Sebastian Kamph

Showing you AI tools before they're mainstream.

AI Educator | 10M+ Views Youtube | Art Director

[Hasan Toor @hasantoxr]

BREAKING: ComfyUI just became 100x easier.

Floyo lets you run ANY open-source workflow in your browser with zero setup.

No installs. No configs. No GPU required.

Here's how:↓

[Sebastian Kamph @SebastianKamph]

@JustinHackney33 Best person for the job!

[Genspark @genspark_ai]

Genspark AI Image upgraded!

Introducing: Draw to edit ✨

Simply draw on the image where you want changes → Describe what you want → Done!

[Genspark @genspark_ai]

Genspark AI Image upgraded!

Introducing: Reference image ✨

Mix A + B + C... and see what magic happens!

[Genspark @genspark_ai]

Genspark AI Image upgraded!

Introducing: Mark to Edit ✨

Click to mark what you want to change → describe the edit → Done!

[Genspark @genspark_ai]

Everyone has a story to tell. Now you can actually show it.

🎊 Our upgraded AI Image works like an agent!

One prompt, and it creates your comic step by step:
• Design your characters
• Follow your plot
• Generate an entire comic series

What story have you been waiting to tell?

[NVIDIA RTX Spark @NVIDIARTXSpark]

Ready to generate your own videos with simple text prompts? 🎬

Learn how to use @ComfyUI and the @ltx_model LTX-2 optimized model on your RTX AI PC with this educational guide linked below.

[Sebastian Kamph @SebastianKamph]

Got to love new models being released open source!

[LTX @ltx_model]

AI video shouldn’t be locked behind closed systems.

We’re releasing LTX-2 as a truly open-source AI video model.

Here’s @ZeevFarbman (CEO & Co-Founder, Lightricks) on why openness, local access, and community matter.

🧵

[Chroma Awards @chromaawards]

We are proud to announce our finalist jury for the Experimental & Open Music Videos Category of the @chromaawards !

We are joined by Julien Durand , @SebastianKamph , @PaigePiskin and @hugo_humain , who’ll be bringing their industry and creative experience to select our winners.

Submit before Nov 17 at https://t.co/fdGKF3MjGP

[Sebastian Kamph @SebastianKamph]

@robrombach Where's my access @robrombach ? Please and thank you.

[Sebastian Kamph @SebastianKamph]

The FASTEST AI Video model just got better. @LTXStudio just dropped a new version of LTXV (0.9.5).
🎬 Keyframes! (set start & end frames)
🖼️ Higher resolution & longer sequences
💰 Commercial licensing (hello, real-world projects 👀)
And yes, you can try it in ComfyUI right now 🔥

[Sebastian Kamph @SebastianKamph]

Don't have a cow, man! Pika 2.2 just launched! 📷 1080p, keyframes, buttery smooth, crazy details and humans that don’t look cursed?? Check it out: https://t.co/4birnAykSf

[Sebastian Kamph @SebastianKamph]

Who's winning the gen AI video race?
Few thought Chinese Alibaba would stand a chance, but they keep dropping awesome releases day after day. The newly released video model ⚡Wanx⚡ will be 🔥 OPEN SOURCE 🔥during the second half of 2025.

🚀 Text-to-video faster than playback
⚡ 1-min 1080p video in just 15s
🥈 Currently #2 on VBench leaderboards

[Sebastian Kamph @SebastianKamph]

Want to get your characters to MOVE with AI? The NEW AnimateAnyone2 is simply amazing.
🖼️ 1 input image
📽️ 1 driving video
🪄 = Magic.

[Sebastian Kamph @SebastianKamph]

SkyworkAI just dropped their new AI Video Model SkyReels V1 - Image2Video.
🔥Open-Source
🙃Advanced Facial Animation
💡Cinematic Lighting and Aesthetics
✅Available in ComfyUI

[Sebastian Kamph @SebastianKamph]

🌟NEW OPEN SOURCE AI VIDEO MODEL🌟
StepFun just dropped their HUGE 30b Step-Video Text2Video open source model.

🔥Deep Compression VAE
🔥Up to 204 frames of video
🔥Open Source and available for download

It requires a 🤖 WHOPPING 80GB 🤖 of vram now, but surely optimizations like with Hunyuan will be made quickly.