thorjank/windy-storm

windy_storm — LoRA

LoRA adapter trained for the concept/style "windy_storm".

Trigger word

Use this token in your prompt:

• windy_storm

Base model

• Tongyi-MAI/Z-Image-Turbo

Files

• *.safetensors — LoRA weights
• config.yaml — training configuration
• (optional) log.txt — training log

How to use

A) ComfyUI / AUTOMATIC1111

1. Put the .safetensors file into your LoRA folder.
2. Prompt example:
   • windy_storm, portrait photo, natural light, high detail

(Adjust LoRA strength to taste, e.g. 0.6–1.0.)

B) Diffusers (generic example)

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "Tongyi-MAI/Z-Image-Turbo",
    torch_dtype=torch.bfloat16
).to("cuda")

# Replace with your actual repo + filename on the Hub:
pipe.load_lora_weights("<YOUR_REPO_ID>", weight_name="<YOUR_LORA_FILENAME>.safetensors")

prompt = "windy_storm, portrait photo, natural light, high detail"
image = pipe(prompt).images[0]
image.save("out.png")