README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
    sculptur3 sculpture of Squidward, a distressed marble with detailed texture
    head bust on a pedestal, his tentacles on his face are individually visible,
    the scene is an intimate garden scene showcase with velvet blue curtains and
    yellow cords
  output:
    url: images/ComfyUI_11077_.png
- text: >-
    sculptur3 sculpture of a bronze head bust, the subject is a large goat, the
    scene is an intimate museum showcase with velvet red curtains and yellow
    cords
  output:
    url: images/ComfyUI_11048_.png
- text: >-
    sculptur3 sculpture of Nosferatu, a distressed marble with detailed texture
    head bust on a pedestal, his fanged teeth individually visible, the scene is
    an intimate garden scene showcase with velvet blue curtains and yellow cords
  output:
    url: images/ComfyUI_11079_.png
- text: >-
    sculptur3 sculpture of a bronze head bust, the subject is a large rhino, the
    scene is an intimate museum showcase with velvet red curtains and yellow
    cords
  output:
    url: images/ComfyUI_11050_.png
- text: >-
   sculptur3 sculpture of a limestone with detailed texture head bust on a pedestal, the subject is a woman's shoulder and head her breasts are draped in a cloth, the scene is an intimate garden scene showcase with velvet blue curtains and yellow cords
  output:
    url: images/ComfyUI_11056_.png
- text: >-
    sculptur3 bizarre mechanic dreamy metallic skeletal with
    {silver|gold|red|plastic|natural stone|agate|fluorite}, surrealism art,
    fully body bust, museum piece, geometric modern fantasy design with a flair
    for the strange (outdoors scenic idyllic)
  output:
    url: images/ComfyUI_11207_.png
- text: >-
    sculptur3 sculpture a closeup view of large metal steel frame gleaming,
    geometric, fluid, creature sculpture towers and is contrasted and surrounded
    by tall topiaries studio set in a stormy purple sky landscape in Europe, the
    cold light showcases the detail work in the chiseled aged appearance 
  output:
    url: images/ComfyUI_11293_.png
- text: >-
    sculptur3 metallic steel frame surrealism sculpture of a full body skeletal
    forms frame character horse with a man riding it, museum piece
  output:
    url: images/ComfyUI_11104_.png
- text: >-
    sculptur3 made of distressed steel and gold, metal hollow frame
    construction, mechanic hybrid cow, black night background, even lighting,
    professionally photographed from a ground angle 
  output:
    url: images/ComfyUI_11331_.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: sculptur3, sculpture
license: creativeml-openrail-m
---
# Sculpture Flux

<Gallery />

## Model description 

Sculpture Flux draws from the Art Institute of Chicago&#39;s prestigious collection of high-resolution public domain images, capturing the nuanced textures, dynamic forms, and timeless beauty of classical sculpture. While masterfully rendering the exquisite details of carved stonework, this versatile concept model transcends traditional materials to generate bold contemporary pieces in marble, bronze, steel, and beyond. Great for visualizing everything from classical busts to abstract modernist forms, each generation maintains the weight, presence, and dimensional complexity inherent to sculptural art.

FOR THE BEST RESULTS USE EULER SAMPLER

Experiment with lowering the guidance scale from the default of 3.0-3.5 down to 2.5 to allow for more creative prompting, doing this will allow for more flexibility both in form and materials. The LoRA was trained primarily on busts but seems flexible enough for figures and full bodies as well.

This LoRA was trained with 22 images captioned with Joy Caption Batch, 2 repeats, 2 batch, 80 epochs, 32 DIM&#x2F;32 ALPHA for a total of 1760 Steps.

Next phases: Since the outputs are so strong I want to make a v2 of this LoRA with a mixture of real images and AI-genereated images to allow for more flexibility in the styles by default.

Please support my research, I want to explore the fine-tuning of Flux to create better LoRAs. Cloud compute companies don&#39;t accept buzz! 🤣 (https://ko-fi.com/renderartist)
 ⬅ Thank you!

Trained with Kohya, tested in ComfyUI.

## Trigger words

You should use `sculptur3` to trigger the image generation.

You should use `sculpture` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/renderartist/sculptureflux/tree/main) them in the Files & versions tab.