8 full-body views. Neutral stance. Flat bare feet. Choose an angle to open or download.
000° Front Download045° Front three-quarter, facing left Download090° Profile, facing left Download135° Rear three-quarter, facing left Download180° Back Download225° Rear three-quarter, facing right Download270° Profile, facing right Download315° Front three-quarter, facing right Download
Angle convention and limits
Nominal turn order: front, left-facing profile, rear, right-facing profile, front. At 090 degrees the nose points image left; at 270 degrees it points image right. Left and right describe image-facing direction, not measured anatomical sides.
Nominal 45-degree directions for generated reference views, not calibrated angular or body measurements. Target pitch 0° and roll 0°. The active barefoot anchor is authoritative. Side, rear and hidden geometry are inferred.
Attach the active anchor and the nearest matching angle. A back view establishes the generated rear silhouette, not unseen facial details.
Expression support. A speaking still is not a complete speech or lip-sync model.
What stays fixed
Identity
Preserve the anchor’s face and body. Change the scene and wardrobe around them.
Kayla’s fixed identity features
Feature
Keep consistent
Face
Oval face, rounded cheeks, softly tapered jaw, short rounded chin; retain source proportions and natural asymmetry.
Eyes
Almond-shaped brown eyes; retain source spacing, eyelids and outer-corner shape.
Brows
Full, softly arched dark-brown brows; retain thickness and placement.
Nose
Relatively narrow, straight-looking bridge and softly rounded tip; defer to source proportions.
Lips
Rose-pink lips, defined upper contour and fuller lower lip; retain mouth width.
Skin
Warm tan as rendered in the source, with natural texture; source lighting is not calibrated skin color.
Hair
Long, center-parted chestnut-brown hair with darker roots, warm caramel highlights and loose waves; retain hairline and highlight placement.
Body
Preserve the approved anchor's shoulder width, torso length, waist-to-hip proportions, bust proportions, arm and leg lengths, and natural asymmetry. Do not slim, enlarge or lengthen body features.
Reference_outfit
Opaque matte rose-pink sleeveless scoop-neck unitard, fitted to the ankles, with bare feet, no footwear, and original wrist jewelry. Keep this outfit consistent across the reference turn.
Current anchor · neutral barefoot revision
What this version establishes
The fictional age direction is mid-20s. Height, exact measurements, ethnicity and voice are unspecified. The fitted-unitard anchor establishes the current designed body proportions. Expressions, additional poses and motion need their own references.
Skin color is described as rendered in the source. The reference lighting is not a calibrated color measurement.
Start every shot here
Still & motion prompts
Build and review the scene first frame with the identity prompt. For image-to-video, describe movement around that accepted frame.
Show Kayla, fictional adult model 001. Use the attached neutral barefoot anchor and nearest face or body reference. Preserve the established facial proportions, brown almond-shaped eyes, full arched brown brows, softly rounded nose tip, rose-pink lips, warm tan skin, natural texture, chestnut hair, caramel highlights and center part. Preserve shoulder width, torso length, bust proportions, waist-to-hip proportions, limb lengths and natural asymmetry. For body references use the fitted pink unitard with bare feet, no footwear, both feet flat, relaxed neutral stance and arms slightly away from the torso. Height target: provisional fictional 170 cm; never claim this was measured from the image. Scene: {scene}. Wardrobe: {wardrobe}. Expression: {expression}. Camera: {camera}. Lighting: {lighting}. Produce one stable scene first frame. Do not reshape the body beneath the clothes. Hidden geometry is interpreted, not measured.
Animate the attached accepted scene first frame. Action: {one_simple_action}. Camera: {camera_motion_or_locked}. Duration: {seconds}. Keep her existing face, body proportions, outfit, hair, lighting, scene and ground contact stable throughout. Use natural movement and continuous anatomy. Do not add scene changes, new people or wardrobe changes. Dialogue, only if configured: {dialogue_or_none}. Preserve lip sync when audio is enabled. Avoid flicker, face drift, body drift, floating heels, extra fingers and sliding feet.
Avoid: identity changes, larger eyes or enlarged lips, thinner nose or sharper jaw, changed skin tone or apparent age, shifted hairline or changed part, new facial marks, plastic skin, mirrored asymmetric features, facial warping, frame-to-frame flicker, body reshaping, waist slimming or exaggerated hips, changed bust proportions, elongated torso or legs, frame-to-frame body drift, footwear or leftover straps in barefoot reference views.
