You can deploy this model and start earning money today!

shiviguptta/
sd-controllora-face-landmarks

Name: sd-controllora-face-landmarks
Availability: InStock

diffusers

safetensors

stable-diffusion

stable-diffusion-diffusers

image-to-image

controlnet

controllora

runwayml/stable-diffusion-v1-5

adapter

creativeml-openrail-m

Views

No views yet

ControlLoRA - Face Landmarks Version

ControlLoRA is a neural network structure extended from Controlnet to control diffusion models by adding extra conditions. This checkpoint corresponds to the ControlLoRA conditioned on Face Landmarks.

ControlLoRA uses the same structure as Controlnet. But its core weight comes from UNet, unmodified. Only hint image encoding layers, linear lora layers and conv2d lora layers used in weight offset are trained.

The main idea is from my ControlLoRA and sdxl control-lora.

Example

Clone ControlLoRA from Github:

$ git clone https://github.com/HighCWu/control-lora-v2

Enter the repo dir:

$ cd control-lora-v2

Run code:

from PIL import Image
from diffusers import StableDiffusionControlNetPipeline, UNet2DConditionModel, UniPCMultistepScheduler
import torch
from PIL import Image
from models.controllora import ControlLoRAModel

image = Image.open('<Your Conditioning Image Path>')

base_model = "runwayml/stable-diffusion-v1-5"

unet = UNet2DConditionModel.from_pretrained(
    base_model, subfolder="unet", torch_dtype=torch.float16
)
controllora: ControlLoRAModel = ControlLoRAModel.from_pretrained(
    "shiviguptta/sd-controllora-face-landmarks", torch_dtype=torch.float16
)
controllora.tie_weights(unet)

pipe = StableDiffusionControlNetPipeline.from_pretrained(
    base_model, unet=unet, controlnet=controllora, safety_checker=None, torch_dtype=torch.float16
)

pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)

# Remove if you do not have xformers installed
# see https://huggingface.co/docs/diffusers/v0.13.0/en/optimization/xformers#installing-xformers
# for installation instructions
pipe.enable_xformers_memory_efficient_attention()

pipe.enable_model_cpu_offload()

image = pipe("Girl smiling, professional dslr photograph, high quality", image, num_inference_steps=20).images[0]

image.show()

You can find some example images below.

prompt: High-quality close-up dslr photo of man wearing a hat with trees in the background

prompt: Girl smiling, professional dslr photograph, dark background, studio lights, high quality

prompt: Portrait of a clown face, oil on canvas, bittersweet expression