F L U X.1 dev Lo R A live 3 D

Shakker-Labs

Introduction

FLUX.1-DEV-LORA-LIVE-3D is a LoRA model designed for integrating 3D elements in image generation. It is based on the FLUX.1-dev model and utilizes diffusers for rendering high-quality 3D images. The model is particularly suited for creating visually rich scenes with a focus on text-to-image conversion.

Architecture

The model leverages the foundational FLUX.1-dev architecture, enhanced with LoRA (Live 3D) training to incorporate 3D visual elements. It supports various tags, including text-to-image, stable-diffusion, and safetensors, ensuring compatibility with multiple pipelines for image generation.

Training

The model was trained to incorporate 3D features, allowing for the creation of complex scenes. Training was conducted by Hongke, a user on Shakker AI, and the process involved integrating LoRA techniques to enhance 3D capabilities.

Guide: Running Locally

To run the FLUX.1-DEV-LORA-LIVE-3D model locally, follow these steps:

  1. Install the necessary packages:

    pip install torch diffusers
    
  2. Load the model and configure it for 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")
    
  3. Generate an image using a specific prompt:

    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")
    

For optimal performance, consider using cloud GPUs, such as those offered by Google Cloud or AWS.

License

The FLUX.1-DEV-LORA-LIVE-3D model is released under the flux-1-dev-non-commercial-license. The full license details can be found here. This license allows usage for non-commercial purposes, and users are required to adhere to the specified terms and conditions.

More Related APIs in Text To Image