GitHub Trending repo Jul 26

quantum32043/LoRACaptioner: A local web tool for annotating image datasets used for training LoRA models (Stable Diffusion / SDXL / Flux). Works directly with the canonical kohya_ss / ai-toolkit format: a folder where each image has a same-named .txt file with its caption next to it.

A local web tool for annotating image datasets used for training LoRA models (Stable Diffusion / SDXL / Flux). Works directly with the canonical kohya_ss / ai-toolkit format: a fol...

GitHub Trending repo Jul 26

luozhilzh/image-prompt-reverse: **图像反推提示词工程师 Skill** —— 反推一张图生成专业级 AI 图像提示词(Midjourney/DALL-E/Stable Diffusion/Flux),独家叠加惊艳增强层把还原同款升级为电影感/胶片感/商业大片。覆盖通用/字体Logo/风景/摄影人像/插画/产品/美食/建筑室内/时尚/汽车等场景,输出还原版+惊艳版+3变体+平台适配版。

**图像反推提示词工程师 Skill** —— 反推一张图生成专业级 AI 图像提示词(Midjourney/DALL-E/Stable Diffusion/Flux),独家叠加惊艳增强层把还原同款升级为电影感/胶片感/商业大片。覆盖通用/字体Logo/风景/摄影人像/插画/产品/美食/建筑室内/时尚/汽车等场景,输出还原版+惊艳版+3变体+平台适配版。