Hugging Face's logo

segmind
/
tiny_lora_mxtun3_style

Text-to-Image
Diffusers
bksdm
bksdm-ttiny
stable-diffusion
stable-diffusion-diffusers
Model card Files Community
tiny_lora_mxtun3_style / README.md
mixy89's picture
mixy89
Update README.md
4f40f03
preview code
|
raw
history blame contribute delete
1.41 kB
metadata
license: creativeml-openrail-m
base_model: SG161222/Realistic_Vision_V4.0
datasets:
  - recastai/LAION-art-EN-improved-captions
tags:
  - bksdm
  - bksdm-ttiny
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
inference: true

Text-to-image Distillation

This pipeline was distilled from SG161222/Realistic_Vision_V4.0 on a Subset of recastai/LAION-art-EN-improved-captions dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Portrait of a pretty girl']:

val_imgs_grid

This Pipeline is based upon the paper. Training Code can be found here.

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("segmind/tiny-sd", torch_dtype=torch.float16)
#Load LoRA finetune
pipeline.load_lora_weights("segmind/tiny_lora_mxtun3_style", weight_name="sd15_tiny_mxtun3_style_lora.safetensors")
prompt = "Portrait of a pretty girl"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

  • Steps: 125000
  • Learning rate: 1e-4
  • Batch size: 32
  • Gradient accumulation steps: 4
  • Image resolution: 512
  • Mixed-precision: fp16