[HY1.5] [Game Design] 3DCG Graphics - v1.0

[HY1.5] [Game Design] 3DCG Graphics

LORA
Original


Updated:

The "Core Formula" for Success

According to the official handbook, your prompt should follow this sequence:

Prompt = Subject + Motion + Scene + [Shot Type] + [Camera Movement] + [Lighting] + [Style] + [Atmosphere]

Strategic "Enhancer" Keywords

  • Motion/Dynamics → Surging, gliding, fluid, pirouette, accelerating, subtle crinkling, fluttering.

  • Lighting → Warm golden hour, cool daylight, soft spotlight, harsh shadows, neon-lit, volumetric lighting.

  • Cinematography → Dolly in/out, horizontal tracking shot, low-angle adjustment, 360-degree surround, rack

  • Style/Texture → Photorealistic, cinematic film grain, minimalist, cyberpunk, high-contrast, intricate textures.

  • Spatial Details → Foreground, background, center of the frame, left/right side, overlapping.

Advanced Prompting Techniques

  • Sequential Logic: Use "process" words to guide the AI through time.

    Example: "First... then... next... meanwhile... finally..."

  • Action Details over Emotions: Don't say "a happy boy." Say "a boy smiles, eyes crinkling slightly."

  • Text Generation: To render text accurately, use quotation marks.

    Example: A neon sign that says "NEO TOKYO" flickering in the rain.

  • Negative Prompting: While Hunyuan 1.5 is better at following instructions, standard negative prompts still help:

    static, blurry, low resolution, distorted, watermark, jittery motion, morphing.

Version Detail

Trained by Tensor
HunyuanVideo_1_5_480P Text2Video
1

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts