metadata

tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - text: t0yb0x 3d render of a toy design, a rocket
    output:
      url: images/3D__00315_.png
  - text: >-
      t0yb0x 3d render of a cute toy design, wizard in a purple robe, smile,
      isolated color background
    output:
      url: images/3D__00429_.png
  - text: >-
      t0yb0x 3d render of a cute toy design, female broadway singer, holding a
      classic microphone, wearing a red dress, glamour, performing, isolated
      white background
    output:
      url: images/3D__00405_.png
  - text: t0yb0x 3d render of a toy design, a knight, white background
    output:
      url: images/3D__00323_.png
  - text: >-
      t0yb0x 3d render of a detailed toy design, army commando, white
      background, dynamic pose jump
    output:
      url: images/3D__00328_.png
  - text: >-
      t0yb0x 3d render of a cute toy design, lawyer, smile, isolated color
      background
    output:
      url: images/3D__00478_.png
  - text: >-
      t0yb0x 3d render of a toy design, a man is kneeling petting his dog,
      looking downward
    output:
      url: images/3D__00366_.png
  - text: >-
      t0yb0x 3d render of a toy design, a family of 3, man, woman, boy, eating
      at a dining room table, isolated white background
    output:
      url: images/3D__00344_.png
  - text: >-
      t0yb0x 3d render of a cute toy design, witch with a bubbling cauldron,
      stirring the pot, smile, isolated color background
    output:
      url: images/3D__00437_.png
  - text: >-
      t0yb0x 3d render of a toy design, a man is kneeling petting his dog,
      looking downward
    output:
      url: images/example_gmuogicwp.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: t0yb0x, simple toy design, detailed toy design, 3D render
license: bigcode-openrail-m

Toy Box Flux

Prompt
t0yb0x 3d render of a toy design, a rocket

Prompt
t0yb0x 3d render of a cute toy design, wizard in a purple robe, smile, isolated color background

Prompt
t0yb0x 3d render of a cute toy design, female broadway singer, holding a classic microphone, wearing a red dress, glamour, performing, isolated white background

Prompt
t0yb0x 3d render of a toy design, a knight, white background

Prompt
t0yb0x 3d render of a detailed toy design, army commando, white background, dynamic pose jump

Prompt
t0yb0x 3d render of a cute toy design, lawyer, smile, isolated color background

Prompt
t0yb0x 3d render of a toy design, a man is kneeling petting his dog, looking downward

Prompt
t0yb0x 3d render of a toy design, a family of 3, man, woman, boy, eating at a dining room table, isolated white background

Prompt
t0yb0x 3d render of a cute toy design, witch with a bubbling cauldron, stirring the pot, smile, isolated color background

Model description

Toy Box Flux was trained entirely on AI-generated images. The concept was to blend the weights of an existing 3D LoRA by SECourses with my Coloring Book Flux LoRA. The results were incredibly cute, as Flux developed a unique style that I decided to pursue further. I selected approximately 71 synthetic images and used them to train a LoRA focused on the specific style I wanted to achieve.

71 images, 1 repeat, 25 epochs, 32 DIM / 32 ALPHA, 2,486 Steps

FOR THE BEST RESULTS USE EULER OR DEIS SAMPLER

This LoRA works best with objects and human subjects, animals are hit or miss, not enough data in the training images. Something interesting I found is that this actually helps increase the quality in realistic 3D renders of interiors as well.

In v2 I plan to train on more generated outputs intermixed with the pre-existing outputs to create a stronger adherence to this style.

Trigger keyword: 't0yb0x' 'simple toy design' 'detailed toy design'

Recommended strengths: 0.7 - 0.9

Trigger words

You should use t0yb0x to trigger the image generation.

You should use simple toy design to trigger the image generation.

You should use detailed toy design to trigger the image generation.

You should use 3D render to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.