作
Prompt🔽

参考上传图片中的同一位女主人物，生成一段 4秒、9:16竖屏、真实感时尚短视频。

【人物】

严格保持上传图片中的人物脸部、五官、发型、发色、肤色、年龄感和身材比例一致。

当前造型：

【场景】

人物位于：

【填写本段咖啡店场景】

场景真实自然，具有精品咖啡店生活感。

人物保持画面中央。

使用 近距离鱼眼超广角、高机位轻俯拍。

杯子靠近镜头时形成明显的巨大前景透视，同时能够看到人物身体和周围环境。

【杯子】

人物手持：

【填写本段杯型＋饮品】

杯子是本段最主要的前景转场道具。

【时��轴】
0.00–1.00秒｜杯子撤开

开场时，杯子已经非常靠近摄影机并占据画面大部分区域。

人物沿镜头正前方将杯子平稳向后收回。

随着杯子撤开，逐渐完整露出：

人物脸部 → 当前穿搭 → 当前咖啡店场景。

摄影机保持稳定。

1.00–3.00秒｜人物展示

人物保持当前坐姿或站姿，直接面对镜头。

完成一个简短自然的表情：

【填写本段表情与小动作】

主要依靠眼神、嘴型、头部和轻微身体姿态变化完成表演。

动作自然真实，幅度较小。

服装和场景在这一段清楚展示。

3.00–4.00秒｜杯子遮镜

人物保持当前表情，将手中的杯子沿摄影机中心直接向前伸出。

杯子快速靠近镜头并明显放大。

最后：

杯身完整覆盖整个画面，保持完全遮镜状态结束。

方便下一段视频从另一只新杯子遮住镜头的状态直接衔接。

【强制统一规则】

每一段视频都保持相同的：

杯子遮镜开场 → 收杯露出人物 → 表情展示 → 杯子再次完全遮镜结束。

人物身份始终一致。

不同视频只更换：

服装 + 场景 + 杯子/饮品 + 表情。

统一保持：

4秒、9:16、强鱼眼超广角、高机位轻俯拍、人物居中、巨大杯子前景透视。

动作自然真实速度，节奏清楚、利落、干脆。

[Nicholas Takeyama @nico_takeyama]

AI凄まじいな。こんなの作ってる最近

[Shams @ShamsAmin56]

MiniMax H3
Character Reveal Presentation - Kinetic Typography

MiniMax H3 is insanely accurate to handle the text renders, I tried some kinetic typography and the results are superb - Modern condensed font.

Tip: You can also use your favorite font/style reference.

Prompt below

[GlobeUpdate @Globupdate]

🚨🇬🇷 BRITISH COUPLE KILLED IN #GREECE HELICOPTER CRASH

Newlyweds Alexander Cromie & Marie Ebert were killed alongside their Greek pilot when their helicopter crashed on Sifnos during their honeymoon

The helicopter crashed just metres from the landing pad & caught fire
#健大高崎