1
Midjourney V8.2
Midjourney
Fast, cinematic frames with a consistent look.
Unmatched art direction through style references.
- Cost
- Own platform / subscription
- Where
- Midjourney's own site · check in app: KREA
- Rights
- Web‑trained.
- Watch out
- Won't follow a brief literally.
How to ask it[subject] [doing what], [medium/style], [lighting], [composition] --ar 16:9 --stylize <0-1000>Keep it under about forty words. This model rewards concision and ignores over‑specification.
Order matters: subject, then medium and style, then lighting, then composition.
Open Midjourney V8.2 in Call Sheet →
2
Nano Banana Pro / Imagen (Google)
Google
Reuse character refs so boards stay on‑model.
Precision + real‑world knowledge.
- Cost
- Mid (Pro). A faster/cheaper tier exists
- Where
- Magnific, Higgsfield, KREA, OpenArt, Runway
- Rights
- Google terms, plus a SynthID watermark.
- Watch out
- Less 'art‑directed' personality than Midjourney out of the box.
How to ask it[Subject] + [action] + [location] + [composition/shot] + [style & lighting]. Edits: [what to change] + [what to keep] + [refs]Write full descriptive sentences, not keyword lists.
Put any on‑image text inside double quotes, spelled exactly as it should appear.
Open Nano Banana Pro / Imagen (Google) in Call Sheet →
3
GPT Image 2
OpenAI
Iterate a panel conversationally ('same shot, low angle').
Conversational, instruction‑driven editing with excellent text.
- Cost
- Mid. Slower
- Where
- Magnific, Higgsfield, KREA, OpenArt, Runway
- Rights
- Check terms.
- Watch out
- Has a recognizable 'look'.
How to ask it[instruction] + [exact text in "quotes"] + [what to keep unchanged] + [style]Write it as an instruction to a person, in plain sentences.
Quote any text that should appear in the image.
Open GPT Image 2 in Call Sheet →