73d50313-2578-444c-8ade-a0fcd72533c2
- Queued
- Jul 24, 2026, 03:19 PM
- Completed
- Jul 24, 2026, 03:20 PM
- Execution time
- 21.7s
- Outputs
- 1 · 5.7 MB
- Inputs
- 4
- Cached nodes
- 4
Outputs
1Click an image to view it full size.
Text prompts
2**POSITIVE PROMPT** Plate for shot S1.09 — @Monitor1 waveform display, screen-filling, self-luminous. Vertical 9:16, 1440x2560. No camera, no room, no reflection, no object of @Loft in frame. The waveform trace occupies the horizontal centre band, **filling roughly 60 percent of frame height** — tighter than S1.02, so a child's small voice takes up more of the frame than an old man's did. **Pure black above and below** the trace, clean and even. Green on black. Trace colour #3FD07A, flat, hard-edged, **no glow, no bloom, no halation, no soft falloff around the trace** — flat and ugly like a real interface, not a music visualiser. Single plane, self-luminous, no light source, no spill, no vignette. **Generate this as a clean, empty black field with the centre band left clear as a comp receiver.** The waveform itself is animated from the locked VO sample and composited — no trace, no type, no timestamps, no UI elements, no cursor generated in the image. Static. Nothing moves. **NEGATIVE PROMPT** glow, bloom, halation, light wrap, soft edges, blurred trace, gradient, neon, glowing green, luminous haze, particle effects, motion blur, scan lines, CRT curvature, screen texture, pixel grid, moiré, dust, scratches, reflections, glass, mirror, monitor bezel, screen edge, room visible, desk visible, hands, face, person, body, reflection of a person, waveform, audio trace, spectrum bars, equaliser, oscilloscope styling, circular waveform, stylised visualiser, text, type, letters, numbers, timestamps, labels, UI elements, interface, buttons, cursor, icons, watermark, subtitle, blue light, white light, amber light, warm tint, multiple colours, gradient colour, crushed blacks, lifted greys, high contrast, oversaturated, HDR, sharpening halo, grain, film emulation, vignette, colour grade, stylisation, cinematic look, moody, atmospheric, beautiful, aesthetic, depth, perspective, 3D, camera angle, camera movement, horizontal framing, AI artefacts
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.
Input media
4Source images and video this run consumed.