Spaces:
Paused
Paused
File size: 2,110 Bytes
683afc3 c1497a6 0737dc8 74c4e79 9754bfe f5ffe3a 97c3973 feede18 4fbc46c c1497a6 683afc3 97c3973 f5ffe3a b12bc82 97c3973 bcbf6e0 0737dc8 74c4e79 5a5a07a 97c3973 683afc3 7968596 feede18 7968596 9754bfe 7968596 683afc3 7968596 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
import gradio as gr
from huggingface_hub import login
import os
import spaces
import torch
from diffusers import StableDiffusionXLPipeline
from PIL import Image
import torch
from diffusers import AutoPipelineForText2Image, DDIMScheduler
from transformers import CLIPVisionModelWithProjection
from diffusers.utils import load_image
token = os.getenv("HF_TOKEN")
login(token=token)
image_encoder = CLIPVisionModelWithProjection.from_pretrained(
"h94/IP-Adapter",
subfolder="models/image_encoder",
torch_dtype=torch.float16,
)
pipeline = AutoPipelineForText2Image.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16,
image_encoder=image_encoder,
)
pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
pipeline.load_ip_adapter(
"h94/IP-Adapter",
subfolder="sdxl_models",
weight_name=["ip-adapter-plus_sdxl_vit-h.safetensors", "ip-adapter-plus-face_sdxl_vit-h.safetensors"]
)
pipeline.set_ip_adapter_scale([0.7, 0.3])
pipeline.enable_model_cpu_offload()
@spaces.GPU
def generate_image(prompt, reference_image, controlnet_conditioning_scale):
reference_image = Image.open(reference_image)
# reference_image.resize((512, 512))
pipeline.set_ip_adapter_scale([controlnet_conditioning_scale])
image = pipeline(
prompt=prompt,
ip_adapter_image=[reference_image],
negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality",
num_inference_steps=50, num_images_per_prompt=1,
).images[0]
return image
# Set up Gradio interface
interface = gr.Interface(
fn=generate_image,
inputs=[
gr.Textbox(label="Prompt"),
gr.Image( type= "filepath",label="Reference Image (Style)"),
gr.Slider(label="Control Net Conditioning Scale", minimum=0, maximum=1.0, step=0.1, value=0.6),
],
outputs="image",
title="Image Generation with Stable Diffusion 3 medium and ControlNet",
description="Generates an image based on a text prompt and a reference image using Stable Diffusion 3 medium with ControlNet."
)
interface.launch()
|