Autoplay
Run Locally
MM-H3 - Dark and Moody.safetensors
68 MB · SafeTensor · bf16
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
MINIMAX H3 · LoRAs
by kermitfrog1202 - Dark and Moody Lighting
Creator notes
Trigger: Dark_and_Moody
SHA256
6DF7CC37DDD2AFA0F6BC9D4512A092AD4277A907052711E4BC29E0ACD3FAEF12
ModelTrends.ai Model ID
#27462
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
1152x1792
Prompt
Dark_and_Moody
A 12-second 16:9 cinematic shot.
integrated_multimodal_description: [Shot 1] Live-action, cinematic. A closed bowling alley at 3 a.m. Only the pin deck lights are on. The rest of the house is black. One ball sits in the return, still spinning. No logos, no watermarks. One continuous shot.
An old man in a rental shirt two sizes too big stands on lane 7 with a cigarette he is not allowed to light. He picks up the ball with both hands like it might apologize. He approaches. His form is terrible and sincere. The ball leaves his hand, hooks the wrong way, and still somehow clips the 7-pin. The pin hops, thinks about it, and falls. He does not celebrate. He just nods once at the empty seats.
The camera starts behind the approach and dollies with him, then lets the ball travel while it stays on his face.
Camera: 16:9 single dolly, hold on his face after release. No cuts. No slow motion.
Lighting: cold pin-deck fluorescents, black house, one red return light on his knuckles.
overall_soundscape: Ball return motor, the roll, the thin crack of one pin, his breath, distant ice machine.
non_diegetic_music: N/A
Settings
Size
1152x1792
Prompt
dark_and_moody
A 10-second 16:9 cinematic shot.
integrated_multimodal_description: [Shot 1] Live-action, cinematic. A flooded underground garage. Ankle-deep black water. One dying exit sign. A sedan with the driver’s door open like a mouth. No logos, no watermarks. One continuous shot.
A soaked tuxedo sits in the water as if someone stepped out of it and kept going. A hand comes up holding a ruined boutonniere. A young man surfaces, gasps, pins the flower back on like the ceremony is still happening two floors up, and walks toward the sign. He does not look at the car.
The camera floats at waterline and tracks backward in front of him. The sign pulses. The water takes his reflection and ruins it.
Camera: 16:9 water-level backward track. No cuts. No slow motion.
Lighting: sick green strobe, black water, wet wool eating the light.
overall_soundscape: Water, his gasp, shoes, the buzz inside the sign.
non_diegetic_music: N/A
Settings
Size
1152x1792
Prompt
dark_and_moody
A 10-second 16:9 cinematic shot.
integrated_multimodal_description: [Shot 1] Live-action, cinematic. A desert two-lane after sundown. Heat still coming off the asphalt. A payphone that should be dead standing alone in the gravel. No logos, no watermarks. One continuous shot.
A woman in a ruined bridesmaid dress walks out of the dark, lifts the receiver, and listens like someone might still be on the other end. She starts laughing, then talks into the dead line anyway. She says, “Yeah. I’m here. No, the dress made it. The marriage didn’t.” She sits in the dirt because the laugh knocks her down. She wipes her face with the skirt and says, quieter, “If you get this, don’t come get me. I like the quiet.” She hangs up like she might get in trouble for being rude.
The camera starts on the empty road and pans with her to the phone, then holds a medium while she talks, laughs, and sits.
Camera: 16:9 single pan to hold. No cuts. No slow motion.
Lighting: leftover sky, phone chrome, the dress color gone to mud.
overall_soundscape: Insects, cooling metal, her laugh, her dialogue, the receiver clicking home.
non_diegetic_music: N/A
Similar Models
AI Models for Image, Video & Text Generation
dark moody lighting 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
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
