Run Locally
Aesthetic_Amateur_Photo_V4_Beta_2.safetensors
18 MB · SafeTensor · bf16
Downloads are served by Civitai. Some creators ask for a Civitai login first.
Torrents
Aesthetic_Amateur_Photo_V4_Beta_2.safetensors
18.37 MB · V4 Beta 2 · 0 seeders ·
CivitasBayMagnet link
Torrents are shared peer to peer by their seeders; ModelTrends.ai hosts no files. Open the magnet link with a BitTorrent client and compare the finished file's checksum with the one on the listing.
About This Model
FLUX · LoRAs
by powerpuff -Yet another amateur photo LoRA to improve the realism of Flux. V4 Beta 2 Trained on more images. V4 Beta 1 I have started to create a completely new dataset with only high quality images. For Beta 1 I used 111 images, though I plan to significantly increase it for Beta 2. All images only have the caption "43stet1c", but it isn't needed to mention it in your prompt. This combination seems to produce the best and most consistent results so far. Increase the strength if the effect isn't strong enough.
Creator notes
Another amateur photo LoRA aimed at making images feel more realistic and closer to everyday smartphone or social media photos. Expect sharper details, brighter colors, and a more casual, natural look overall.
Krea V4:
Higher quality dataset, more steps, better captions.
Krea V3:
Similar to V2 but the captions used a tag-style instead of full sentences.
Krea V2:
More steps, more images, completely new captions
Krea V1:
Initial release trained with basic captions.
Z-Image Exp 1:
Experimental version trained with chinese captions.
Only 2000 steps and a small dataset but produces pretty good images.
Trigger:
这张照片是用iPhone 13拍摄的。
Z-Image V2:
More than doubled the steps compared to V1
Stronger effect
Can be used with higher strength
Z-Image V1:
A new version for Z-Image trained on a small dataset.
V4 Beta 2:
Trained on more images.
V4 Beta 1:
I have started to create a completely new dataset with only high quality images. For Beta 1 I used 111 images, though I plan to significantly increase it for Beta 2. All images only have the caption "43stet1c", but it isn't needed to mention it in your prompt.
This combination seems to produce the best and most consistent results so far.
Increase the strength if the effect isn't strong enough.
V3:
Same dataset as V2 but completely recaptioned with Claude 3.5 Sonnet and upscaled to 1024 with Gigapixel.
V2:
Trained on 124 images with no captions at all. Let me know if this works better than V1. Results can be inconsistent, use HiRes fix and Beta scheduler.
V1:
This was trained on a dataset of 61 "aesthetic" images captioned with Claude 3.5 Sonnet.
Trigger words
43stet1c
SHA256
4514C9CB12473F170BAEE4D447B7DF3A07A1A20E29017C3E32F8F5A66B8A46E9
ModelTrends.ai Model ID
#15969
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
Sampler
euler
Steps
20
Guidance
1
Seed
737716820
Size
1664x2432
Prompt
raw photo, detailed 4k, a gorgeous tiny 1 inch tall miniature woman, blonde hair, in a bikini relaxing laying beside a kitchen sink, dish soap bottle towering over her, on a towel, window letting light shine down, plants on windowsill. 43stet1c
Settings
Sampler
Euler
Steps
40
Guidance
1
Seed
513392242
Size
896x1152
Prompt
43stet1c The image shows a woman taking a selfie, styled in a gothic fashion. Her hair is a mix of black and green, with the colors blending in streaks or sections. She has visible tattoos on her arms and possibly other parts of her body, adding to her alternative look. She is wearing various pieces of jewelry, such as rings, necklaces, or bracelets, but notably has no piercings visible. Her makeup is dark, featuring bold black eyeshadow or eyeliner and possibly dark lipstick, contrasted by white highlights on her face, accentuating certain facial features like the eyes or cheekbones. <lora:Aesthetic_Amateur_Photo_V4_Beta_2:1.2>
Settings
Sampler
Undefined
Steps
25
Guidance
3.5
Seed
1903414887
Size
832x1216
Clip skip
2
Weight used
1
Prompt
In the heart of a serene valley, a tranquil lake mirrors the surrounding beauty of lush, rolling hills dotted with vibrant wildflowers in full bloom. A gentle morning mist clings to the surface of the water, catching the soft rays of a golden sunrise breaking through scattered clouds. The scene is rich with detail: a solitary heron stands poised on the lake’s edge, its reflection shimmering in the still water, while a pair of deer graze quietly near the tree line, their silhouettes softened by the haze. Towering pines and oaks frame the vista, their leaves tinged with a subtle mix of deep greens and warm yellows, hinting at the early days of autumn. Above, the sky transitions from a gentle pink and orange gradient to a clear, serene blue, inviting the viewer to bask in the calm and timeless splendor of nature.
