正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

GPT-5.3-Codex + Image-to-3D Skill Just generated a cute avatar for Sam Altman

Hyper3D by Deemos

12,505 subscribers

80,329 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

GPT-5.3-Codex with image gen skill (NBP) I'm loving this model so much. This is one-shot

GPT-5.3-Codex with image gen skill (NBP) I'm loving this model so much. This is one-shot

Angel 🌼

306,384 次观看 • 5 个月前

Here's how to vibe code your very own 3D game characters for iOS. > nano banana pro > meshy for rig > export to glb > threejs skill to import > capacitor js for iOS > GPT 5.3 codex Full prompts + workflow in 🧵

Here's how to vibe code your very own 3D game characters for iOS. > nano banana pro > meshy for rig > export to glb > threejs skill to import > capacitor js for iOS > GPT 5.3 codex Full prompts + workflow in 🧵

Chong-U

143,553 次观看 • 5 个月前

GPT 5.4 medium in Codex + gpt-taste skill prompt was "landing page. 8sections. for an AI agency" here's the skill: Left: no skill Right: using skill

GPT 5.4 medium in Codex + gpt-taste skill prompt was "landing page. 8sections. for an AI agency" here's the skill: Left: no skill Right: using skill

Leon Lin

24,334 次观看 • 3 个月前

Step 1: Generate the base image with GPT-2 Step 2: Serve the image you just generated back to GPT-2 with this prompt: "Convert this scene into a 360 equirectangular image"

Step 1: Generate the base image with GPT-2 Step 2: Serve the image you just generated back to GPT-2 with this prompt: "Convert this scene into a 360 equirectangular image"

A.I.Warper

77,151 次观看 • 3 个月前

GPT Image 2 + Codex is such a strong combo

GPT Image 2 + Codex is such a strong combo

Angel 🌼

451,097 次观看 • 3 个月前

Meta dropped not just SAM-3 yesterday but also SAM-3D (for objects and humans)🤯 SAM 3D Body is a promptable model for recovering full-body 3D human meshes from a single image. Seems to be the new SOTA

Meta dropped not just SAM-3 yesterday but also SAM-3D (for objects and humans)🤯 SAM 3D Body is a promptable model for recovering full-body 3D human meshes from a single image. Seems to be the new SOTA

Niels Rogge

125,157 次观看 • 8 个月前

I took that 3D pirate character and made a point and click adventure game! > walkable nav mesh > item hotspots > animated backgrounds (ai generated) > debug level editor It's a proof of concept - but I really happy with how it's turning out. GPT 5.2 High + Codex 5.3 High

I took that 3D pirate character and made a point and click adventure game! > walkable nav mesh > item hotspots > animated backgrounds (ai generated) > debug level editor It's a proof of concept - but I really happy with how it's turning out. GPT 5.2 High + Codex 5.3 High

Chong-U

54,529 次观看 • 5 个月前

Asked GPT-5.5 in Codex to reconstruct this model from the image. Pretty close!

Asked GPT-5.5 in Codex to reconstruct this model from the image. Pretty close!

Ruben Kostandyan

124,735 次观看 • 2 个月前

I don't even need to mention which landing page was created by Opus 4.6 and which one by GPT-5.3-CODEX

I don't even need to mention which landing page was created by Opus 4.6 and which one by GPT-5.3-CODEX

Karan

90,021 次观看 • 5 个月前

Updating gpt-taste skill ⏳ this site was built with GPT 5.4 medium in Codex using gpt-taste prompt was "landing page. 8sections. for an AI agency"

Updating gpt-taste skill ⏳ this site was built with GPT 5.4 medium in Codex using gpt-taste prompt was "landing page. 8sections. for an AI agency"

Leon Lin

25,714 次观看 • 3 个月前

3D generation now down to 30s (was 5+ minutes before) using Z-Image T2I --> SAM-3D Image to 3D ⛏️

3D generation now down to 30s (was 5+ minutes before) using Z-Image T2I --> SAM-3D Image to 3D ⛏️

Blendi

127,713 次观看 • 7 个月前

GPT 5.3 vs Opus 4.6: a second win for Opus! ✔︎ Opus builds the file 2x faster ✔︎ Opus nails a good first version ❌ Codex needs 3x "fix bugs" to have a first working version ❌ Codex UI looks really bad Let's try more things....

