Model Bakeoffrendered on fal · 2026-09-03

Character serial, block 1

Two stylised characters from a bible, four lines, an entrance through a doorway and a small flyer hanging from a lamp. The establishing frame carries two artifacts of its own, which every single-frame model faithfully reproduces.

establishing frame
frame + 6 references
0–4 s: The brass bell goes ding. The baker looks up slowly from the counter and says, warmly: 'Welcome in. Come in.' A small voice from the doorway: 'It's me!' 4–10 s: The flyer swoops in and hangs upside down from the lamp, wrapping his wings around himself. 'A bun please! Last time the jam went up my nose.' The baker: 'Yes, of course.'
4 models received different prompt text — show each

Each model is given the prompt its input contract calls for: a multi-reference model is told which reference is which character, a segmented model gets shot segments. The frame, the references and the requested length are identical throughout. This is the honest version of "the same prompt".

H3 Max, Wan 2.7, Veo 3.1, LTX-2

Modern 3D animated feature style for preschool: soft rounded forms, chunky simple silhouettes, large expressive eyes, smooth matte surfaces with subtle fuzz on fur, warm rim light and soft ambient occlusion, shallow depth of field, saturated but gentle colour, no harsh shadows, no photorealism. Cosy and glowing rather than dark. Vertical 9:16, character centred and large in frame, uncluttered background so the character always reads instantly. A single continuous 10-second scene. One location: a tiny warm bakery at night. A wooden counter, a glass dome over a cake stand, a round brass bell, shelves of jars, a big friendly oven with a glowing window, and one window onto a deep blue night with round stars. Everything is soft and rounded - no sharp knives, no fire, no mess. Characters are stylized animals that walk upright, wearing at most one simple accessory each. No humans, no text or signage, no crowds. The night outside is cosy, never frightening. 0s–4s: The brass bell goes ding. The baker looks up slowly from the counter and says, warmly: 'the shop. Come in.' A small voice from the doorway: 'It's me!' 4s–10s: The flyer swoops in and hangs upside down from the lamp, wrapping his wings around himself. 'A bun please! Last time the jam went up my nose.' The baker: 'Yes, of course.' Hold every character's design exactly as shown. Do not drift toward photorealism. Avoid: photorealistic, live action, human, person, realistic fur, uncanny, creepy, scary, dark, gloomy, horror, gritty, harsh shadow, sharp knife, fire, flames, mess, spilled, sharp teeth, text, letters, signage, watermark, subtitles, caption, logo, cluttered background, crowd, extra characters, deformed, extra limbs, distorted face

H3 ref2v, Seedance 2.0

Modern 3D animated feature style for preschool: soft rounded forms, chunky simple silhouettes, large expressive eyes, smooth matte surfaces with subtle fuzz on fur, warm rim light and soft ambient occlusion, shallow depth of field, saturated but gentle colour, no harsh shadows, no photorealism. Cosy and glowing rather than dark. Vertical 9:16, character centred and large in frame, uncluttered background so the character always reads instantly. Image 1, Image 2, Image 3 are The baker (large brown bear baker, cream apron, round spectacles) from 3 angles — the same character every time. Image 4, Image 5, Image 6 are The flyer (small purple fruit bat, orange bow tie) from 3 angles — the same character every time. Image 7 is the room, and the exact look of the scene. A single continuous 10-second scene. One location: a tiny warm bakery at night. A wooden counter, a glass dome over a cake stand, a round brass bell, shelves of jars, a big friendly oven with a glowing window, and one window onto a deep blue night with round stars. Everything is soft and rounded - no sharp knives, no fire, no mess. Characters are stylized animals that walk upright, wearing at most one simple accessory each. No humans, no text or signage, no crowds. The night outside is cosy, never frightening. 0s–4s: The brass bell goes ding. The baker looks up slowly from the counter and says, warmly: 'the shop. Come in.' A small voice from the doorway: 'It's me!' 4s–10s: The flyer swoops in and hangs upside down from the lamp, wrapping his wings around himself. 'A bun please! Last time the jam went up my nose.' The baker: 'Yes, of course.' Hold every character's design exactly as shown. Do not drift toward photorealism. Avoid: photorealistic, live action, human, person, realistic fur, uncanny, creepy, scary, dark, gloomy, horror, gritty, harsh shadow, sharp knife, fire, flames, mess, spilled, sharp teeth, text, letters, signage, watermark, subtitles, caption, logo, cluttered background, crowd, extra characters, deformed, extra limbs, distorted face

Kling v3 Pro

[{"prompt":"The brass bell goes ding. Baba looks up slowly from the counter and says, warmly: 'Night Kitchen. Come in.' A small voice from the doorway: 'It's me!'","duration":"4"},{"prompt":"Fen swoops in and hangs upside down from the lamp, wrapping his wings around himself. 'A bun please! Last time the jam went up my nose.' Baba: 'Yes, of course.'","duration":"6"}]

