How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("AlanB/TransformersStyle")

prompt = "UNICODE\u0000\u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000T\u0000r\u0000a\u0000n\u0000s\u0000f\u0000o\u0000r\u0000m\u0000e\u0000r\u0000s\u0000S\u0000t\u0000y\u0000l\u0000e\u0000:\u00001\u0000.\u00000\u0000>\u0000 \u0000T\u0000r\u0000a\u0000n\u0000s\u0000f\u0000o\u0000r\u0000m\u0000e\u0000r\u0000s\u0000S\u0000t\u0000y\u0000l\u0000e\u0000 \u0000L\u0000i\u0000g\u0000h\u0000t\u0000_\u0000p\u0000i\u0000n\u0000k\u0000,\u0000 \u0000G\u0000r\u0000e\u0000e\u0000n\u0000,\u0000 \u0000b\u0000e\u0000e\u0000t\u0000l\u0000e\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000L\u0000o\u0000w\u0000R\u0000a\u0000:\u00000\u0000.\u00003\u0000>\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000a\u0000d\u0000d\u0000_\u0000d\u0000e\u0000t\u0000a\u0000i\u0000l\u0000:\u00000\u0000.\u00005\u0000>\u0000"
image = pipe(prompt).images[0]

Transformers Style LoRA 1.5

Prompt
UNICODE<lora:TransformersStyle:1.0> TransformersStyle Light_pink, Green, beetle <lora:LowRa:0.3> <lora:add_detail:0.5>

Model description

Legends say that a transformer started this whole thing. Copied from https://civitai.com/models/216460/transformers-style-autobots-transform-and-roll-out

This model supports multiple colors.

Try prompting for multiple colors in the prompt, and you're likely to get a good mix of them in the subject.

Usage Use the trigger word: "TransformersStyle" along with the LoRA to activate it.

Example prompt: TransformersStyle blue, red, white, blender<lora:TransformersStyle:0.8>

I've found that most settings work well with this model. No special samplers or CFG-scale.

Tips & Tricks Here is a list of words that can enhance the quality of your prompts when it comes to a style like this:

mechanical technical hi-tech sci-fi I may be using the following extensions in the reference images: FreeU or ADetailer / Face Editor. I may also be using a specific Hires Checkpoint (swaps to another model when doing the hires steps). If your results don't match mine exactly, this may explain why.

Training Data included

Like it?

https://ko-fi.com/mnemic

https://www.buymeacoffee.com/mnemic

Trigger words

You should use TransformersStyle to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Downloads last month
8
Inference Examples
Examples
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AlanB/TransformersStyle

Adapter
(2741)
this model

Space using AlanB/TransformersStyle 1