metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - image-generation
  - flux
  - safetensors
widget:
  - text: >-
      A purple lovely plush monster, sitting on the top of a high building in
      New York, looking up at the perspective, Times Square, there are some
      colored balloons, the ground is pink, billboards, rich design sense of the
      picture, excellent advertising ideas
    output:
      url: images/5217c705409cdf78f6d49b1bd234ced636694f580d03a0462679913b.jpg
  - text: >-
      A cartoon 3D monkey lies in the middle of the city,aerial view,shift axis
      photography,
    output:
      url: images/51a716fb6fe9ba5d54c260b70e7ff661d38acedc7fb725552fa77bcf.jpg
  - text: >-
      A colorful cartoon monkey sits on a bus as it rolls down the street in
      Times Square, New York
    output:
      url: images/c5dafa68197f677c6ba55e68e63e94afefe6cf710d80298adc62ab7b.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: null
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-live-3D

This is a LoRA (Live 3D) trained on FLUX.1-dev for 3D elements by Hongke on Shakker AI.

Showcases

Prompt
A purple lovely plush monster, sitting on the top of a high building in New York, looking up at the perspective, Times Square, there are some colored balloons, the ground is pink, billboards, rich design sense of the picture, excellent advertising ideas

Prompt
A cartoon 3D monkey lies in the middle of the city,aerial view,shift axis photography,

Prompt
A colorful cartoon monkey sits on a bus as it rolls down the street in Times Square, New York

Trigger words

Trigger is not required. The recommended scale is 0.9 to 1.3 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-live-3D", weight_name="FLUX-dev-lora-live_3D.safetensors")
pipe.fuse_lora(lora_scale=1.1)
pipe.to("cuda")

prompt = "A colorful cartoon monkey sits on a bus as it rolls down the street in Times Square, New York"

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.