dwzhu-pku/PaperBanana
- Source
- GitHub
- First trending
- Category
- Media
- GitHub stars
- 7,093
- Main language
- Python
This page introduces an external open-source repository. It is not an HDATF product.
What it does
A tool that generates illustrations for academic papers with a vision-language model and an image generation model, offering a Streamlit interface for choosing models. It is a fork of Google Research's PaperVizAgent.
How it helps ATF
Could be a reference for LabChin when a final research report needs figures. Its separate choice of a main model and an image model is also worth comparing.
License
Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.
More in this category
- jamiepine/voicebox
A local AI voice studio that clones voices from short audio samples, generates speech with several TTS engines, and dictates into any text field with a hotkey. It can also give MCP-aware AI agents a voice. - ace-step/ACE-Step-1.5
ACE-Step 1.5 is an open-source music generation model that runs locally on Mac, AMD, Intel and CUDA devices. Users can train a LoRA from a few songs to capture their own style. - waooAI/waoowaoo
An AI workspace for making images and videos. Users develop a brief with an assistant, upload references, generate and refine results on a canvas, and keep the original when a result is refined into a new version. - QwenLM/Qwen3-TTS
An open-source series of text-to-speech models from the Qwen team at Alibaba Cloud. It supports streaming speech generation, free-form voice design, voice cloning and voice control through natural language. - nikopueringer/CorridorKey
CorridorKey is a neural network for green screen keying. From a raw green screen frame it predicts the foreground color and a clean linear alpha channel for each pixel, including semi-transparent edges and motion blur.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.