visual-prompt-forge

Generate model-specific prompts from shots.json. Outputs copy-paste-ready prompts for stills (Midjourney, Flux, Ideogram, GPT Image, Nano Banana, Seedream) and motion video (Kling, Veo, Seedance, Hailuo). Also runs a revision mode that reads a critique.json and re-emits prompts for only the failed shots, closing the QA loop. Use when the user asks for image or video prompts, mentions any of those generators, wants AI-generated frames for a storyboard, or hands over shots.json. The prompt half of the pipeline. Composes with storyboard-architect upstream, visual-asset-critic downstream.

适合你，如果需要为多个AI图像/视频模型批量生成提示词。