TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

6cc03e77-22c0-4f8d-90e0-aa3216ede2a6

Queued
Jul 24, 2026, 02:59 PM
Completed
Jul 24, 2026, 02:59 PM
Execution time
28.9s
Outputs
1 · 5.3 MB
Inputs
4
Cached nodes
4

Outputs

1

Click an image to view it full size.

character_ref_00403_.png

node 3 · 5.3 MB

Text prompts

3
Promptnode 1 · PrimitiveStringMultiline · valueCharacter Description (your input)

**POSITIVE PROMPT** @Wren, keyframe for shot S1.20. Vertical 9:16, 1440x2560. Close-up, frontal, chest up. She sits left of centre with the **negative space band at 22 percent** of frame width at frame-right — step 5 of 6, the room measurably smaller than at S1.14. **One sodium bar behind her, now partially cropped by the frame edge**, so the room is not just smaller but becoming unreadable. Face on the upper third line. Top edge of @Keyboard at the bottom frame line. Three planes. Lens character **50mm** at 0.86 m, camera at seated eye height 118 cm, frontal, honest perspective, no distortion. She faces screen-left. **Generate locked off** — the 3 percent push is a comp-stage scale ramp, never a generated camera move. 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. Forward head 5cm anterior to the shoulder line, rounded shoulders, right leg folded under, weight settled and unchanged. Expression state: **Focused, ceiling 2.** She is still transcribing. Working posture, head square to the monitor. Eyes reading in saccades that have slowed further but have not stopped. Blink rate 8 to 10 per minute. **Listening tilt absent — the head is not tilted.** Brow inner ends drawn down 1mm, sustained faint tension. Mouth closed and softening, left corner low. Breath shallow but steady. **Nothing on her face registers the content of what she is hearing.** No softening toward emotion, no tenderness, no recognition. Hands: **typing intermittently, in short failing bursts**, just clipped by the bottom frame line, wrists low and unsupported, fingers close to the keys, caught mid-burst. Anchors: A1 left mouth corner 1.5mm lower than the right; A2 right-eye freckle 8mm below the outer corner of the right eye. Interocular distance 1.08x classical spacing. Right brow 2mm higher, sharper arch, three inner-left brow hairs out of line. Left palpebral fissure 1mm narrower, more hooded. Long philtrum, thin upper lip, fuller lower lip with the chronic dry patch left of centre. Recessed chin, soft 128-degree jaw, 3mm mole below the left jawline. Grey-green irides reading grey under monitor light, dark limbal ring, sclera faintly grey-blue with fine vessels. Deep-set eyes, shallow trough beneath the lower lids, hollow under the outer cheekbone. @Chain flat in the suprasternal notch if the collarbone reads. Lighting: primary **green** key from @Monitor1, front and slightly below — Elias playing continuously — catching under the brow, the tip of the nose, the upper lip and the front of the throat, abandoning the top of her head. Secondary: **one sodium bar on the brick, cropped by the frame edge**, faint amber rim on her right shoulder and hair. Room 4 to 6 stops down, black lifted and noisy. No fill, no third source. Skin: unretouched, real pore texture, cool undertone, faint permanent redness across the nose and inner eye corners, no cosmetic surface, no makeup. She reads 32. **NEGATIVE PROMPT** listening tilt, head tilted, head turned, gaze unfocused, gaze parked, staring past the screen, saccades stopped, hands stopped, hands frozen, hands withdrawn, hands out of frame, moved expression, softening, tenderness, sympathy, empathy, warmth, sadness, wistful, on the verge of tears, tear, wet eyes, glassy eyes, dead eyes, smile, half-smile, parted lips wide, mouth open, speaking, emotional performance, acting, expression held as a photograph, symmetrical face, corrected asymmetry, equal brows, equal eyelids, narrowed interocular distance, straightened posture, upright spine, squared shoulders, chin lifted, looking upward, looking at camera, direct-to-lens gaze, facing screen-right, three-quarter angle, profile, 85mm compression, tight ECU, wide negative space, 45 percent band, no bar, two full bars, uncropped sodium bar, blue-white key, warm key on face, fill light, rim light for flattery, haze, volumetrics, god rays, atmosphere, visible monitor, visible screen content, legible text, deep background detail, bright room, camera movement, push in, drift, handheld, dolly, zoom, low angle, high angle, headphones missing, changed headphone model, earrings, makeup, mascara, eyeliner, lip gloss, retouched skin, airbrushed, plastic skin, smooth skin, poreless, flawless, perfect skin, beautiful, pretty, gorgeous, stunning, model, glamorous, youthful, cute, reads 25, crushed blacks, clean blacks, high contrast, oversaturated, HDR, sharpening halo, lens flare, halation, glow bloom, grain, film emulation, vignette, colour grade, stylisation, cinematic look, moody, atmospheric, cozy, tidy, text, watermark, horizontal framing, wide shot, morphing features, AI face, duplicate eyes, misaligned eyes, extra fingers, malformed hands, floating chain

Systemnode 2 · GeminiImageDirect · system_promptCharacter Image Generator (Nano Banana)

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

4

Source images and video this run consumed.

character_ref_00375_ (1).png

node 4 · 1.2 MB

character_ref_00384_.png

node 5 · 1.3 MB

character_ref_00377_.png

node 6 · 1.4 MB

character_ref_00376_.png

node 7 · 1.3 MB