Spaces:
Paused
Paused
File size: 2,695 Bytes
a4cc7b2 683afc3 c1497a6 0737dc8 a4cc7b2 b1029c2 97c3973 b1029c2 a4cc7b2 feede18 4fbc46c c1497a6 683afc3 b12bc82 a4cc7b2 b1029c2 a4cc7b2 bcbf6e0 0737dc8 74c4e79 a4cc7b2 e92cda4 dbeec98 97c3973 a4cc7b2 97c3973 dbeec98 b1029c2 a4cc7b2 97c3973 a4cc7b2 683afc3 7968596 dbeec98 a4cc7b2 dbeec98 a4cc7b2 7968596 9754bfe 7968596 683afc3 7968596 a4cc7b2 |
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 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
import torch
from diffusers.models import MotionAdapter
from diffusers import AnimateDiffSDXLPipeline, DDIMScheduler
from diffusers.utils import export_to_gif
import gradio as gr
from huggingface_hub import login
import os
import spaces,tempfile
import torch
from diffusers import StableDiffusionXLPipeline
from PIL import Image
import torch
from diffusers import AutoPipelineForText2Image, DDIMScheduler
from diffusers import AutoPipelineForText2Image
from diffusers.utils import load_image
import torch
from diffusers.models import MotionAdapter
from diffusers import AnimateDiffSDXLPipeline, DDIMScheduler
from diffusers.utils import export_to_gif
token = os.getenv("HF_TOKEN")
login(token=token)
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-sdxl-beta", torch_dtype=torch.float16)
model_id = "stabilityai/sdxl-turbo"
scheduler = DDIMScheduler.from_pretrained(
model_id,
subfolder="scheduler",
clip_sample=False,
timestep_spacing="linspace",
beta_schedule="linear",
steps_offset=1,
)
pipe = AnimateDiffSDXLPipeline.from_pretrained(
model_id,
motion_adapter=adapter,
scheduler=scheduler,
torch_dtype=torch.float16,
variant="fp16",
).to("cuda")
pipe.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
# enable memory savings
pipe.enable_vae_slicing()
pipe.enable_vae_tiling()
pipeline = pipe
@spaces.GPU
def generate_image(prompt, reference_image, controlnet_conditioning_scale,num_frames):
style_images = [load_image(f.name) for f in reference_image]
pipeline.set_ip_adapter_scale(controlnet_conditioning_scale)
output = pipeline(
prompt=prompt,
ip_adapter_image=[style_images],
negative_prompt="",
guidance_scale=5,
num_inference_steps=30,
num_frames=num_frames,
)
frames = output.frames[0]
export_to_gif(frames, "animation.gif")
return "animation.gif"
# Set up Gradio interface
interface = gr.Interface(
fn=generate_image,
inputs=[
gr.Textbox(label="Prompt"),
# gr.Image( type= "filepath",label="Reference Image (Style)"),
gr.File(type="file",file_count="multiple",label="Reference Image (Style)"),
gr.Slider(label="Control Net Conditioning Scale", minimum=0, maximum=1.0, step=0.1, value=1.0),
gr.Slider(label="Number of frames", minimum=0, maximum=1.0, step=0.1, value=1.0),
],
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()
|