A Midjourney and GPT Creative Workflow
gizakdag · x · 2026-07-17
The poster shared their recent creative workflow: first using Midjourney to generate a character, and then using GPT to make the character "look more like a real person." This is a classic multimodal relay workflow: starting with visual setup and then using an LLM to refine and photorealize the output, making it ideal for character design, concept art, and content creation.
Related event: Midjourney and GPT Workflow for Photorealistic Images(2 posts)→
More from Multimodal
- LTX-2.3 Foley LoRA turns silent video into generated sound effects — linoy_tsaban · 2026-07-21
- A prompt for Magnific and GPT-2 produced a dense surreal comic about unlived lives — CurieuxExplorer · 2026-07-21
- Seedance 2.0 prompt aims for MiniDV-style footage with handheld imperfections — eyishazyer · 2026-07-21
- AI-made “cat mode” stunt turns a skateboard clip into a surreal landing demo — taherdhanera · 2026-07-21
- OCT-Bench sets 10,076 questions to test whether multimodal models really understand retinal scans — Baochen Fu · 2026-07-21
- LTX-2.3 face-and-voice LoRA training can work on 12GB VRAM with heavy tradeoffs — __alpha_____ · 2026-07-21