fabdream.ai

Visual Storyteller | Dad | IG 350K | Exploring the intersection of art, history, futurism, and technology

[fabdream.ai @fabdreamai]

The Second Renaissance : I made this 1-minute film in 48 hours with the help of 6 AI agents.

Open source models. Local & cloud.
$47 in API cost. Submitted to an international competition.

Full breakdown 🧵

[Claude @claudeai]

Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.

Available today at the same price.

[Logan Kilpatrick @OfficialLoganK]

Welcome to Gemini 3.5 Flash, our most powerful model to date. It pushes the frontier of intelligence, speed, and cost putting 3.5 Flash in a class of its own.

We spent the last 6 months making sure Flash is great for real world use cases. It's available everywhere now!

[fabdream.ai @fabdreamai]

@Miguel07Code tried Avatar V with Seedance mode, French is completely broken, it just invents its own phonetics. any workaround planned? even feeding a pre-recorded voiceover didn't help

[fabdream.ai @fabdreamai]

@HeyGen tried Avatar V with Seedance mode, French is completely broken, it just invents its own phonetics. any workaround planned? even feeding a pre-recorded voiceover didn't help

[fabdream.ai @fabdreamai]

@HeyGen now that V is out, does Avatar IV pricing drop or ?

[fabdream.ai @fabdreamai]

@karpathy @moritzkremb Wow Anthropic win 🤯

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[Google DeepMind @GoogleDeepMind]

We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video.

It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵

[fabdream.ai @fabdreamai]

@ingi_erlingsson @ltx_model so good !

[fabdream.ai @fabdreamai]

@PrunaAI cool, where do I test the new version? fal up to date or is there another playground I should use?

[fabdream.ai @fabdreamai]

@PrunaAI Thank you , feel free to let me know when a new update is up, for testing 😁

[fabdream.ai @fabdreamai]

@PrunaAI Yes look :

[fabdream.ai @fabdreamai]

@PrunaAI I mean the eyes, they lose focus and stop looking straight at the camera, sometimes going slightly off-axis mid-sentence. It breaks the illusion instantly, and even explicit prompts like 'look directly at the camera' don't fix it. You can actually see it in your own demo.

[fabdream.ai @fabdreamai]

@0xInk_ Yees ! hâte de voir ce que tu va nous pondre, ça manque clairement de contenu qualy dans la commu french

[fabdream.ai @fabdreamai]

@NousResearch @TonyJMatos @ComfyUI already running comfyui as an agent skill. my setup does this. going to push it further with this. thanks 🔥

[fabdream.ai @fabdreamai]

@runwayml

[fabdream.ai @fabdreamai]

@TencentHunyuan wow 🔥

[fabdream.ai @fabdreamai]

@peterom

[fabdream.ai @fabdreamai]

@HeyGen CLI