metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - image-generation
  - flux
  - safetensors
widget:
  - text: >-
      Installation art style, A colorful inflatable bear is wrapped in a clear
      plastic bag against a white background,dolls made from inflatable garbage
      bags,colorful,huge toys,on a white background,artist's
      exhibition,environmental art,
    output:
      url: images/6e086917898ed6abfa2ee8b7534efdeb741fe03022d2aeaf7fc27c79.jpg
  - text: >-
      Installation art style, Inflatable transparent plastic bag full of Coke
      bottles
    output:
      url: images/42e944819b43869a03dc252d10409b5944a62494c7082816121016f9.jpg
  - text: >-
      A colorful plastic-wrapped figure resembling a bird sits against a white
      background with a transparent plastic bag draped over its shoulder
    output:
      url: images/2063ac89e584b7507cc1d11535987e8ec48f43c61bb12b8a6865d2ac.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Inflatable plastic bag
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-Garbage-Bag-Art

This is a LoRA (Garbage-Bag-Art) trained on FLUX.1-dev by Hongke on Shakker AI.

Showcases

Prompt
Installation art style, A colorful inflatable bear is wrapped in a clear plastic bag against a white background,dolls made from inflatable garbage bags,colorful,huge toys,on a white background,artist's exhibition,environmental art,

Prompt
Installation art style, Inflatable transparent plastic bag full of Coke bottles

Prompt
A colorful plastic-wrapped figure resembling a bird sits against a white background with a transparent plastic bag draped over its shoulder

Trigger words

You should use Inflatable plastic bag as trigger words. The recommended scale is 1.0 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-Garbage-Bag-Art", weight_name="FLUX-dev-lora-Garbage-Bag-Art.safetensors")
pipe.fuse_lora(lora_scale=1.1)
pipe.to("cuda")

prompt = "Installation art style, A colorful inflatable bear is wrapped in a clear plastic bag against a white background,dolls made from inflatable garbage bags,colorful,huge toys,on a white background,artist's exhibition,environmental art,"

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

Online Inference

You can also download 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.