Settings
Sampler
Euler
Steps
40
Guidance
1
Seed
13847341
Size
896x1152
Prompt
43stet1c A man is sitting at a table in a restaurant, casually dressed in a t-shirt. In front of him is a burger on a white plate, stacked with a thick beef patty, melted cheese, lettuce, tomato, and a toasted bun. A side of fries sits next to the burger, along with a small dish of ketchup. The restaurant has a cozy atmosphere, with warm lighting, wooden tables, and other patrons visible in the background, engaged in conversation. There’s a decorative plant on the table, and behind him, a large window allows natural light to pour in, with a view of the street outside. <lora:Aesthetic_Amateur_Photo_V4_Beta_2:1.2>
Settings
Sampler
Euler
Steps
40
Guidance
1
Seed
1910499577
Size
896x1152
Prompt
43stet1c The selfie features a woman with a striking gothic style. Her blonde hair is styled sleekly, falling over her shoulders. She wears bold, dramatic makeup with dark, smoky eyeshadow, sharp eyeliner, and matte black lipstick that contrasts with her pale complexion. A black lace choker with a pendant wraps around her neck, complementing her outfit—a fitted black corset-style top with lace detailing. Subtle silver jewelry accentuate her edgy look, while her expression is confident and slightly enigmatic. <lora:Aesthetic_Amateur_Photo_V4_Beta_2:1.2>
Settings
Sampler
Euler
Steps
40
Guidance
1
Seed
4241253808
Size
896x1152
Prompt
43stet1c The image shows a woman standing on a sidewalk, holding a cup of bubble tea. The cup is transparent, with visible tapioca pearls at the bottom and a wide straw poking through the lid. The woman is casually dressed, possibly wearing jeans, a t-shirt, or a light jacket, depending on the weather. She may have a bag or purse slung over her shoulder. The sidewalk around her features typical urban elements such as street signs, parked cars, or nearby buildings. In the background, there may be pedestrians or storefronts, adding to the city-like atmosphere. <lora:Aesthetic_Amateur_Photo_V4_Beta_2:1.2>
Settings
Sampler
Euler
Steps
40
Guidance
1
Seed
1160599356
Size
896x1152
Prompt
43stet1c A table is covered with a variety of fast food items. There is a large pizza with several slices, chicken wings arranged on a plate, a pile of golden fries in a basket or on a tray, and several burgers with buns and toppings visible. Additional items include dipping sauces in small containers, possibly for the wings or fries, and some soda cups with straws. The food is spread out across the table, giving a sense of an abundant, casual meal. <lora:Aesthetic_Amateur_Photo_V4_Beta_2:1.2>
Settings
Sampler
Undefined
Steps
30
Guidance
2
Seed
1933747832
Size
1024x1024
Clip skip
2
Weight used
1
Prompt
43stet1c, after party photo taken during night time, photo features a young woman and a humanoid male alien sitting on a red leather couch on a house backyard, beer bottles on couch, woman is caucasian blond wearing a night dress and male alien has a gray skin with large oval shaped head and large black eyes, male alien is wearing a cowboy hat and a summer shirt with palm trees graphic, both looking at camera and has a wasted expression, flash photo taken from upper knee with bokeh background, random pose, 2000s image
Similar Models
Badges for creators
Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge. Every badge links back to this page.
Badge shape
AI Models for Image, Video & Text Generation
Aesthetic Amateur Photo V4 Beta 2 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
415
Anima Models
519
Chroma Models
17
Flux Models
1,498
Flux 2 / Klein Models
1,239
MiniMax H3 Models
330
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
676
Qwen Models
20
Qwen2 Models
36
Ltx2 Models
152
Stable Diffusion 1.5 Models
7,042
Stable Diffusion XL 1.0 Models
17,420
Zimage Models
815
Wan Models
1,244
Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
All Rights Reserved