GPT Image 2 prompt aims to lock character identity and outfit consistency in ChatGPT
eyishazyer · x · 2026-07-23
A prompt for GPT Image 2 on ChatGPT focuses on preserving a character’s identity when generating new artwork.
It instructs the model to treat the uploaded reference as the strict source of truth for face, proportions, skin tone, hairstyle, accessories, outfit, and overall vibe, while avoiding any hardcoded traits. The post highlights a stylized “reality meets doodle chaos” look built on strong character consistency.
Related event: GPT Image 2 Prompt: Realistic Portrait with Graffiti Shadow(3 posts)→
More from Multimodal
- Open-source node-based LoRA trainer puts captioning, checkpoints and VRAM stats in one graph — ashishsanu · 2026-07-23
- TERRA-129 debuts as an AI-animated sci-fi episode credited to Matygoo — Matygoo1 · 2026-07-23
- Alibaba launches Qwen-Audio-3.0-TTS with 16 languages and 3-minute one-pass audio — Alibaba_Qwen · 2026-07-23
- Kling AI is said to handle close-up facial expressions better — burny_tech · 2026-07-23
- FameGrid Krea 2 aims to generate more realistic social-media-style images — UltraMuseArt · 2026-07-23
- A reusable ChatGPT image prompt for a realistic portrait plus doodle-shadow twin — SimplyAnnisa · 2026-07-23