Wiki-Model / app.py
Pclanglais's picture
Update app.py
9afb445
import spaces
import gradio as gr
import torch
from diffusers import LCMScheduler, AutoPipelineForText2Image
from diffusers import AutoPipelineForInpainting, LCMScheduler
from diffusers import DiffusionPipeline, LCMScheduler
from PIL import Image, ImageEnhance
import io
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
variant="fp16",
torch_dtype=torch.float32
).to("cuda")
# set scheduler
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
# Load and fuse lcm lora
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl", adapter_name="lcm")
pipe.load_lora_weights("Pclanglais/wiki-model", weight_name="pytorch_lora_weights.safetensors", adapter_name="mickey")
# Combine LoRAs
pipe.set_adapters(["lcm", "mickey"], adapter_weights=[1.0, 1.0])
pipe.fuse_lora()
@spaces.GPU
def generate_image(prompt, num_inference_steps, guidance_scale):
model_id = "stabilityai/stable-diffusion-xl-base-1.0"
adapter_id = "latent-consistency/lcm-lora-sdxl"
pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.float32, variant="fp16")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.to("cuda")
# Load and fuse lcm lora
pipe.load_lora_weights(adapter_id)
pipe.fuse_lora()
# Generate the image
image = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale).images[0]
return image
def inpaint_image(prompt, init_image, mask_image, num_inference_steps, guidance_scale):
pipe = AutoPipelineForInpainting.from_pretrained(
"diffusers/stable-diffusion-xl-1.0-inpainting-0.1",
torch_dtype=torch.float32,
variant="fp16",
).to("cuda")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")
pipe.fuse_lora()
if init_image is not None:
init_image_path = init_image.name # Get the file path
init_image = Image.open(init_image_path).resize((1024, 1024))
else:
raise ValueError("Initial image not provided or invalid")
if mask_image is not None:
mask_image_path = mask_image.name # Get the file path
mask_image = Image.open(mask_image_path).resize((1024, 1024))
else:
raise ValueError("Mask image not provided or invalid")
# Generate the inpainted image
generator = torch.manual_seed(42)
image = pipe(
prompt=prompt,
image=init_image,
mask_image=mask_image,
generator=generator,
num_inference_steps=num_inference_steps,
guidance_scale=guidance_scale,
).images[0]
return image
def generate_image_with_adapter(prompt, num_inference_steps, guidance_scale):
generator = torch.manual_seed(0)
# Generate the image
image = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale, generator=generator).images[0]
return image
with gr.Blocks(gr.themes.Soft()) as demo:
with gr.Row():
image_output = gr.Image(label="Generated Image")
with gr.Row():
with gr.Accordion(label="Wiki-Mouse Image Generation"):
adapter_prompt_input = gr.Textbox(label="Prompt", placeholder="papercut, a cute fox")
adapter_steps_input = gr.Slider(minimum=1, maximum=10, label="Inference Steps", value=4)
adapter_guidance_input = gr.Slider(minimum=0, maximum=2, label="Guidance Scale", value=1)
adapter_generate_button = gr.Button("Generate Image with Adapter")
adapter_generate_button.click(
generate_image_with_adapter,
inputs=[adapter_prompt_input, adapter_steps_input, adapter_guidance_input],
outputs=image_output
)
demo.launch()