metadata

base_model: black-forest-labs/FLUX.1-dev
library_name: diffusers
license: openrail++
tags:
  - text-to-image
  - diffusers-training
  - diffusers
  - lora
  - fine-tuned
  - template:sd-lora
instance_prompt: a photo of sks charctrbwy
widget:
  - text: A photo of sks charctrbwy
    output:
      url: image_0.png
  - text: sks charctrbwy in a futuristic setting
    output:
      url: image_1.png
  - text: Portrait of sks charctrbwy wearing medieval attire
    output:
      url: image_2.png

FLUX.1-dev LoRA Fine-Tuning - shahin-canary/charctrbwy

Prompt
sks charctrbwy in a futuristic setting

Prompt
Portrait of sks charctrbwy wearing medieval attire

Model Description

This is a fine-tuned LoRA adaptation of the black-forest-labs/FLUX.1-dev model, created for generating images of the character sks charctrbwy. This model is capable of generating high-quality, customizable images based on text prompts. The fine-tuning process was performed using DreamBooth and was trained to accurately represent sks charctrbwy in various contexts and settings.

Trigger Words

To generate images, use the phrase “a photo of sks charctrbwy” as a prompt starter. Customize prompts with additional context for varied results (e.g., "sks charctrbwy in a serene landscape").

How to Use

To use this model in your code, install the diffusers library and set up the pipeline as shown below:

from diffusers import StableDiffusionPipeline
import torch

model_id = "shahin-canary/charctrbwy"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "A photo of sks charctrbwy in a mystical forest"
image = pipe(prompt).images[0]
image.save("output.png")