How to use and evaluate “A Sofa Selfie Together Before Going Out”
This couple prompt is designed as an editable starting point, not a guaranteed one-click result. The notes below translate its JSON into a readable visual plan, identify the controls that matter, and show how to diagnose a weak generation without simply adding more text.
Prompt-specific blueprint
Scene and atmosphere
- Location
- A normal apartment living room with a plain grey sofa, a cushion slightly out of position, the edge of a bookshelf and a plug socket low on a pale wall. Include the unremarkable room corner without styling it.
- Time
- Late afternoon indoors before going out.
- Mood
- Familiar and relaxed; an ordinary photo kept in a phone gallery.
Visual treatment
- Photography
- A normal unedited photograph from a personal phone camera roll. Mild everyday phone sharpening and compression, modest dynamic range, visible ordinary surroundings. Not a professional image, not deliberately styled to look candid, and not made artificially ugly or grainy.
- Camera
- Ordinary smartphone FRONT camera, arm-length wide selfie perspective. The near forearm is visible only at the lower edge.
- Lighting
- Mixed leftover window light and a normal warm room lamp; slight uneven white balance and modest sensor noise in the background, no flattering studio fill.
- Color Mood
- Ordinary default phone colour processing and believable white balance; no coordinated colour palette or cinematic grade.
- Depth Of Field
- Keep background details reasonably clear as a normal small-sensor phone does; no artificial portrait blur or creamy lens bokeh.
Composition and wardrobe
- People Count Label
- two uploaded reference people as a couple
- People Count
- couple
- Reference Instruction
- Use image 1 for A and image 2 for B. Keep both distinct identities while fitting the normal phone snapshot.
- Shot Type
- 3:4 vertical close selfie, both heads fit a little tightly, shoulders and top halves of torsos only; one sofa cushion is clipped awkwardly.
- Wardrobe · Clothing
- Individual A wears a plain oatmeal knit top with blue jeans. Individual B wears a dark charcoal cotton tee and a simple open denim shirt. Clothes look comfortably worn and are not a matching couple set.
- Wardrobe · Pose
- Seated close on the sofa, A holds the phone at arm length; B leans slightly inward to fit. Heads touch lightly at the hair while both faces remain clearly separate. Do not add intertwined hands.
- Wardrobe · Hair
- Reference-accurate hair, ordinary flyaways and slight natural mess, not salon styling.
Recommended workflow
- 01
Prepare the input
Choose reference images you have permission to use. For A Sofa Selfie Together Before Going Out, prioritize a clear subject and avoid unrelated people or private details in the frame.
- 02
Lock the visual plan
Confirm subject count, framing, scene, and lighting before adding finishing language. Resolve conflicts such as close-up versus full-body composition.
- 03
Adapt for one model
Start with ChatGPT Image. Keep a baseline generation and document the exact model version, references, aspect ratio, and visible settings.
- 04
Revise from evidence
Name the visible failure, change one instruction block, and compare it against the baseline. Keep only revisions that improve the intended criterion.
Model adaptation notes
ChatGPT Image
Keep the JSON structure, attach references in the same conversation, and use follow-up edits for one local correction at a time.
A compatibility label means the visual intent can be adapted; it does not promise identical output across providers, versions, or settings.
Prompt-specific quality checklist
- Capture one believable photo with an ordinary reason for taking it: a selfie or asking someone to take a keepsake.
- Let the phone framing remain mildly imperfect; do not polish composition, lighting, clothing or location into a campaign.
- Anatomy and face identity must stay sound; imperfection comes from capture conditions, not from distorted bodies.
Failures to check before publishing
- advertising photograph
- fashion campaign
- editorial photography
- cinematic film still
- professional portrait lighting
- studio fill light
- reflector lighting
Why the editable controls matter
Gender
Required identity direction for the reference subject.
People count
Default is a single uploaded reference person.
Lighting
Changes Prompt.Style.Lighting without requiring a full prompt rewrite.
Mood
Changes Prompt.Scene.Mood without requiring a full prompt rewrite.
Color palette
Changes Prompt.Style.Color Mood without requiring a full prompt rewrite.
Shot size
Changes Prompt.Composition.Shot Type without requiring a full prompt rewrite.
Identity or subject drift
Reduce competing style language, improve the reference, and separate stable traits from pose, gaze, and expression.
Composition breaks
Check whether crop, shot distance, aspect ratio, subject count, and required objects can all be satisfied in one frame.
Artificial lighting or texture
Name a motivated light source and believable material behavior before adding grain, grading, sharpness, or resolution terms.
@cankirkgoz
Comments
Share the result you got, attach an image, and reply to other people's results.
You need to sign in to comment.