TechPractice1's profile picture. Democratize AI! Youtube channel @ https://www.youtube.com/@tech-practice9805

TechPractice

@TechPractice1

Democratize AI! Youtube channel @ https://www.youtube.com/@tech-practice9805

#Wan2.2 is amazing. Try this prompt at agireact.com/wan-t2v : "a young white 26 years old blonde woman with High ponytail hair, leaning forward, getting very close to the camera." Then make adjustments. It may surprise you. #AIart #aivideo


Tried to generate it using #Wan2.2

やばいプロンプト発見した... #Sora2 #AIart



Tested a prompt, Sora2 and Veo3 can both generate them. Although Sora2 have many ''Something went wrong" errors but I don't think it's censored. If interested, follow and DM for prompt.


transformers version 4.57 breaks diffusers. Quick fix: downgrade it using pip install -U transformers==4.56


Grok Imagine v0.9 video is releases. Can generate video from images and also generate audio. #Grok #GrokImagine


9s video cost $0.9

#Sora2 api is available, pricing:

TechPractice1's tweet image. #Sora2 api is available, pricing:


#Sora2 api is available, pricing:

TechPractice1's tweet image. #Sora2 api is available, pricing:

RTX 3090 vs 4090 vs 5090 GPU speed test: running Wan2.2-Animate medium.com/p/rtx-3090-vs-…


Openai's #Sora2 must be trained on tons of Chinese tiktok videos 😄


Sora2 - Sam Altman becomes a teacher #Sora2 #altman


China's Z.ai releases GLM-4.6. Can be used in many coding tools such as Claude code.

TechPractice1's tweet image. China's Z.ai releases GLM-4.6. Can be used in many coding tools such as Claude code.

Thank you!

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely…



🔥🔥

🔥 Qwen-Image-Edit-2509 IS LIVE — and it’s a GAME CHANGER. 🔥 We didn’t just upgrade it. We rebuilt it for creators, designers, and AI tinkerers who demand pixel-perfect control. ✅ Multi-Image Editing? YES. Drag in “person + product” or “person + scene” — it blends them like…

Alibaba_Qwen's tweet image. 🔥 Qwen-Image-Edit-2509 IS LIVE — and it’s a GAME CHANGER. 🔥

We didn’t just upgrade it. We rebuilt it for creators, designers, and AI tinkerers who demand pixel-perfect control.

✅ Multi-Image Editing? YES.
Drag in “person + product” or “person + scene” — it blends them like…


This one is funny😂 generated using #Wan 2.2 Animate


Loading...

Something went wrong.


Something went wrong.