Run Locally
sparkle-000012.safetensors
38 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
FLUX · LoRAs
by op7418 - Stardust Touch · Stardust Touch · FLUX
Creator notes
A model trained on Tatiana Tsiguleva's Midjourney style code
Can generate stunning light effects, triggered by the word "Sparkle"
Adding elements like water, glass, ocean, space, bokeh, stars, light leaks, or any shiny objects from real life in the prompts can enhance the expressiveness.
Very similar to Perplexity's promotional image style - for layout and generation, you can reference some of their images.
Trigger words
Sparkle
SHA256
0F01F93285997ADF5955DE2B3328702D9FCC4142FD1257EA7AE7C6138C4F407D
ModelTrends.ai Model ID
#17358
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Steps
12
Guidance
3.5
Seed
845755902522387
Size
832x1216
Prompt
A towering, unfinished structure of exposed steel and concrete rises above a dense grid of brutalist city blocks, rendered in stark cinematic realism. The central tower is wrapped with partial data panels—deep blue, crystalline textures embedded with tangled circuit lines and broken holographic displays. A thin fog settles across the city, diffusing the pale gray daylight. Scaffolding, suspended bridges, and dangling maintenance cables weave through the skeleton of the structure. Far below, the surrounding city appears silent and lifeless, built from stacked concrete modules and fractured slabs. A lone figure in a dark coat stands at the edge of a protruding platform, gazing toward the partially illuminated core of the tower. Dust and data particles drift slowly through the air. The perspective is high and vertical, emphasizing depth, isolation, and the scale of forgotten infrastructure. The atmosphere is cold, minimal, and data-choked — a fortress of abandoned information.
in the style of cksc,,, midjourney mix,, Sparkle
<lora:ck-shadow-circuit-000021:0.5> <lora:midjourney-mix:0.56> <lora:sparkle-000012:0.5> <lora:flux_vividizer:0.4>
Settings
Sampler
Euler
Steps
20
Guidance
1
Seed
4091889654
Size
896x1152
Prompt
high resolution digital art of a woman with long hair, holding an old clock with both hands, in the night sky. the woman's eyes are closed and her long voluminous hair is flowing in the breeze. she wears an elegant long dress. the image has a space nebula style, consisting of glowing lights, clouds and stars. the overall image is high quality and vibrant. <lora:FLX-Style-SparkleStardust:1> Sparkle
Settings
Sampler
Undefined
Steps
30
Guidance
3.5
Seed
235089777
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
A hyper-realistic photo, glamour. cinematic upper body photo, Dramatic Shadow with a Bold Look, A brunette woman, she is wearing floral dress adorned with gold, glass crystals and prisms casting rainbow exuding an air of mystery. beam of light on her, Nestled on the woman shoulder is a huge white python snake, excellent dynamic range, makeup, she stand among trees, natural youthful glow. White modern clothes, straight white hair cascading down her shoulders, Her eyes are almond-shaped and striking blue ,accentuated by thick ,eyeliner. Her eyebrows are well-groomed,framing her eyes. arctic circle snow drift, snowing, snowflakes, cold, chill bumps, approaching perfection, dynamic, highly detailed, smooth, sharp focus, intricate details, shallow depth of field, vignette, forest, nature, pink trees, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy,(skin texture:1.4)
Similar Models
AI Models for Image, Video & Text Generation
stardust touch flux is a LoRA for the Flux family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Flux models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
332
Hunyuan Models
198
Ideogram Models
20
Krea2 Models
675
Qwen Models
17
Qwen2 Models
37
Ltx2 Models
151
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
920

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
All Rights Reserved
