{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/972a93bf423246cb9404772fc73e3638\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/972a93bf423246cb9404772fc73e3638-c94f8a0bc61aa270.gif","duration":388.16,"title":"Master Character Consistency With Reference Sheets","description":"This Loom explains a workflow to maintain consistent character identity in ChatGPT image generation using visual references. It recommends creating a 35-year-old Italian man character named Marco Romano as a high-quality 4K master character with dark brown hair, thick eyebrows, brown eyes, a short beard, an athletic build, and specific clothing. The process then adds an emotion sheet and a multi-angle character reference sheet to prevent identity drift from changing facial expressions and viewpoints. For future story scenes, it emphasizes using the same defining features and always uploading the master character, emotion sheet, and reference sheet as the source of truth."}