Month: November 2025

Tip word website Prompthero https://prompthero.com I saw it recommended on a YouTube channel while learning AI animation. The website has many AI prompts, such as “Stable Diffusion”. Select an image to see the corresponding hints and reverse hints. Copy the hints into your AI editor for rendering. For example, you can use the same prompts…

AnimateDiff Introduction GitHub address: https://github.com/guoyww/AnimateDiff It can be used with Stable Diffusion web UI to generate animations. For example, a 2-second, 16-frame animation (8 frames per second). The image below shows the result, but the actual generated animation is not as good as the ones online. I don’t know if it’s a problem with my…

Let’s talk about AI deployment LatentSync 1.5 has a one-click Windows executable. I tested it in an internet cafe with a GTX 4070 graphics card and my own P06-100 6GB SSD, and it worked perfectly, with relatively good performance. MuseTalk is a new AI recommended by XAI and ChatGPT, and is said to be better…

Prerequisites First, install Stable Diffusion WebUI.Then, open GitHub: https://github.com/Mikubill/sd-webui-controlnet.Click the Extensions tab in Stable Diffusion WebUI, select “Install from URL,” enter the GitHub URL, and click “Install. “After installation, it’s recommended to restart Stable Diffusion WebUI.Installing the ControlNet extension alone isn’t enough; you also need to download the corresponding model.Model address:https://huggingface.co/lllyasviel/ControlNet-v1-1/tree/main. After downloading the model,…

github https://github.com/openai/whisper Tips If you’re doing self-media or video creation, you absolutely must try this free, open-source AI for speech-to-text conversion. Before it came out, a 10-minute speech-to-text conversion cost me about $1 in cloud service fees. And that 10 minutes had to be error-free, uploaded to the cloud, and the text was subject to…

GitHub address https://github.com/AUTOMATIC1111/stable-diffusion-webui webui webui tips For me, using it as a YouTube cover image is a bit of a stretch. However, it’s quite good as illustrations for WordPress blog posts. With a suitable graphics card, it can work continuously, generating dozens or even hundreds of beautiful landscape, hand-drawn, and technological images overnight. If you…

Project Features Voice timbre cloning and voice style transfer This is not TTS text-to-speech, but rather directly converting songs or speech into your own voice (unrelated to the text content). You can train your own voice model. It can be used as a digital human for YouTube videos or for other video creation, supporting multilingual…