Agusdor/Art_Directed_Stock_Photos_bottles_and_people

Release of the first model in the fine-tuned Loras collection for Flux: Art Directed Stock Photos Series

This model is designed to create photorealistic, professional scenes with a superior aesthetic of people with bottles in everyday settings—perfect for Ads photography.

Combine it with other realistic refinement LoRas and use it in photo enhancement workflows to get the most out of it. I share here some unrefined and uncherry-picked outputs. Try the magic and share your generations! 🧙‍♂️🌟

What is the Art Directed Stock Photos Series? It’s a series of models carefully trained for professional use with Flux. The dataset images were meticulously chosen and manually captioned by me to achieve high-quality professional outputs, so you can use them for more than just hobbyist purposes. Ideal for Graphic Designers, Art Directors, Photographers, and Creative Industry Professionals on a daily basis.

Best setup is:

Strength: 0.8-1.0

CFG: 3-4

Sampling method: Euler - Normal | DPM++2M

Steps: 20-30

Triggers: bottles and people

⬇Download from CivitAI⬇

https://civitai.com/models/1330756

Outputs

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Agusdor/Art_Directed_Stock_Photos_bottles_and_people', weight_name='Art_Directed_Stock_Photos_Bottles_and_People_v1.safetensors')
image = pipeline('your prompt').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers