Genesis Prompt Assistant
A desktop prompt-generation tool powered by a local large language model, built on the Llama.cpp framework. It combines a template library with a locally running language model to help users generate high-quality prompts for AI image generation and video generation, supporting scenarios such as film and television, gaming, and e-commerce.
Timeline (last 90 days)
Origin Prompt Assistant is a desktop tool whose core positioning is to help users write prompts rather than generate images, consisting of a template library application combined with a locally running large language model.
The Origin Prompt Assistant drives local large language models based on Llama.cpp, and the stronger the model, the higher the quality of the generated prompts.
The minimum hardware requirement to run the Origin Prompt Assistant is 16 GB of RAM (32 GB for greater stability), and an Nvidia discrete GPU with 16 GB of VRAM can run a 27B quantized model.
The Origin Prompt Assistant adopts a portable, installation-free design — deleting three folders is equivalent to uninstalling it, as it writes nothing to the registry and installs no services.
The consistency anchor feature in the film and television prompt module keeps descriptions of the same character or scene word-for-word unchanged, ensuring consistency across shots.
The game prompt module supports HLSL shader generation and can produce function bodies for PBR materials and emissive effects, but only outputs positive prompts and does not generate negative prompts.
The platform content operations module can generate sponsored articles for seven platforms in one go: Douyin, Kuaishou, Xiaohongshu, Bilibili, Weibo, WeChat Official Accounts, and brand press releases.
The visual reverse-inference module can reverse-engineer reference images or videos into positive prompts, supporting JPG/PNG images and MP4/MOV/MKV videos (up to 500 MB), with the entire process handled by a local model so that images never leave the user's machine.
The Origin Prompt Assistant is permanently open-source and free; its developer is the Bilibili UP creator "光追樱花," who only has an account on Bilibili.
All Facts (9)
Origin Prompt Assistant is a desktop tool whose core positioning is to help users write prompts rather than generate images, consisting of a template library application combined with a locally running large language model.
50%UnverifiedThe Origin Prompt Assistant drives local large language models based on Llama.cpp, and the stronger the model, the higher the quality of the generated prompts.
50%UnverifiedThe minimum hardware requirement to run the Origin Prompt Assistant is 16 GB of RAM (32 GB for greater stability), and an Nvidia discrete GPU with 16 GB of VRAM can run a 27B quantized model.
50%UnverifiedThe Origin Prompt Assistant adopts a portable, installation-free design — deleting three folders is equivalent to uninstalling it, as it writes nothing to the registry and installs no services.
50%UnverifiedThe consistency anchor feature in the film and television prompt module keeps descriptions of the same character or scene word-for-word unchanged, ensuring consistency across shots.
50%UnverifiedThe game prompt module supports HLSL shader generation and can produce function bodies for PBR materials and emissive effects, but only outputs positive prompts and does not generate negative prompts.
50%UnverifiedThe platform content operations module can generate sponsored articles for seven platforms in one go: Douyin, Kuaishou, Xiaohongshu, Bilibili, Weibo, WeChat Official Accounts, and brand press releases.
50%UnverifiedThe visual reverse-inference module can reverse-engineer reference images or videos into positive prompts, supporting JPG/PNG images and MP4/MOV/MKV videos (up to 500 MB), with the entire process handled by a local model so that images never leave the user's machine.
50%UnverifiedThe Origin Prompt Assistant is permanently open-source and free; its developer is the Bilibili UP creator "光追樱花," who only has an account on Bilibili.
50%