Lecture automatique
Exécuter en local
MM-H3 - Whispering.safetensors
591 MB · SafeTensor · bf16
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
À propos de ce modèle
MINIMAX H3 · LoRA
by kermitfrog1202 - Whispering
Notes du créateur
Trigger: He/She whisper "Insert dialogue here."
Minimax H3
Recommended Lora Strength: 1
SHA256
7BF28BA58BA97002543EBF6DA8CD1FC445451AF9311A4A4B621F1116F4E66EAD
ID de modèle ModelTrends.ai
#26718
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
576x896
Prompt
A beautiful woman with soft, elegant features and long flowing hair stands in a warmly lit room, wearing an elegant red slip dress that drapes smoothly over her figure. She leans in close to the camera, her expression playful and intimate, and whispers “I have been testing and trying to figure out optimum training settings for mini max h3. There is still progress to be made but rest assured… we will figure it out!” She then giggles softly. The camera holds a tight, intimate medium close-up that slowly pushes in as she leans forward, dynamic cinematic lighting with warm practical lamps creating soft volumetric glow, gentle highlights on her skin and the silky fabric of the dress, and shallow depth of field, ambient sounds of her whispered voice, light giggle, and quiet room atmosphere.
Réglages
Taille
640x768
Prompt
7s, 5:6 vertical, cinematic photorealism, dramatic lighting. Use <Picture 1> as the exact visual reference and opening frame.
A blonde woman ASMR artist says in a whisper "I know you love playing with ComfyUI, but I am lonley, you should come over right now " as she twists her hair around her fingers playfully smiling.
no music.
No cuts, no multi-shots, no scene change, no camera-angle changes, no identity drift, no extra characters, no deformed anatomy, no extra limbs, no warped hands, no clipping, no unrealistic movement, no cartoon style, no text overlay, no subtitles, no watermark, no flickering, no low-detail textures.
Réglages
Taille
1408x2496
Prompt
How the reference pictures align with the target video — <Picture 1> (from [Shot 1]) aligns with the 0.00-second mark of the target video.
integrated_multimodal_description: [Shot 1] 2D-anime style, a medium close-up shot focuses on the upper body of a blonde anime girl wearing a white frilly blouse and brown ribbon. At 00:00.000, she is looking directly at the camera with blue eyes, her expression soft and maternal. She speaks in a gentle tone: <d>[English] "oh baby. You had a bad day? come here." </d> As she finishes speaking, the camera perspective shifts to a first-person point of view from the viewer's position. The viewer walks forward toward the girl, resting his head on her lap as she looks down at him with a smile. Her chest rises and falls gently with soft breathing. At 00:03.500, she whispers, <d>[English] "Shhh, there, mommy's here... it's ok" </d> while using both hands to caress the viewer's hair. Her breasts move slightly with her breathing and body movement. The lighting remains warm and intimate throughout.
overall_soundscape: Soft, rhythmic breathing sounds from the girl mixed with the gentle rustling of fabric as she moves. A faint, comforting ambient hum fills the background.
non_diegetic_music: Sweet, recomforting motherly embrace music ambiance, featuring warm piano chords and soft strings that swell gently during the embrace.
Réglages
Étapes
8
Seed
903100749
Taille
704x960
Poids utilisé
0.7
Prompt
she say I am your naughty girl is our secret shhhhhh
Modèles similaires
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.
Modèles d'IA pour générer image, vidéo et texte
whispering 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
Modèles Text / LLM
415
Modèles Anima
519
Modèles Chroma
15
Modèles Flux
1,495
Modèles Flux 2 / Klein
1,238
Modèles MiniMax H3
330
Modèles Hunyuan
204
Modèles Ideogram
20
Modèles Krea2
676
Modèles Qwen
20
Modèles Qwen2
36
Modèles Ltx2
152
Modèles Stable Diffusion 1.5
7,027
Modèles Stable Diffusion XL 1.0
17,373
Modèles Zimage
815
Modèles Wan
1,244

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
Tous droits réservés




