GoJun AI Daily

English

简体中文

English

简体中文

Appearance

Spend 1 minute every day to get selected cutting-edge AI information.

The content covers but is not limited to cutting-edge AI news, AI tools, AI painting, open source projects, and learning tutorials, etc.

Follow AI Daily to stay up-to-date with AI trends, and we hope it helps you. Important information will be posted separately for detailed introduction.

Below is the latest AI information for July 22.

AI Painting ​

1. Easily achieve image stylization transfer with B-LoRA.

You can separate style and content of images to achieve high-quality mixing and adjustment of style and content, as well as exchange style and content between two stylized images.

Trained B-LoRAs can be used as independent components for various image stylization tasks, including image style transfer, text-based image stylization, consistent style generation, etc.

Detailed introduction: https://b-lora.github.io/B-LoRA/

Those interested can try using the following ComfyUI workflow.

GitHub: https://github.com/liusida/ComfyUI-B-LoRA

Figure

2. Tencent's PhotoMaker has been updated to the second version, with better fidelity and controllability!

No need to train LoRA, just upload a few photos of a person to generate multiple styles of realistic human images.

Compared to v1, v2 has higher fidelity and supports the use of T2I-Adapter to improve controllability of the images.

GitHub: https://github.com/TencentARC/PhotoMaker

Online experience: https://huggingface.co/spaces/TencentARC/PhotoMaker-V2

image-20240722213822142

Open Source Projects ​

1. A free open-source tool AudioNotes that quickly converts audio and video into structured notes.

Built on FunASR and Qwen2, it can quickly extract audio and video content and organize it into structured Markdown notes using large model capabilities, making it easy to read quickly.

GitHub: https://github.com/harry0703/AudioNotes

The tool supports using local models with Ollama and provides a Docker quick deployment method.

image

2. A powerful interactive command-line (CLI) open-source tool Claude Engineer.

It integrates the Claude 3.5 model into the command line terminal, utilizing the model's multimodal capabilities combined with file system operations, network search, and more, to assist in various software development tasks.

GitHub: https://github.com/Doriandarko/claude-engineer

Key features include:

  • Provides an interactive chat interface with Claude;
  • Comprehensive file system, capable of creating folders, reading and writing files, etc.;
  • Can perform network searches to get the latest information;
  • Assists developers in intelligent management and project creation;
  • Offers intelligent code analysis and modification suggestions;
  • Supports dragging and analyzing images directly in the terminal;
  • Can autonomously complete tasks, supporting iterative tracking and management.

Overall, it is a powerful software development assistance tool that we believe will improve our development efficiency and code quality.

image-20240722163243017

3. Discovered an open-source alternative list OpenAlternative on GitHub that collects mainstream software alternatives.

It collects various well-known mainstream software alternatives, introduces the pros and cons of the tools in detail, and lists more similar open-source alternatives.

For example, for Google Analytics, it lists open-source alternatives like Umami/Matomo/Plausible/OpenPanel.

GitHub: https://github.com/piotrkulpinski/openalternative

It also provides an online website for category division, making it easy for everyone to search, filter, and find the software they need.

image-20240722172554753