GPT 5.3 vs Opus 4.6: a second win for Opus! ✔︎ Opus builds the file 2x faster ✔︎ Opus nails a good first version ❌ Codex needs 3x "fix bugs" to have a first working version ❌ Codex UI looks really bad Let's try more things....

Melvyn • Builder

70,874 次观看 • 5 个月前

Image-to-Multiple 3D Parts 🔥🚀 Generated in one click.

Image-to-Multiple 3D Parts 🔥🚀 Generated in one click.

Emm | scenario.com

59,254 次观看 • 1 年前

GPT Image 2.0 + Generated Normal Maps = Dynamic Lighting and Shadows for UI. 🤯 The workflow for building high-fidelity skeuomorphic UI concepts with AI + Three.js just got a lot easier. Interactive experience, sound fx, and normals all generated with Omma AI (tool by Spline). 3D iPhone by Ranguel on Sketchfab. Happy to share the remix link if you would like to poke around, lmk!

GPT Image 2.0 + Generated Normal Maps = Dynamic Lighting and Shadows for UI. 🤯 The workflow for building high-fidelity skeuomorphic UI concepts with AI + Three.js just got a lot easier. Interactive experience, sound fx, and normals all generated with Omma AI (tool by Spline). 3D iPhone by Ranguel on Sketchfab. Happy to share the remix link if you would like to poke around, lmk!

Gábor Pribék

12,290 次观看 • 3 个月前

From a passing glance to holding hands forever 🌸❤️ Generated this with GPT image 2 + Seedance 2.0 on BudgetPixel AI

From a passing glance to holding hands forever 🌸❤️ Generated this with GPT image 2 + Seedance 2.0 on BudgetPixel AI

Ai Arainz

19,169 次观看 • 2 个月前

Putting the AI generated sprites into a PLAYABLE demo. → Codex CLI → GPT 5.4 xHigh → GPT Image 1.5 for Idle + Attack → Sora 2 for Walk + Run + Jump While not perfect, I'm actually quite impressed at these early experimental results. Goal: Vibe code an entire game with AI (gameplay, art, sfx) and document learnings as much as I can.

Putting the AI generated sprites into a PLAYABLE demo. → Codex CLI → GPT 5.4 xHigh → GPT Image 1.5 for Idle + Attack → Sora 2 for Walk + Run + Jump While not perfect, I'm actually quite impressed at these early experimental results. Goal: Vibe code an entire game with AI (gameplay, art, sfx) and document learnings as much as I can.

Chong-U

125,889 次观看 • 4 个月前

Sam Altman says GPT-5 (!) will be smarter than him. Why will it take orders from him? Will GPT-6? Daily reminder that they're about to unleash 100 billion smarter-than-sam shoggoths onto the internet and are just HOPING they stay obedient forever

Sam Altman says GPT-5 (!) will be smarter than him. Why will it take orders from him? Will GPT-6? Daily reminder that they're about to unleash 100 billion smarter-than-sam shoggoths onto the internet and are just HOPING they stay obedient forever

AI Notkilleveryoneism Memes ⏸️

29,693 次观看 • 1 年前

After a weekend of testing and working on something with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look like

After a weekend of testing and working on something with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look like

Tibor Blaho

29,794 次观看 • 5 个月前

A single image generated by GPT Image 2, combined with Seedance 2.0, can already achieve this kind of effect Below is the Image 2 prompt👇

A single image generated by GPT Image 2, combined with Seedance 2.0, can already achieve this kind of effect Below is the Image 2 prompt👇

Ai Arainz

28,476 次观看 • 2 个月前