bingbangboom/flux-miniature-worlds

miniature worlds

Prompt

a cat in a field of lavender flowers. Image in the style of MNTRWRLDS.

Prompt

a penguin eating an ice cream, standing on ice floating on water. it is holding a sign that says 'i love ice'. Image in the style of MNTRWRLDS.

Prompt

a dog playing with a ball in a park. Image in the style of MNTRWRLDS.

Prompt

a girl wearing glasses and a scarf, reading a book in a cafe. a burger and a cup is kept on the table. Image in the style of MNTRWRLDS.

Prompt

a cat taking a nap on a work table. the text 'at work' is written on a sign board kept on the table. Image in the style of MNTRWRLDS.

Prompt

a boy and his pet monster watering a potted plant. the text 'do not melt' is written on a text bubble. Image in the style of MNTRWRLDS.

Model description

Flux LoRA for creating miniature scenes. Use 'Image in the style of MNTRWRLDS' to trigger the model. Best with DEV (works well even with fp8). To use with flux1-dev-bnb-nf4 try increasing the LoRA strength (to say 1.3 and then adjust accordingly). If you struggle with text or feel that the prompt adherence is off, try turning model stregth down to like 0.8 or use flux_MNTRWRLDS_000001500.safetensors (and increase its strength as needed). Try easily at https://glif.app/@bingbangboomlab/glifs/cm2bs7pn1000aq4d1pwd5pfg4

Update: Try new flux_MNTRWRLDS_v2.safetensors (at 0.85 strength or as you find suitable). Test the difference for your prompts easily using the above glif link.

Trigger words

You should use Image in the style of MNTRWRLDS to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Training at Glif

Model trained with AI Toolkit by Ostris under the Glif Loradex program by Glif