f7881d79-e58a-4640-8107-5a61d307936e
- Queued
- Jul 24, 2026, 02:38 PM
- Completed
- Jul 24, 2026, 02:39 PM
- Execution time
- 22.7s
- Outputs
- 1 · 5.5 MB
- Inputs
- 4
- Cached nodes
- 4
Outputs
1Click an image to view it full size.
Text prompts
3**POSITIVE PROMPT** @Wren, keyframe for shot S1.04. Vertical 9:16, 1440x2560. Close-up, chest up, **three-quarter angle** — face turned screen-left so the right side of her face is fully presented and the left cheek and jaw fall away completely into shadow. She is placed left of centre and occupies roughly 60 percent of frame width. Frame-right holds the episode's **first negative space band, 45 percent** at maximum width: a vertical band of dark room, five stops down, with **one sodium bar** crossing it on brick. Her mouth sits on the horizontal midline, in the lower-lit part of the frame, deliberately off any bright plane. Two planes only. Bottom frame line includes the top edge of @Keyboard. No mug in frame. Lens character 50mm at 1.0 m, camera at seated eye height 118 cm, three-quarter frontal, honest perspective, no stylisation. Locked off. State: fatigue 30 percent, wash cycle day 3, wardrobe look EP01, hair tucked behind the right ear and loose on the left, parting 15mm right of centre, greys at the right temple, headphone dent present, @Headphones on. Right ear exposed by the tuck and readable at this angle. Posture: seated, right leg folded under her, forward head 5cm anterior to the shoulder line, rounded shoulders, weight settled left. Left hand finishing a line on @Keyboard at the bottom frame edge, right hand resting at @Console. **Nothing in her body changes.** Eyes screen-left, on the transcript, in reading saccades — never toward the thing she is speaking to. Expression state: working, at rest, unremarkable. She is at her job. Mouth caught in the shape of a two-syllable word spoken out of habit — lips parted a small, unemphatic amount, jaw barely dropped, no projection, no articulation effort, the mouth of someone who has said something without deciding to. **Not a performance, not a farewell, not tenderness.** Blink irregular, micro-saccades present, breath quiet. Anchors: A1 left mouth corner 1.5mm lower than the right, holding through the word shape; A2 right-eye freckle 8mm below the outer corner of the right eye, fully readable on this presented side. Interocular distance 1.08x classical spacing. Right brow 2mm higher with the sharper arch. Left palpebral fissure 1mm narrower, more hooded, further reduced by the turn. Long philtrum, thin upper lip, fuller lower lip with the chronic dry patch left of centre, 1:1.8 ratio, soft vermilion border. Recessed chin, soft 128-degree jaw. 3mm mole below the left jawline sitting in the shadowed side. Grey-green irides reading grey under monitor light, dark limbal ring, sclera faintly grey-blue with fine vessels. Lighting: primary @Monitor1 **blue-white**, front and slightly below, no playback. Secondary sodium bar on the brick behind her at frame-right, amber, faint rim on her right shoulder and hair edge. Left cheek and jaw in full falloff. No reflection in frame. No third source. Skin: unretouched, real pore texture, dry, no cosmetic surface, no makeup, no jewellery except @Chain if the collarbone reads. She reads 32. **NEGATIVE PROMPT** smile, smiling mouth, warm expression, tenderness, sadness, grief, wistful, longing, eyes closed, eyes toward camera, eyes toward the speaker, looking off to the side, looking down, head turned right, frontal angle, profile, dramatic mouth shape, wide open mouth, exaggerated articulation, teeth showing, mid-shout, projecting voice, emotional performance, acting, expression held as a photograph, caught mid-blink, tear, wet eyes, glassy eyes, dead eyes, frozen face, symmetrical face, corrected asymmetry, equal brows, equal eyelids, narrowed interocular distance, straightened posture, upright spine, squared shoulders, head back, chin up, both feet flat, green key light, green spill, warm key on face, amber face light, two sodium bars, bright room, visible monitor, visible screen content, legible text, mug in frame, visible mattress, visible window, deep background detail, background bokeh detail, small negative space, centred subject, camera movement, push in, drift, handheld, dolly, low angle, high angle, direct-to-lens gaze, headphones missing, headphones changed model, missing tape on hinge, earrings, makeup, mascara, eyeliner, lip gloss, retouched skin, airbrushed, plastic skin, smooth skin, flawless, perfect skin, beautiful, pretty, gorgeous, stunning, model, glamorous, youthful, cute, reads 25, crushed blacks, high contrast, oversaturated, HDR, sharpening halo, lens flare, halation, grain, film emulation, vignette, colour grade, stylisation, cinematic look, moody, atmospheric, cozy, warm, inviting, tidy, text, watermark, horizontal framing, wide shot, morphing features, AI face, duplicate eyes, misaligned eyes, extra fingers, malformed hands, floating chain
Generate a single, hyper-realistic character reference image (strictly no collages, text, watermarks, or borders). The image must feature a cinematic, three-quarter portrait of the described character, maintaining a sharp, tack-focused emphasis on the face with natural skin textures, pore details, and realistic micro-expressions. The lighting should be cinematic and directional (e.g., subtle split or Rembrandt lighting) to give depth, blending seamlessly with the environment specified in the character description. The character must have a natural, living presence, looking slightly off-camera or directly at the lens with a subtle, context-aware expression. Ensure the full head, neck, and upper shoulders are completely unobstructed. This image serves as a high-fidelity identity blueprint for temporal-consistent video generation.
1 other text field— sigmas, filenames, and other non-prompt strings the logger swept up
node 4 · LoadImage · image
character_ref_00375_ (1).png
Input media
4Source images and video this run consumed.