Try if you want, but I am not sure this lora helps the generation of h3 for the same scene. This is a testing lora. I need to figure out the penis rendering issue. Will add a dataset of pictures along to the video dataset to refine the penis, but I am still not sue is worthed spending more time on this lora It works for both I2V and T2V Example of prompt: integrated_multimodal_description: [Shot 1] pssMB, A white woman with shoulder-length straight black hair sits upright on the floor directly facing forward in front of a white leather sofa, accented by two large plush black fur throw pillows against a muted pale turquoise wall. She wears a tight-fitting orange top paired with a thick black spiked choker. To her immediate right stands a man holding his penis, releasing a heavy, voluminous, bright golden-yellow stream of piss pssMB aimed precisely toward her open mouth. The thick, vibrant liquid cascades continuously, creating a stark, luminous color contrast against the room. Her eyelids remain partially lowered, brows drawn together in concentration or mild distress as highly visible, brightly colored droplets pool heavily along her chin and upper lip. Her facial muscles tense intermittently, causing slight puckering motions in her cheeks indicative of sensory overload from the high-volume ingestion. Behind them, the plain ceiling is cast in moody, low-key shadow, replacing soft daylight with a darker environment to forcefully emphasize the glowing fluid dynamics. The camera angle hovers just below eye level in a mid-frame focus centered on the woman’s profile, capturing her upward gaze aligned perfectly with the descending heavy flow. This tight framing isolates her micro-expressions—tightened lips and intense anticipation—as the vivid stream splashes continuously before her.overall_soundscape: Silence cut by heavy, continuous liquid splashing and deep, shifting stream impacts. Secondary audio includes dynamic background dialogue, abrupt gagging and vomiting noises, gentle bubbling from an out-of-frame reservoir, and low ambient indoor room tone.non_diegetic_music: na

Pissed On_Coach_H3

not sure it makes a difference on H3 base model generation

minimax_h3_pss_longcap_t2v_rev2_000003000.safetensors

minimax_h3_pss_longcap_t2v_rev2_000003900.safetensors

minimax_h3_pss_longcap_t2v_rev2_000003700.safetensors

minimax_h3_pss_longcap_t2v_rev2.safetensors

minimax_h3_pss_longcap_t2v_rev2_000003500.safetensors

v1.0

<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Try if you want, but I am not sure this lora helps the generation of h3 for the same scene. <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">This is a testing lora. <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">It works for both I2V and T2V <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Example of prompt: grated_multimodal_description: [Shot 1] A white woman with shoulder-length straight black hair sits upright on the floor directly facing forward in front of a white leather sofa with two large plush black fur throw pillows against a pale turquoise wall. She wears a tight-fitting orange top and a thick black spiked choker. Immediately to her right at face level, a man is kneeling or standing close beside her, holding a tool directly aligned with her face. From the nozzle of the tool held tightly in his hand right next to her, a heavy jet of liquid pssMB shoots horizontally forward, colliding directly with her chin and splashing outward aimed precisely toward her open mouth. Her eyelids remain partially lowered, brows drawn together in concentration as droplets accumulate along her chin and upper lip line. Facial muscles tense intermittently with slight puckering motions. The camera hovers just below eye level, capturing the close spatial alignment between the man's tool and her face.overall_soundscape: silence except for gentle bubbling noises emanating softly from the device held in-frame by the man, dynamic background dialogue, shifting liquid stream sounds, gagging, and ambient indoor noise.non_diegetic_music: na

Files with SHA256: 2fe069469325a598e37bba90c681188064558f6db33f97932c8c991affff918a