Turn
accepted · 1/2 attempts
Lead-reviewed working motion baseline; shot-specific production review still required.
Download clipTurns to the left-facing profile and holds; feet planted.
First frame: accepted working test input · QA: accepted
Bethany · Model 004 · v0.1.0
One face. One body. Every shot.
Cream top and charcoal leggings reference · Fictional adult actress · No real person depicted
The rotation
8 full-body views. 8 ready, 0 pending. Neutral stance. Choose an angle to open or download.
Open the 360° sheet · Download
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; all eight views are generated interpretations at 4K, not measurements. Target pitch 0° and roll 0°. All views are generated; no photograph of a real person exists or is used.
Attach the face anchor and the nearest matching angle. A back view establishes the rear silhouette, not unseen facial details.
Closer reference
The approved front face is the face authority. Generated turns and expressions are interpretations that must match it. A speaking still is not a lip-sync model.
What stays fixed
Preserve her face and body. Change the scene and wardrobe around them.
| Feature | Keep consistent |
|---|---|
| Face | Soft oval face with defined adult cheekbones and jaw; retain the face anchor's proportions and natural asymmetry. |
| Eyes | Blue eyes; retain shape, spacing and eyelids from the face anchor. |
| Brows | Natural, softly arched light-brown brows. |
| Nose | Straight, narrow bridge with a softly rounded tip. |
| Lips | Full lips with a defined upper contour; retain mouth width. |
| Skin | Fair skin with a natural warm blush and light freckles across the nose and cheeks; natural texture. |
| Hair | Long, loose, wavy honey-blonde hair with pastel pink lengths and a soft side part. |
| Body | Curvy hourglass build: slim waist, flat stomach, full hips and rounded glutes, toned thighs, medium bust. Do not slim, enlarge or lengthen body features. |
| Reference outfit | Cream ribbed long-sleeve fitted crew-neck top, charcoal high-waist full-length leggings, plain white low-top sneakers. |
Jev (TypeSafe System One, jev-1.14.0) feature-match probability and 0-4 likeness score with confidence against the approved face anchor; ArcFace (InsightFace buffalo_l) cosine similarity. Full-body shots score lower because the face is small at the scorer's input size. Confidence is not proof; the owner decides.
| Image | Jev feature match | Jev likeness (0–4) · confidence | Face-ID |
|---|---|---|---|
| Face baseline from the owner (pilot input) | 40% | 2.96 · 0.60 | 0.57 |
| Face front | 89% | 3.44 · 0.52 | 0.91 |
| Face three-quarter left | 84% | 3.38 · 0.46 | 0.80 |
| Profile facing right | 78% | 3.35 · 0.46 | 0.68 |
| Smile | 67% | 3.45 · 0.56 | 0.80 |
| Body front | 40% | 2.75 · 0.55 | 0.62 |
| Body side | 48% | 2.89 · 0.51 | — |
| Hero anchor | 48% | 2.75 · 0.56 | 0.58 |
| Different person · Kayla (control) | — | — | 0.23 |
Jev (jev-1.14.0) compares each image with the approved face anchor; face-ID is ArcFace cosine similarity against the same anchor (a different person scores 0.23). The owner's baseline scores lower by design: the finals keep her features but read clearly adult. Full-body shots score lower because the face is small at the scorer's input size. Confidence is the spread of Jev's answers, not proof.
The approved pilot face draft governs her face, eyes, freckles, hair and apparent age; the approved pilot body draft governs build and the reference outfit. Final 4K stills were generated from 2x restorations of both (face creativity 0).
Unspecified: height, exact body measurements, unseen distinguishing marks.
Apparent age is a fictional design choice (adult, early-to-mid 20s) and is never made younger. Skin color is described as rendered in the references. The reference lighting is not a calibrated color measurement.
Not a real person
Bethany is a fictional adult character, the owner’s AI actress. No real person is depicted, so no consent record applies. The face starts from the owner’s own AI-generated image; the body is described in text.
Start every shot here
Build and review the scene first frame with the identity prompt. For image-to-video, describe movement around that accepted frame.
Generate {shot} of the same woman. Image 1 (bethany face anchor) is the face authority: keep her exact face, blue eyes, brows, nose, full lips, freckles, fair skin and long wavy honey-blonde hair with pastel pink lengths. Image 2 (nearest body view) sets her curvy hourglass build. She is an adult woman in her early-to-mid 20s, exactly as mature as in image 1; never younger. Wardrobe: {wardrobe}. Scene: {scene}. Lighting: {lighting}. Photorealistic, natural skin texture, sharp focus. One person only, no text, no watermark.
Animate the attached accepted scene first frame. Action: {one_simple_action} Camera: locked, no camera movement. Duration: 5 seconds. @bethany is this same woman: keep her existing face, age, blue eyes, freckles, long wavy honey-blonde hair with pastel pink lengths, body proportions, cream top, charcoal leggings and white sneakers, lighting, scene and ground contact stable throughout. Use natural movement and continuous anatomy. Do not add scene changes, new people, text, captions, logos or wardrobe changes. No dialogue. Avoid flicker, face drift, warped frames, body drift, floating heels, extra fingers and sliding feet.
Avoid: identity changes, younger-looking face or proportions, changed eye color, removed or moved freckles, hair color or part changes, plastic skin, beauty filter, facial warping, frame-to-frame flicker, body slimming, bulking or lengthening, wardrobe drift in reference shots, added text, captions or logos.
