metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - image-generation
  - flux
  - safetensors
widget:
  - text: >-
      sketched style,A stick-figure-style robot, and some sci-fi machines, with
      pastel colors, highlight the innocence and romance of children
    output:
      url: images/1f20519208cef367af2fda8d91ddbba674f39b097389d12ee25b4cb1.jpg
  - text: >-
      sketched style,A joyful girl with balloons floats above a city wearing a
      hat and striped pants,
    output:
      url: images/4f534fe804cf803ad5b2ef7478ebdd3f3c7679efa754b625e60aa2a6.jpg
  - text: sketched style,Some happy children stand ready to take pictures
    output:
      url: images/8f2d9a4e8df18a57ae91c96427e0d0e169fe03b3e6a6f0dd6a35da5d.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: sketched style
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md

FLUX.1-dev-LoRA-Children-Simple-Sketch

This is a LoRA trained on FLUX.1-dev for Children's Simple-Sketch by Hongke on Shakker AI.

Showcases

Prompt
sketched style,A stick-figure-style robot, and some sci-fi machines, with pastel colors, highlight the innocence and romance of children

Prompt
sketched style,A joyful girl with balloons floats above a city wearing a hat and striped pants,

Prompt
sketched style,Some happy children stand ready to take pictures

Trigger words

You should use sketched style to trigger the image generation. The recommended scale is 0.8 to 1.5 in diffusers.

Inference

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/FLUX.1-dev-LoRA-Children-Simple-Sketch", weight_name="FLUX-dev-lora-children-simple-sketch.safetensors")
pipe.fuse_lora(lora_scale=1.5)
pipe.to("cuda")

prompt = "sketched style,A joyful girl with balloons floats above a city wearing a hat and striped pants,"

image = pipe(prompt, 
             num_inference_steps=24, 
             guidance_scale=3.5,
            ).images[0]
image.save(f"example.png")

Online Inference

You can also run this model at Shakker AI, where we provide an online interface to generate images.

Acknowledgements

This model is trained by our copyrighted users Hongke. We release this model under permissions. The model follows flux-1-dev-non-commercial-license.