How to use and evaluate “Title: Realistic Bedroom Mirror Selfie in Black Mini Dress”
This selfie 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 realistic bedroom with an unmade white bed, rumpled duvet, a brass arched floor lamp turned off, a power cable trailing naturally across the floor, lightly scuffed dusty wooden flooring, and a large mirror with faint dust specks and a small fingerprint smear
- Time
- late afternoon
- Mood
- candid, intimate, realistic, unfiltered, high-detail, natural, confident
Visual treatment
- Photography
- hyper-photorealistic unedited iPhone mirror selfie photography with realistic phone processing, no beauty filters, no airbrushing, visible real-life imperfections, skin pores, subtle texture, faint cellulite dimples, tiny goosebumps, soft pink pressure flush on cheeks and knees, and freckles over…
- Camera
- iPhone 16 Pro, 1x lens, 48MP, f/1.78, RAW HEIF, unedited capture, slight barrel distortion, realistic mirror-reflection perspective
- Lighting
- natural late-afternoon window light coming from the left, soft shadows, slight warm cast, realistic contrast, minor lens flare on the mirror edge, subtle purple fringing on high-contrast edges
Composition and wardrobe
- People Count Label
- one uploaded reference woman
- People Count
- single
- Reference Instruction
- Use one uploaded reference woman as the main subject. Preserve her face and hair identity with extremely high consistency while adapting them naturally to the requested mirror selfie, pose, lighting, and perspective.
- Framing
- full-body vertical 9:16 mirror selfie, iPhone 1x perspective, realistic 3D depth, dynamic side-profile flamingo stance
- Wardrobe · Dress
- extremely tight black strapless tube mini dress with subtle stretch lines and a slight top-edge roll
- Wardrobe · Footwear
- black strappy high-heel sandals with thin ankle ties
- Wardrobe · Phone
- red matte phone case held in the left hand at eye level, with fingerprint smudges and a tiny scratch near the camera bump; the phone reflection shows low battery and notifications
Recommended workflow
- 01
Prepare the input
Choose reference images you have permission to use. For Title: Realistic Bedroom Mirror Selfie in Black Mini Dress, 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 Midjourney. 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
Midjourney
Translate the core fields into concise natural language and add current version-specific reference or aspect controls in Midjourney itself.
Gemini
Provide the JSON with clearly labeled reference images. Restate any ignored constraint in plain language without duplicating the whole prompt.
ChatGPT Image
Keep the JSON structure, attach references in the same conversation, and use follow-up edits for one local correction at a time.
Stable Diffusion
Move observable failures into the interface’s negative prompt field and document the checkpoint, sampler, guidance, and resolution used.
Flux
Preserve the semantic hierarchy but favor coherent natural language; weighting and negative-prompt behavior depend on the host workflow.
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
- The woman's hair must match the uploaded reference image in color, texture, roots, frizz, length, density, direction, and styling characteristics, while still behaving naturally in the new pose and lighting.
- Skin should include real pores, freckles over the nose and shoulders, faint cellulite dimples, tiny goosebumps, and soft pink pressure flush on cheeks and knees.
- The mirror should show faint dust specks and a small fingerprint smear.
- The wooden floor should look lightly scuffed and dusty.
- The image should include realistic iPhone artifacts: minor lens flare on the mirror edge, subtle purple fringing on high-contrast edges, and slight barrel distortion.
- No beauty filters, no airbrushing, no plastic skin, no overly polished editorial retouching.
- Output should be ultra high resolution 4K, vertical 9:16.
Failures to check before publishing
- changed face
- changed hair
- altered hair color
- wrong hair texture
- altered bone structure
- directly copied reference pose
- directly copied reference gaze
Why the editable controls matter
Gender
Required identity direction for the reference subject.
People count
Default is a single uploaded reference person.
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.