Downloads · 30 days
18
24% of all-time downloads
CinematicStyle-v1
nickqian/CinematicStyle-v1
CinematicStyle-v1 is a text-to-image model from nickqian. 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.
All-time downloads
76
Public
Repo size
6.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.9 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Access
- Public
- Created
- Jan 22, 2026
- Updated
- Jan 22, 2026
- SHA
- d20ee6dd
Base models
Model card
From the Hugging Face model README
SDXL-CinematicStyle-v1.0
📌 Model Overview
| Item | Details |
|---|---|
| Base Model | stabilityai/stable-diffusion-xl-base-1.0 |
| Model Type | SDXL Full Checkpoint (safetensors format, ~6.8GB) |
| Fine-tuning Data | 8000 high-resolution (1024×1024) classic movie frames (Sci-Fi/Neo-Noir/Drama/Epic) |
| Fine-tuning Method | Full parameter fine-tuning (fp16 mixed precision) |
| License | Apache-2.0 (commercial/non-commercial use allowed) |
| Compatibility | Diffusers >=0.24.0 / Stable Diffusion WebUI / ComfyUI |
| Core Feature | Movie-level lighting/composition/color grading rendering |
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Languages
- en
- Created
- Jan 22, 2026
- Updated
- Jan 22, 2026