Autoplay
Run Locally
Snorricam_H3.safetensors
125 MB · SafeTensor · bf16
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
MINIMAX H3 · LoRAs
By - nebsh.
Creator notes
Snorricam to avoid to have randomly the harness. Work in T2V / I2V / REF
SHA256
EF42BA0B572AF0D69F42DAC860865601A316ECB9EE6D86DC6C642FAF698C37C2
ModelTrends.ai Model ID
#26892
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Size
1920x1088
Prompt
Block 1: Reference Material Notes
<Picture 1> serves as the locked, unchanging first-frame anchor for the entire 5-second sequence. The subject’s identity — specifically, the Joker’s face with its signature smeared white base, exaggerated red lips, and black tear-streaks extending from his eyes — must remain identical in expression, makeup texture, and lighting intensity. His disheveled dark hair with green undertones is preserved. Wardrobe continuity includes the frayed purple coat over a patterned shirt and green tie. Lighting conditions are fixed: the single dominant streetlamp above him casting a warm glow on his face while the background remains dimly lit by blurred neon signs and ambient city glow. The wet pavement reflecting light and the shallow depth of field blurring the urban environment behind him are maintained throughout.
Block 2: Visual Style & Camera Setup
Live-action cinematic video shot using a Snorricam rig mounted on the Joker’s head, creating an extreme close-up, fisheye lens perspective that distorts the edges of the frame. The visual medium is gritty, high-contrast film stock with a cool color temperature offset by the warm streetlight, producing strong chiaroscuro lighting. Framing is tight on the Joker’s face, with the fisheye lens exaggerating the curvature of the scene around him. Depth of field remains shallow, keeping only the Joker’s face sharply focused while the background street melts into bokeh. The camera is mounted to move with the subject’s body, not the environment.
Block 3: Timed Shot List & Motion Sequence
[0s-0.5s]: The Joker’s head snaps forward slightly, eyes widening as he inhales sharply. His mouth remains closed, lips tensed. The camera, mounted on his head, tilts minutely upward as he lifts his chin.
[0.5s-1.2s]: He begins a slow, deliberate turn to his right (viewer’s left), head rotating 90 degrees while keeping his gaze fixed ahead. His left hand, holding a silver knife, emerges from under his coat, blade glinting briefly in the streetlight. His facial expression intensifies — eyebrows furrow, lips part slightly.
[1.2s-2.7s]: He strides briskly forward, feet moving in real-time pace across the wet pavement. The camera pushes forward with him, maintaining the extreme close-up on his face. His head turns slightly to his left (viewer’s right) as if scanning the alleyway. His right hand swings out in a quick, almost imperceptible gesture, then retracts.
[2.7s-4.2s]: He pauses mid-stride, stopping abruptly. His head rotates fully 180 degrees to face directly toward the viewer. His eyes lock onto the camera with manic intensity. The knife is now held low, pointing slightly downward in front of his torso. His mouth opens wider, revealing teeth, as if about to speak or laugh.
[4.2s-5.0s]: With a sudden jerk, he snaps his head back to the right (viewer’s left), eyes darting rapidly. The camera follows this micro-movement, creating a slight whip-pan effect. His right hand moves quickly to his side, pulling the knife up again. The fisheye lens distorts the background street lights into streaks of red and green as he moves.
Block 4: Audio & Soundscape Direction
Diegetic Sound & Foley:
[0s-0.5s]: A sharp intake of breath, followed by the faint sound of raindrops hitting wet pavement.
[0.5s-1.2s]: The metallic *clink* of the knife being drawn from his coat pocket, accompanied by the rustle of fabric as he shifts weight.
[1.2s-2.7s]: Heavy, wet footsteps echoing on the pavement, each step synchronized with his stride. A low, rhythmic *thump-thump-thump* of his heart, audible through the audio mix.
[2.7s-4.2s]: A sudden, deep inhale — a gasp — followed by the soft *hiss* of air escaping his lips as he prepares to speak. The knife makes a subtle *tink* against his coat.
[4.2s-5.0s]: A rapid, metallic *snick* as the knife is re-sheathed. A final, faint *splash* of water as he steps on a puddle.
Dialogue / Voiceover:
< d > “You’re all going to die... and I’m gonna be the one who laughs.” </d>
Delivered at 0.8x normal speed, voice rising in pitch and volume, ending with a sharp, manic laugh that cuts off at 5.0s.
Non-Diegetic Score:
Genre: Industrial electronic with heavy bass and glitchy percussion. Tempo: 120 BPM. Entry: Starts at 0.5s, building steadily. Emotional progression: Starts tense and ominous, peaks at 3.0s with a distorted synth stinger, then drops into a pulsing, mechanical rhythm that fades slightly as the Joker turns away at 4.2s, leaving a lingering, unresolved beat until 5.0s.
Similar Models
Badges for creators
Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.
AI Models for Image, Video & Text Generation
snorricam h3 is a LoRA for the MiniMax H3 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other MiniMax H3 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
332
Hunyuan Models
198
Ideogram Models
20
Krea2 Models
675
Qwen Models
17
Qwen2 Models
37
Ltx2 Models
151
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
920

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
All Rights Reserved

