elevendr-エレベンダー

@JoshuaTookes Real

Daffy looking hotter than lola as usual

@trickytwitch Been a while since you posted

@FuzzyBull @imagine I mean too be fair no video model ha real world info yet but Nano Banana as a image model dose so

One hour left to submit. What was Chibi You up to this weekend?

@imagine Hi I'm trying to create the Chibi but this screen keeps coming up when I try to prompt it, is this a bug?

totally normal behavior

@TySights Here is one example I was able to make with Grok Imagine

I don't see any examples of this. I wasn't impressed with grok's video maker, most has been hype.

@erickxie When I tried, it got me this screen

Worth of a try especially the video image-to-video feature.

@ThePandemos But why though? Is it because you see too much AI slop and not actual AI Art that has been really put into effort. Grok Imagine was free and good alternative for Sora and know I'm stuck with no questions

Watching AI Bros crash out because they can't generate their porn is funny Like half of these are complaining about the price, and the other half are upset with moderation being 'too strict' due to the lawsuits from when grok allowed them to generate porn of IRL people Fuck AI.

@Avieshek @ihtesham2005 This is a method of abliteration that preserves the intelligence of LLMs better then other types of Abliteration

@ihtesham2005 Isn’t Abliteration better?

This is wild 🤯 Someone built a tool that automatically removes safety alignment from ANY AI model. It's called Heretic. → Works on Llama, Qwen, Gemma, Mistral and most major models → Runs on a consumer RTX 3090 in ~45 minutes → Achieves same refusal suppression as manually tuned abliterations → Preserves model intelligence better than existing methods The scary part isn't the tool itself. It's that every AI lab spending billions on safety alignment is now in a race against a 14-contributor open source repo. Every safety update shipped → community figures out how to abliterate it → repeat. This is what the AI safety debate actually looks like in 2026. 100% Opensource. Link in the comments 👇

@FionaMaray Real

Asmongold

@theGothicVixen Yes hun

Morning did you sleep well?

five words. 20 years. unfinished.

@techdevnotes Somehow I can generate Grok Imagine photos via replies as a free user

xAI has Officially removed this feature from X

@paulism @support_huihui @grok That's because it's been distilled from Claude Opus 4.6 so Qwen wont overthink

@support_huihui I don't understand why there's a claude in the name of this model, of this Qwen model. @grok

New Model: huihui-ai/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated This is an uncensored version of Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2 created with abliteration huggingface.co/huihui-ai/Huih…

@imagine When I try to make Grok Imagine photos, the photos are stuck like this, anyone know why?

Need more Chibi on your timeline? Show us how Chibi You spends the weekend in a “day in my life” video with Grok Imagine. The #1 entry will win a custom desk figurine of their main Chibi character plus one year of SuperGrok. The 4 runners-up will each win one year of SuperGrok. Use our Chibi template on the @grok app or website to bring it to life.

@diXenn1 @techdevnotes They actually switched from Flux to their own in house image model for Grok Imagine

@techdevnotes Why Grok Imagine? After all, it's Flux. Be honest.

New Grok Imagine account on X

Ummm I did not remember posting this.

A TikToker goes viral after he was pretending to be a Trump fan and then scamming MAGA followers for $30,000😬