Downloads · 30 days
65
10% of all-time downloads
JunkieMonkey69/Chaseinfinity_ZimageTurbo
Chaseinfinity_ZimageTurbo is a text-to-image model from JunkieMonkey69. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
65
10% of all-time downloads
All-time downloads
620
Public
Repo size
171 MB
Likes
6
Public
Click a slice to open those files.
.safetensors170 MB · 100%
From the Hugging Face model README
🧩 LoRA Name: ChaseInfinity_Actress
> Base Model: Tongyi-MAI / Z-Image-Turbo > LoRA Type: Character / Actress > Trigger Word(s): Chase Infinity (demographic descriptors are learned implicitly; name-based prompting recommended) > Recommended Weight: 0.6 – 0.85 (sweet spot ≈ 0.75)
✨ Overview
> This LoRA captures the facial identity, proportions, and high-fashion presence of actress Chase Infinity, optimized for ZimageTurbo. It is trained to maintain strong likeness fidelity across editorial, cinematic, and intimate portrait scenarios, while remaining flexible to varied lighting, wardrobe, and mood setups.
The model emphasizes realistic skin texture, expressive eyes, and confident poses, making it suitable for fashion editorials, luxury interiors, paparazzi-style flash photography, and cinematic close-ups.
🎨 What This LoRA Is Good At
> Strong identity preservation across angles and lighting > High-fashion and editorial portrait aesthetics > Clean, realistic skin rendering with natural highlights > Performs well in both studio and environmental scenes > Consistent results in portrait, mid-shot, and vertical 9:16 compositions
⚙️ Usage Notes
> Best results with portrait, editorial, and cinematic framing > Prompting “Chase Infinity” is sufficient; avoid stacking strong character LoRAs > Works especially well with fashion, luxury interiors, flash photography, and cinematic lighting > Guidance scale ≤ 1 is recommended for native ZimageTurbo behavior
🧪 Example Prompt Chase Infinity, high-fashion editorial portrait, cinematic lighting, luxury interior, confident pose, realistic skin texture, sharp focus
📐 Training Details
> Dataset Size: Captioned image set > Training Resolutions: 512 / 768 > Total Steps: 3,100 > Batch Size: 1 > Content vs Style: Balanced > Noise Scheduler: FlowMatch > Optimizer: AdamW 8-bit > Learning Rate: 1e-4 > Precision: BF16 > Text Encoder Training: Disabled > UNet Training: Enabled > Quantization: QFloat8 (model + text encoder) > Architecture: ZImage Turbo LoRA (LoKR full-rank enabled)
⚠️ Limitations / Notes
> Not intended for anime or heavily stylized cartoon outputs > Extreme facial distortion or exaggerated wide-angle lenses may reduce likeness > Best used alone or with light stylistic LoRAs only
You should use Chase Infinity to trigger the image generation.
Download them in the Files & versions tab.