H3 ref2v + voice, Seedance + voice

Modern 3D animated feature style for preschool: soft rounded forms, chunky simple silhouettes, large expressive eyes, smooth matte surfaces with subtle fuzz on fur, warm rim light and soft ambient occlusion, shallow depth of field, saturated but gentle colour, no harsh shadows, no photorealism. Cosy and glowing rather than dark. Vertical 9:16, character centred and large in frame, uncluttered background so the character always reads instantly. Image 1, Image 2, Image 3 are The baker (large brown bear baker, cream apron, round spectacles) from 3 angles — the same character every time. Image 4, Image 5, Image 6 are The flyer (small purple fruit bat, orange bow tie) from 3 angles — the same character every time. Image 7 is the room, and the exact look of the scene. Audio 1 is the scene's complete dialogue, in order: The baker says "the shop. Come in.", then The flyer says "It's me!", then The flyer says "A bun please! Last time the jam went up my nose.", then The baker says "Yes, of course.". Animate each character's mouth to match Audio 1 exactly, and let the other characters listen while one speaks. A single continuous 10-second scene. One location: a tiny warm bakery at night. A wooden counter, a glass dome over a cake stand, a round brass bell, shelves of jars, a big friendly oven with a glowing window, and one window onto a deep blue night with round stars. Everything is soft and rounded - no sharp knives, no fire, no mess. Characters are stylized animals that walk upright, wearing at most one simple accessory each. No humans, no text or signage, no crowds. The night outside is cosy, never frightening. 0s–4s: The brass bell goes ding. The baker looks up slowly from the counter and says, warmly: 'the shop. Come in.' A small voice from the doorway: 'It's me!' 4s–10s: The flyer swoops in and hangs upside down from the lamp, wrapping his wings around himself. 'A bun please! Last time the jam went up my nose.' The baker: 'Yes, of course.' Hold every character's design exactly as shown. Do not drift toward photorealism. Avoid: photorealistic, live action, human, person, realistic fur, uncanny, creepy, scary, dark, gloomy, horror, gritty, harsh shadow, sharp knife, fire, flames, mess, spilled, sharp teeth, text, letters, signage, watermark, subtitles, caption, logo, cluttered background, crowd, extra characters, deformed, extra limbs, distorted face
  • The baker: “Night Kitchen. Come in.”
  • The flyer: “It's me!”
  • The flyer: “A bun please! Last time the jam went up my nose.”
  • The baker: “Yes, of course.”
10 s asked9:16Character serial character: The bakerimported-ep01_call1

rendered in a production pipeline with a character bible and recorded cast voices — not reproducible from this repository. Character names and one spoken line were changed for publication, so takes rendered before that change say the original words and the lines check reads one short for them. Each take page shows the exact text its model received.

Same character, separate call: Character serial, block 2 · how consistent each model was

0.0 ssound: off — click a take
H3 Max $0.80 · 13s · 768×1344 lines 4/4 · synth voice · motion 3.35
H3 ref2v $0.76 · 10:07 · 768×1344 lines 4/4 · synth voice · motion 0.95
Kling v3 Pro $1.96 · 6:39 · 1072×1928 lines 3/4 · synth voice · motion 0.74
Wan 2.7 $1.00 · 4:38 · 720×1280 lines 4/4 · synth voice · motion 2.75 · 3 cuts
Seedance 2.0 $1.80 · 3:56 · 720×1280 lines 4/4 · synth voice · motion 3.68
Veo 3.1 $3.20 · 46s · 720×1280 lines 4/4 · synth voice · motion 1.80 · 8.00s
LTX-2 $0.45 · 84s · 576×1024 lines 1/4 · synth voice · motion 0.49
H3 ref2v + voice $0.76 · 16:42 · 768×1344 lines 4/4 · our voices · motion 1.23 · clips · 1 cut
Seedance + voice $1.80 · 4:54 · 720×1280 lines 4/4 · synth voice · motion 2.19
Seedance 2.5 est. price · — · 720×1280 lines 3/4 · motion 0.98
H3 MaxH3 ref2vKling v3 ProWan 2.7Seedance 2.0Veo 3.1LTX-2H3 ref2v + voiceSeedance + voiceSeedance 2.5
Lines heard4/44/43/44/44/44/41/44/44/43/4
Voicesynth 0.208synth 0.227synth 0.183synth 0.2synth 0.201synth 0.21synth 0.113ours 0.945synth 0.277model's own
Motion3.350.950.742.753.681.800.491.232.190.98
Scene changes0003000100
Loudness / peak-20.3 / -5.4-17.7 / -2.9-23.6 / -7-15.2 / -2.4-17.9 / -1.8-18 / -3.6-13.9 / -1.4-14.2 / 0.1-16.2 / -1.2-22.3 / -7.7
Length10.14s10.14s10.04s10.03s10.05s8.00s9.71s10.14s10.05s10.04s
Frame768×1344768×13441072×1928720×1280720×1280720×1280576×1024768×1344720×1280720×1280
Wait13s10:076:394:383:5646s84s16:424:54
Attempts1112111710
Cost$0.80$0.76$1.96$1.00$1.80$3.20$0.45$0.76$1.80

The read

The single-frame model won. H3 Max continued the establishing frame — same baker, same flyer, same counter — and directed the block with a push-in, in 13 seconds for $0.80. Every multi-reference model (H3 ref-to-video, Wan, Seedance, Veo) re-staged the scene from the references instead: better adherence to the shot prompts, worse continuity with the frame, and a cape on the flyer that the bible's 'wings wrapped like a cloak' sentence invited. Kling was the only take to drop a line. Only H3 ref-to-video with the audio reference contains the cast's actual recordings (0.94); Seedance accepts an audio reference and produces a sound-alike (0.28). Two artifacts — a duplicate flyer and a doubled face — are in the establishing frame itself and appear in every single-frame render.

One person's judgment from the takes above, 2026-09-03. The table is the evidence; this is the opinion.

what whisper heard