happyzjp/image_lora_Image-005

LoRA Model

This is a LoRA (Low-Rank Adaptation) model fine-tuned from black-forest-labs/FLUX.1-dev.

LoRA Configuration

• Rank (r): 16
• Alpha: 32
• Target Modules: proj_out, to_v, to_out.0, proj_in, to_k, to_q

Usage

With Diffusers

from diffusers import DiffusionPipeline
import torch

# Load base model
pipe = DiffusionPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev",
    torch_dtype=torch.float16
)
pipe = pipe.to("cuda")

# Load LoRA weights
pipe.load_lora_weights("YOUR_USERNAME/YOUR_REPO_NAME")

# Generate image
image = pipe(
    prompt="your prompt here",
    num_inference_steps=30,
    guidance_scale=7.5
).images[0]

image.save("output.png")

Training

This model was trained using the Satori network.

License

This model is released under the Apache 2.0 license.