Attach the face anchor. Add the nearest full-body angle.
Compare face, freckles, hair and body in the first frame before generating the full shot.
Check turns, walking, speech and the final frame. Reject face, age or body drift.
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 anchors.
A stable baseline
| Setting | Reference standard |
|---|---|
| Camera | Level camera at mid-body height · natural full-body perspective without wide-angle distortion |
| Framing | Full body, crown through shoes, level camera and consistent body scale |
| Light | Soft, even studio light without dramatic shadows |
| Background | Seamless medium warm-grey studio backdrop and floor |
| Expression | Calm closed lips unless an expression is briefed · gaze follows head direction |
| Head | Pitch 0° · Roll 0° |
| Reference outfit | Cream ribbed long-sleeve fitted crew-neck top, charcoal high-waist full-length leggings, plain white low-top sneakers. |
| Pose | Neutral relaxed stance, arms slightly away from the sides, feet flat on one ground plane |
| Texture | Natural skin and matte textile detail; no beauty filter |
Test before finishing
Brief. Reviewed first frame. Short native-resolution test. QA. Finish only when needed.
Applied: AI Media Cost Framework · v3. 32 jobs quoted at $8.21; actual bills and setup/compute costs remain unknown.
Not setHeight · Fictional character; height not specified.
Lily - Velvety Actressapproved by owner
$10.00External API cap · no top-ups
Reviewed working inputs. Motion review: 4 accepted, 0 rejected. Motion baselines carry no audio; speech is shown in the voice proof.
Voice: Lily - Velvety Actress · approved by owner. Premade actress voice, distinct from Kayla's Brittney. Approved by the owner on 2026-11-03.
accepted · 1/2 attempts
Lead-reviewed working motion baseline; shot-specific production review still required.
Download clipTurns to the left-facing profile and holds; feet planted.
First frame: accepted working test input · QA: accepted
accepted · 2/2 attempts
Lead-reviewed working motion baseline; shot-specific production review still required.
Download clipWalks toward the camera; travel distance is short. First attempt failed at the provider (character upload, no charge); retry passed.
First frame: accepted working test input · QA: accepted
accepted · 1/2 attempts
Lead-reviewed working motion baseline; shot-specific production review still required.
Download clipTurns and sits on the chair, settles upright; hands and feet grounded.
First frame: accepted working test input · QA: accepted
accepted · 1/2 attempts
Lead-reviewed working motion baseline; shot-specific production review still required.
Download clipTalks to the camera with natural head motion and blinks; identity stable.
First frame: accepted working test input · QA: accepted
accepted · asr and waveform verified visual reviewed
Download clipLine: “Hi, I'm Bethany. This is my reference model for JBNX Design.” Transcript check: “Hi, I'm Bethany. This is my reference model for JBNx design”. Waveform match 0.9998 at 0.0 s offset.
Proof quote: $0.334; reserved maximum: unknown; actual bill: unknown.
QA report · Complete for the stored v0.1.0 references. Future scenes require their own review. Next: Each production scene still needs its own first-frame and motion review; spoken lines beyond the approved intro need the owner's approval.
Hash the exact reference bytes, prompt, provider/model/version, settings, duration, resolution and audio options. Reuse accepted outputs; review existing outputs before retrying. A fixed seed is not an identity guarantee.
Cost per accepted deliverable includes all retries, discarded jobs, audio, LLM, finishing, storage and compute. Unknown cost stays unknown.
Renderer: kie · kling-3.0/video · kling-3.0 pro. Access: access verified actual jobs reviewed. Kling handles this real person's likeness; Seedance 2.x tops the Artificial Analysis image-to-video board but blocks real-person faces at the model layer. The 4K mode exists but adds cost and file weight for reference clips delivered at 1080p.
Stills: fal-ai/nano-banana-pro/edit at 4K. Restoration: fal-ai/topaz/upscale/image (Recovery V2 2x on the approved face draft (creativity 0)).
Rates, resolution, sources, verification time and exact settings: production config.
Voice: ElevenLabs / pFZP5JQG7iQjIQuC4Bku · eleven_multilingual_v2.
30- and 60-second finished video costs are not measured; quote from an approved shot list. The owner approved the voice and intro line; any other spoken line needs his approval.
Observed consumption: 360 kie credits · $1.80 at listed rates. Actual cash charges remain unconfirmed.
Reserved/committed external API cap usage: $8.2060 of $10.00. This is not a final billed total.
32 jobs: 30 accepted outputs, 1 rejected. Unknown-cost entries: 32.
Full cost per accepted output remains unknown until cash billing and unmetered support costs are reconciled. Count video, audio, LLM, retries, discarded jobs, finishing, storage and compute.
Ready to reuse
Keep the history
The owner approved the v0.1.0 reference pack and the ElevenLabs 'Lily' voice with the line 'Hi, I'm Bethany. This is my reference model for JBNX Design.'
Created from the owner's own AI-generated face baseline as a fictional adult AI actress. Cheap 1K pilot (Nano Banana 2.1) of face, body front and side, scored with Jev and approved by the owner; then 19 4K references (8 body angles, 5 face turns, 3 expressions, 2 scene frames, hero anchor), a 360 sheet, four Kling 3.0 pro motion baselines and a voice proof in ElevenLabs 'Lily'. Voice and line await the owner's approval.
1K drafts the owner approved before the 4K pass. They are the face and body authorities the v0.1.0 stills were generated from. Kept for the record.