Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Lecture automatique
Exécuter en local
aswhm_lora_v1_500.safetensors
148 MB · SafeTensor · bf16
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<asmr-audio-h3>
À propos de ce modèle
MINIMAX H3 · LoRA
Créé par
AdaptiveVision
sur Civitai
by AdaptiveVision - ASMR Trigger & Audio Minimax H3 - High quality audio with whisper and mouth sounds. Trained on T2V but supports also I2V. 720x1280 resolution with 15-30 steps. Weight 0.75-0.8 is recommended
Notes du créateur
ASMR Trigger & Audio LoRA for Minimax H3 High quality audio with whisper and mouth sounds Trained on T2V but supports also I2V 720x1280 resolution with 15-30 steps Weight 0.6-0.8 is recommended Prompt: she is holding mic in one hand, she leans her head close to the mic and whispers: 'text here'
1,580 téléchargements · 130 j'aime sur Civitai
SHA256
F25636D61B8D0EAF5E6DE7EE7F10C5A838E474FAFABFF9AB4CBB1B71E0F374D0
ID de modèle ModelTrends.ai
#27200
Signaler le contenu
Rendus d'exemple
Prompts et réglages partagés par les personnes qui ont réalisé ces rendus sur Civitai. Choisissez un rendu pour voir comment il a été fait.
Réglages
Taille
736x1120
Prompt
integrated_multimodal_description: [Shot 1] Live-action, cinematic ASMR style, extreme close-up of a 22-year-old Korean idol woman with soft black hair, wearing casual tube top, fair skin and glossy pink lips, seated at a simple wooden table under soft warm indoor lighting. Close to a white ASMR microphone on the table in front of her on the left. A red-and-white KFC paper bucket is next to her at the right. She lifts a crispy fried chicken drumstick toward her mouth with both hands. The camera holds a static tight shot on her lips and the chicken as she slowly bites into the golden skin, pulling a strand of meat free with her teeth. Oil glistens on her lower lip. She chews deliberately with small open-mouth movements, then takes another slow bite while her tongue briefly appears to catch a crumb. She gets her mouth very close to the microphone at the left and whispers quietly: <d>[English, whisper] "Mmm, so good..."</d> overall_soundscape: Crisp crackling of fried chicken skin breaking under teeth, wet chewing and soft saliva sounds, quiet breathing through the nose, faint rustle of the paper bucket, and the subtle sticky sound of greasy fingers. non_diegetic_music: N/A
Réglages
Étapes
8
Taille
512x800
Prompt
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1] Live-action, cinematic, soft and intimate lighting suited to an ASMR setting, the female influencer shown in <Picture 1> remains seated in her chair exactly as established, preserving her appearance, the table, and the white ASMR microphone resting in front of her from the reference image. The camera holds a static shot throughout, with the position, framing, and lens completely still from start to finish. From 00:00.000 to 00:02.500, without breaking eye contact with the camera, she slowly leans her face forward and downward toward the microphone, closing the distance between her lips and it in an unhurried, deliberate motion. From 00:02.500 to 00:06.500, now close beside the microphone, she whispers softly and intimately, her voice hushed to barely above a breath, A white subtitle reading "The Lusty Argonian Maid, v1." appears at the bottom of the frame. <d>[Japanese] アルゴニアンのじじょ、だいいっかん</d> She draws a small breath and continues, whispering: A white subtitle reading "Author : Crassius Curio" appears at the bottom of the frame. <d>[Japanese] クラッシウス・キュリオ、ちょ</d> From 00:07.000 to 00:10.000, She draws a small breath and continues, she whispers softly and intimately, her voice hushed to barely above a breath, A white subtitle reading "Act IV, Scene III, continued" appears at the bottom of the frame. <d>[Japanese] だいよんまく、だい3シーン、続き</d> From 00:10.500 to 00:14.500, She draws a small breath and continues, she whispers softly and intimately, her voice hushed to barely above a breath, A white subtitle reading "Certainly not, kind sir. I am here but to clean your chambers" appears at the bottom of the frame. <d>[Japanese] とんでもありません、だんなさま。ただお部屋の掃除に来ただけです。</d> overall_soundscape: Her breathing is soft and audible as she leans in, and her whispered words carry a light, airy quality with the characteristic close-mic'd intimacy of ASMR audio, each soft consonant and breath rendered with delicate clarity. non_diegetic_music: N/A
Réglages
Étapes
10
Seed
189240300
Taille
704x960
Poids utilisé
1
Prompt
she is holding a glass of wine in one hand, she leans her head close to the camera and whispers: 'You have been very patient. Take off your shirt.'
Modèles d'IA pour générer image, vidéo et texte
asmr audio h3 est un LoRA pour la famille MiniMax H3, référencé sur ModelTrends.ai, un catalogue en lecture seule de modèles d'IA open source pour l'image, la vidéo et le texte. Comparez-le aux autres modèles MiniMax H3, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Parcourir par famille de modèles
Voir tous les modèles