Downloads · 30 days
41
40% of all-time downloads
strkyyy/cinestill-800t
cinestill-800t is a text-to-image model from strkyyy. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as openrail++.
Authentic CineStill 800T tungsten film look — the iconic cinematic night aesthetic. This LoRA captures the signature red halation glow around light sources, cool blue shadows balanced for tungsten lighting, fine grain…
Downloads · 30 days
41
40% of all-time downloads
All-time downloads
102
Public
Repo size
99.2 MB
Likes
2
Public
Click a slice to open those files.
.safetensors89.7 MB · 90%
From the Hugging Face model README
Authentic CineStill 800T tungsten film look — the iconic cinematic night aesthetic. This LoRA captures the signature red halation glow around light sources, cool blue shadows balanced for tungsten lighting, fine grain, and that unmistakable neon-soaked nightlife mood.
Trigger with 'c1n3st1ll' in your prompt at a suggested strength of 0.85-1.0. Best paired with FluxGuidance 3.0-4.0 for optimal results.
c1n3st1ll a neon-lit cityscape with reflections in puddles, focus on futuristic architecture
c1n3st1ll portrait of a night owl in dimly lit jazz bar, soft shadows and red halation glow
c1n3st1ll close-up of abandoned street sign under flickering light, cool blue tungsten tones
c1n3st1ll racing car speeding through dark tunnel with intense headlights and blurred motion
c1n3st1ll mood piece capturing the essence of a rainy night in Tokyo, neon lights and reflections
c1n3st1ll abstract composition featuring fine grain texture and halation around light sources
Activate with c1n3st1ll. Recommended strength: 0.9.

diffusersfrom diffusers import AutoPipelineForText2Image
import torch
pipe = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights("strkyyy/cinestill-800t")
image = pipe("c1n3st1ll, your prompt", num_inference_steps=30).images[0]