1. Anchor
Keep the active anchor attached. Add the individual image for the nearest matching angle.
2. Check a still
Compare face and body in the first frame before generating the full shot.
3. Review motion
Check turns, walking, speech and the final frame. Reject face or body drift.
Identity drift checklist
Visible face and body match the active barefoot fitted-unitard anchor and nearest reference angle.
Hairline, center part, hair color and volume remain stable.
Skin tone and apparent age remain consistent under intended lighting.
Body proportions and nominal rotation direction agree with the full-body references.
Identity remains stable through motion, speech, blinks and the final frame.
Shoulders, torso, bust, waist, hips and limb proportions stay consistent; clothing does not reshape them.
Every current reference shows bare feet with natural toes and heel placement; no footwear or leftover straps remain.
The neutral turn has flat heels and toes on one ground plane, relaxed stance and a clear body silhouette.
Record the reference files, prompt, generator version, settings and seed when available. A matching seed alone does not guarantee identity. Regenerate drifting outputs from the approved anchor.
A stable baseline
Capture standards
Reference image capture standards
Setting
Reference standard
Camera
Level camera at mid-body height · natural full-body perspective without wide-angle distortion
Framing
Full body, crown through bare toes, level camera and consistent body scale
Light
Soft, even studio light without dramatic shadows
Background
Transparent alpha; neutral display surface for inspection
Expression
Relaxed closed lips, matching the approved anchor · gaze follows head direction without forcing eye contact in profile
Head
Pitch 0° · Roll 0°
Reference outfit
opaque matte rose-pink sleeveless scoop-neck unitard to ankles; bare feet, no footwear; original wrist jewelry
Pose
neutral relaxed stance, both heels and toes resting naturally on one ground plane, arms slightly away from torso; hair behind shoulders where needed to show the silhouette
Texture
Natural skin and matte textile detail; no beauty filter
Test before finishing
Production
Brief. Reviewed first frame. Short native-resolution test. QA. Finish only when needed.
Applied: AI Media Cost Framework · v3. Four test clips are quoted at $0.84 total; actual bills and setup/compute costs remain unknown.
170 cmProvisional design target · not measured
Brittneyowner selected pending proof
$5.00Shared external API test cap · no top-ups
Scene first frames
Walk / turn working frame · DownloadSit working frame · Download
Reviewed working inputs. Motion review: 4 accepted, 1 rejected. The talk baseline remains muted.
Voice: Brittney - Social Media Voice - Fun, Youthful & Informative · owner selected pending proof
Front-to-profile reference ending in full side profile with eyes open; no final hold requirement. Original five-second request and final two-second hold are not re-approved.
Identity and barefoot anatomy remain stable in twelve sampled frames, but the requested quarter-turn stops at a modest oblique pose rather than a full side profile. Reject for action adherence; retain the billed attempt. Stored clip is muted; voice and lip sync remain unvalidated.
The source reaches profile but misses its original final hold. The new curated reference uses only its reviewed front-to-profile segment. Original full-brief QA remains false.
First frame: accepted working test input · QA: accepted reference cut
Walk
accepted · 1/2 attempts
Root-reviewed working motion baseline; shot-specific production review still required.
Twelve sampled frames and first/mid/final face/feet crops show stable identity, hair, fitted outfit and body proportions with coherent forward steps and visible bare feet. Stored clip is muted; voice and lip sync remain unvalidated.
First frame: accepted working test input · QA: accepted
Sit
accepted · 1/2 attempts
Root-reviewed working motion baseline; shot-specific production review still required.
Twelve sampled frames show coherent lowering onto the chair with stable face, body and outfit. Bare toes remain in contact with the floor; heels rise late, so this is not a flat-foot seated-pose validation. Stored clip is muted; voice and lip sync remain unvalidated.
First frame: accepted working test input · QA: accepted
Talk
accepted · 1/2 attempts
Root-reviewed working motion baseline; shot-specific production review still required.
Twelve sampled frames of the finished file preserve face, hair and outfit through visible articulation and blinks. Same-resolution finishing is visually consistent with the reviewed original. Muted articulation does not validate voice or lip sync. Stored clip is muted; voice and lip sync remain unvalidated.
