SD2_1_Base_Rank_8_CulText_8k

<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. -->

LoRA text2image fine-tuning - iiiiDeal/SD2_1_Base_Rank_8_CulText_8k

These are LoRA adaption weights for stabilityai/stable-diffusion-2-1-base. The weights were fine-tuned on the None dataset.

Intended uses & limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline
import torch
from diffusers import StableDiffusionPipeline


model_path = "iiiiDeal/SD2_1_Base_Rank_8_CulText_8k"
prompt = "A high resolution image of a modern security checkpoint in China, featuring bilingual signage, uniformed personnel, and sleek architectural design."
pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1-base", torch_dtype=torch.float16).to("cuda")

# can probably use a better sampler
image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
image.save("samples/pretrain.png")


pipe.unet.load_attn_procs(model_path)

image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
image.save("samples/finetune.png")

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]