Mike0021/flux2-klein-apple-emoji-lora

This repository contains LoRA weights for generating Apple-style emoji icons with emj icon as the trigger phrase.

The LoRA was trained for research and experimentation on Apple-style emoji assets. It is not affiliated with, endorsed by, or sponsored by Apple. The raw Apple emoji training images are not included in this repository.

Usage

import torch
from diffusers import Flux2KleinPipeline

pipe = Flux2KleinPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-base-4B", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Mike0021/flux2-klein-apple-emoji-lora", weight_name="pytorch_lora_weights.safetensors")
pipe.enable_model_cpu_offload()

image = pipe(
    "emj icon of a smiling dragon, centered on a plain white background",
    height=1024,
    width=1024,
    num_inference_steps=30,
    guidance_scale=4.0,
).images[0]

Training Summary

• Base model: black-forest-labs/FLUX.2-klein-base-4B
• Trigger phrase: emj icon
• Dataset: 3,783 Apple emoji image/caption pairs prepared from iamcal/emoji-data
• Training images are RGB 1024x1024 composites on a plain white background
• Captions were metadata-derived; the first public baseline uses the shared prompt emj icon for memory reasons

Limitations

• This model is intended for research and experimentation.
• Apple emoji source assets are Apple IP; review the relevant terms before using derivatives commercially.
• The model may reproduce Apple-like visual conventions and should not be presented as an official Apple model.