trsh.py

import gradio as gr
from huggingface_hub import login
import os
import spaces,tempfile
import torch
from diffusers import AnimateDiffSparseControlNetPipeline
from diffusers.models import AutoencoderKL, MotionAdapter, SparseControlNetModel
from diffusers.schedulers import DPMSolverMultistepScheduler
from diffusers.utils import export_to_gif, load_image
token = os.getenv("HF_TOKEN")
login(token=token)


model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
motion_adapter_id = "guoyww/animatediff-motion-adapter-v1-5-3"
controlnet_id = "guoyww/animatediff-sparsectrl-rgb"
lora_adapter_id = "guoyww/animatediff-motion-lora-v1-5-3"
vae_id = "stabilityai/sd-vae-ft-mse"
device = "cuda"

motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, torch_dtype=torch.float16).to(device)
controlnet = SparseControlNetModel.from_pretrained(controlnet_id, torch_dtype=torch.float16).to(device)
vae = AutoencoderKL.from_pretrained(vae_id, torch_dtype=torch.float16).to(device)
scheduler = DPMSolverMultistepScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    beta_schedule="linear",
    algorithm_type="dpmsolver++",
    use_karras_sigmas=True,
)
pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
    model_id,
    motion_adapter=motion_adapter,
    controlnet=controlnet,
    vae=vae,
    scheduler=scheduler,
    torch_dtype=torch.float16,
).to(device)
pipe.load_lora_weights(lora_adapter_id, adapter_name="motion_lora")


@spaces.GPU
def generate_image(prompt, reference_image, controlnet_conditioning_scale,num_frames):
    style_images = [load_image(f.name) for f in reference_image]

    video = pipe(
        prompt=prompt,
        negative_prompt="low quality, worst quality",
        num_inference_steps=25,
        num_frames=num_frames,
        conditioning_frames=style_images,
        controlnet_frame_indices=[0],
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        generator=torch.Generator().manual_seed(42),
    ).frames[0]
    export_to_gif(video, "output.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()