Skip to content
Agientry
ZH

Demos

AIGC demos filed by vertical — agents and LLMs doing real work, world models, AI-made games and design. Each clip carries its vertical and capability domain; pick a chip to narrow the feed.

WaterfallPagination
All verticalsDevelopmentData & AnalyticsSecurityDocs & SlidesMediaDesign & FrontendGame MakingResearchKnowledgeEducationMarketing & GrowthCommerce & RetailLegal & FinanceHealthcareManufacturing

Media vertical hub →Video editing, image generation, audio and scoring

LTX 2.5 + CQ Enhancer LoRA: 8-step zero-prompt AI video cleanup (before/after)
4:48

LTX 2.5 + CQ Enhancer LoRA: 8-step zero-prompt AI video cleanup (before/after)

@princedoesai · 582 views · 2026-10-04
LTXVideo-Enhancer
Qwen-Image-2.1 outfit-swap consistency LoRA: dress a person from two pics with 0.1px drift
0:19

Qwen-Image-2.1 outfit-swap consistency LoRA: dress a person from two pics with 0.1px drift

@wildmindai · 621 views · 2026-10-04
Qwen-ImageLoRA
FreeVideo: MiniMax H3 video generation on a laptop with as little as 8GB VRAM — VDN-H3 linear attention plus hardware-adaptive execution planning, open source as a ComfyUI plugin
0:45

FreeVideo: MiniMax H3 video generation on a laptop with as little as 8GB VRAM — VDN-H3 linear attention plus hardware-adaptive execution planning, open source as a ComfyUI plugin

@HaochengXiUCB · 1.1k views · 2026-10-02
Seamless 30-second Kung Fu Panda from two MiniMax H3 clips: ComfyUI-H3-Motion-Context chains clips via latent slicing and audio continuation
0:29

Seamless 30-second Kung Fu Panda from two MiniMax H3 clips: ComfyUI-H3-Motion-Context chains clips via latent slicing and audio continuation

@eternityspring · 937 views · 2026-10-02
MiniMax H3ComfyUI
Microsoft MAI-Transcribe-2-Streaming tops Artificial Analysis: 2.5% WER with first partials ~100ms after speech — Japanese streamer demos it live: "the meeting-notes app era is over"
0:35

Microsoft MAI-Transcribe-2-Streaming tops Artificial Analysis: 2.5% WER with first partials ~100ms after speech — Japanese streamer demos it live: "the meeting-notes app era is over"

@studio_yebisu · 602 views · 2026-10-01
Speech-To-TextStreaming
"Welcome to the era of Superintelligence": Fable 5.5 apparently goes live — devs report auto-routing on claude.ai, and a Superman continuous-animation demo in multiple art styles
0:40

"Welcome to the era of Superintelligence": Fable 5.5 apparently goes live — devs report auto-routing on claude.ai, and a Superman continuous-animation demo in multiple art styles

@chetaslua · 798 views · 2026-10-01
LLMAnthropic
Tavus Griffin: the first model to pass the video Turing test — 48% of live callers thought it was human
1:49

Tavus Griffin: the first model to pass the video Turing test — 48% of live callers thought it was human

@tavus · 731 views · 2026-10-01
TavusGriffin
Qwen-Image-2.1-Fix: one LoRA repairs Qwen Image 2.1's common generation flaws without touching the base checkpoint
0:27

Qwen-Image-2.1-Fix: one LoRA repairs Qwen Image 2.1's common generation flaws without touching the base checkpoint

@Oluwaphilemon1 · 796 views · 2026-10-01
Image GenerationQwen Image 2.1
Google Vids opens free AI video creation: Veo 3.1 clips, AI avatars, voiceover, music and subtitle styles with just a Google account
0:50

Google Vids opens free AI video creation: Veo 3.1 clips, AI avatars, voiceover, music and subtitle styles with just a Google account

@Lonely__MH · 676 views · 2026-10-01
Voice InteractionGoogle Vids

LuxTTS: small-and-fast open voice cloning — 150x realtime on one GPU, native 48 kHz, 1 GB VRAM, fully local

@bkdgiffug · 693 views
Voice InteractionTTS
Ideogram 4.5 live on fal: ten consecutive edits with 94–99% of unasked pixels unchanged, typography rendered exactly in any language
0:16

Ideogram 4.5 live on fal: ten consecutive edits with 94–99% of unasked pixels unchanged, typography rendered exactly in any language

@fal · 639 views · 2026-09-30
Image GenerationIdeogram
Microsoft's open-source VibeVoice-ASR: one pass over a 60-minute meeting yields speakers, timestamps and content; 54k GitHub stars
0:22

Microsoft's open-source VibeVoice-ASR: one pass over a 60-minute meeting yields speakers, timestamps and content; 54k GitHub stars

@axichuhai · 788 views · 2026-09-30
Voice InteractionASR

As an Amazon Associate, we earn from qualifying purchases.