First frame: accepted working test input · QA: accepted
Reference pack complete for v0.4.0. The stored speech proof below used the previous voice (Kokoro bf_emma); the current voice needs its own proof.
Machine-verified short voice proof; exact stored clip approved.
Short proof quote: $0.291; reserved maximum: $0.60; actual bill: unknown.
SyncNet evaluated all 177 valid five-frame windows over 7.24 seconds, with all 187 resampled face frames detected; estimated offset -40 ms, confidence 7.5897. Known +/-480 ms audio shifts and reversed-audio negative control behaved as expected. Independent ASR decoded identical master and returned speech; contraction-normalized content matches all 19 expected words. The exact stored short proof passes machine review. No human listening or universal future-video quality claim.. Exact stored 7.466667-second clip only; future speech clips require their own review..
QA report · Complete for the stored short references. Future scenes require their own review.
Workflow, model & voice settings
Shot brief. Define one action, scene, camera, lighting, wardrobe, aspect ratio and duration.
Scene first frame. Create or reuse one scene still. Review face, anatomy and scene before motion; record reviewer and exact image hash.
Motion test. Use the verified provider's supported native output; do not force a new 720p render when an economical native result passes QA.
Qa. Check face, body, feet, hands, hair, flicker, motion continuity and audio when present. Reject drift.
Final. Render 1080p only when a test is accepted and a higher-resolution deliverable is needed. An accepted native-resolution clip may be sufficient.
Upscale or edit. Use at most one justified finishing pass on an accepted output. No mass 4K rerolls.
Hash the exact reference bytes, prompt, provider/model/version, settings, duration, resolution and audio options. Reuse accepted cached outputs; review existing rendered outputs before retrying. A fixed seed is not an identity guarantee.
Compare direct providers and existing aggregators using verified rates, quality and access. Cost per accepted deliverable includes all retries, discarded jobs, audio, LLM, finishing, storage and compute. Do not describe self-hosting as costless. Unknown cost stays unknown.
Renderer: kie · kling/v2-5-turbo-image-to-video-pro · v2-5-turbo-image-to-video-pro. Access: access verified actual jobs reviewed.
Rates, minimum duration, resolution, audio features, sources, verification time and exact settings: production config.
Voice: ElevenLabs / kPzsL2i3teMYv0FxEYQ6 · Owner-selected ElevenLabs library voice (Brittney). Key read by name from Supabase Edge secrets. The library voice owner can retire it with 180 days' notice. The v0.4.0 lip-sync proof used Kokoro bf_emma and does not validate this voice; a new short proof is needed.
30- and 60-second finished video costs are not measured; quote from an approved shot list. The stored speech proof is machine-verified; silent articulation clips remain separate.
Normalized proportions follow the anchor at height unit 1.0. No exact anatomical measurements are invented.
Budget ledger
Observed consumption: 266 credits · $1.33 at listed rates. Actual cash charges remain unconfirmed.
Reserved/committed external API cap usage: $1.6500 of $5.00. This is not a final billed total.
Known recorded subtotal: $0.0000. Unknown-cost entries: 11. Accepted outputs: 5.
Full cost per accepted output remains unknown until cash billing and unmetered support costs are reconciled. API quotes are shown separately.
Production voice switched to ElevenLabs Brittney (owner choice) with a new sample. Kokoro bf_emma and its v0.4.0 lip-sync proof are kept as history; the new voice needs its own proof. Face and body unchanged.
2026-10-30
v0.4.0
Added a neutral barefoot anchor and full turn, close-up face and expression references, separate still and motion prompts, staged production gates and a budget ledger. Historical poses remain archived.
2026-10-24
v0.3.0
Removed footwear from the active anchor and every full-body angle reference. Preserved the fitted-unitard body design above the ankles and archived all earlier files unchanged.
2026-10-25
v0.2.0
Replaced the active anchor with the owner-approved fitted pink unitard and added eight separately downloadable full-body 360-degree references. Preserved v0.1.0 source and face matrix in the archive.
2026-10-24
v0.1.0
Established the original identity anchor, eight-view 360° matrix, identity rules and video prompt framework.
2026-10-23
Previous references · v0.1.0–0.3.0
Archived for history. Use the current barefoot anchor for new work.
