Midjourney's new Draft Mode is fantastic for character creation.
It generates 24 low-resolution variations in a single run, making it incredibly easy to explore different character directions and quickly find designs you like.
Once you find a promising result, you can use those images directly in GPT Image 2 to generate character sheets.
You can also fix generation errors, modify outfits and accessories and change the visual medium or art style.
GPT Image 2 Character Sheet Prompt:
Create an artistic 16:9 CHARACTER IDENTITY BOARD.
Use Image A as the subject and the visual medium. Name: Clara. Fix headphones. (just change this line as your needs.)
Soft off-white background. No environment, no logo, no watermark.
DESIGN DIRECTION:
Do not create a standard character reference sheet.
Create a cinematic identity board that feels like a high-end animation studio character study mixed with an artbook layout.
The layout should be asymmetrical, elegant and visually memorable.
Use large empty space, varied image scale and intentional imbalance.
Avoid grids, blueprint design, catalog layout and repetitive turnaround presentation.
IMPORTANT LAYOUT RULE:
Do not overlap any character images.
Every view must have clear separation and breathing room.
Keep all bodies, portraits, silhouettes and detail studies visually distinct.
No cropped faces, no hidden limbs, no stacked figures, no merged poses.
MAIN COMPOSITION:
Place one large hero full-body view slightly off-center as the visual anchor.
Around it, arrange smaller supporting studies with clean spacing:
neutral full-body view, back view, profile view, seated pose, leaning pose, crouching pose, top-down body angle, low-angle body angle, expressive portrait studies.
Each view should feel like a separate clean character study, not a frame from one scene.
IDENTITY LOCK:
Preserve strict identity consistency across all views:
same face, same facial proportions, same hairstyle, same outfit, same body proportions, same posture language, same visual personality.
USEFUL REFERENCE DETAILS:
Make the character readable for future image and video generation:
clear face shape, clear hair silhouette, clear outfit silhouette, clear body shape, clear hands, clear posture, clear expression range.
ARTISTIC SECTIONS:
Include a small silhouette study area with 2-3 simplified black character silhouettes.
Include a small expression study area with subtle emotional variations.
Include a small detail study area showing key visual features of the face, hair and outfit.
TEXT DESIGN:
Add one stylish CHARACTER ID block.
Keep it minimal, bold and art-directed.
Use only:
NAME
ROLE
CORE MOOD
VISUAL SIGNATURE
Use small handwritten-style labels only where helpful.
Subtle editorial arrows and annotation marks are allowed, but keep them minimal and elegant.
STYLE:
minimal, cinematic, premium, artbook-like, clean, expressive, useful for production.
The final image should feel like an artistic character identity board designed to help an AI model understand the character’s face, silhouette, outfit, posture and emotional range.
How do you turn a scene idea into a Prompt?
All you need to do is roughly describe what's in your head to an LLM. It doesn't have to be perfect or highly detailed. Once it understands the core idea, it can help turn it into a well-structured prompt.
In my case, I use a custom skill file that I built myself. After I provide the idea, it generates both a storyboard and video prompts for me. I then review the outputs and refine them through iteration, giving feedback like "make this shot wider," "change this action," or "move the camera here."
After a few rounds of adjustments, I usually arrive at the final result. The process is much closer to directing than writing a perfect prompt from scratch.
The Idea: Two characters face each other. Serenity fights like a Wing Chun master. She unleashes a rapid barrage of punches into Ruk's abdomen. The fight should feel highly energetic and sakuga-driven, with exaggerated action beats and dynamic choreography. Use 14 panels. The final attack should show Serenity launching high into the sky, then diving straight down at extreme speed. She lands with both feet on Ruk's head, driving him deep into the ground and burying him on impact. All other scenes should be equally creative and visually inventive. Emphasize fast pacing, flash cuts, burst cuts, sudden perspective changes, dramatic impact moments, and imaginative camera angles. Use aggressive screen direction, strong momentum shifts, dynamic framing, and escalating choreography to create a thrilling, high-energy martial arts sequence.
This is the final video, you can check the prompts in the replies.
Used tools: Midjourney, Codex, GPT Image 2, Seedance 2.0, Suno, Capcut
Tekko was an experimental enhanced organic unit originally engineered for off world Asteroid Mining. The Pilot Program was cancelled due to public outcry and “Tekko” was given his freedom. His Neural AI Enhancements gave him a genius level understanding of Quantum Mechanics and invent the first Quantum “Racer.” #DreaminaCPP #DreaminaAI #DreamUpDreamina #DreaminaSeedance2 #CharacterConsistency #AIVideo #AICreations #AIFilmmaking #sciencefiction #quantumracers #scifi
#adventure #anime #aishorts #studioofworlds #worldbuilding @dreamina_ai
@PJaccetturo After watching you on yout live stream the other night I ran across this and that it migh be useful in you workflow. https://t.co/S92NYHXMCI
New style creator --sref 8323996627 --stylize 1000
tested.
Prompt below. It's so nice we have Seedance 2.0 Mini now so we can test these things without worrying too much about credits.