import gradio as gr import numpy as np import random import os import spaces #[uncomment to use ZeroGPU] from diffusers import DiffusionPipeline import torch from diffusers import DiffusionPipeline, UNet2DConditionModel, LCMScheduler from huggingface_hub import hf_hub_download from safetensors.torch import load_file import sys sys.path.append('.') from utils.lora import LoRANetwork, DEFAULT_TARGET_REPLACE, UNET_TARGET_REPLACE_MODULE_CONV model_repo_id = "stabilityai/stable-diffusion-xl-base-1.0" repo_name = "tianweiy/DMD2" ckpt_name = "dmd2_sdxl_4step_unet_fp16.bin" device = "cuda" if torch.cuda.is_available() else "cpu" if torch.cuda.is_available(): torch_dtype = torch.bfloat16 else: torch_dtype = torch.float32 # Load model. unet = UNet2DConditionModel.from_config(model_repo_id, subfolder="unet").to(device, torch_dtype) unet.load_state_dict(torch.load(hf_hub_download(repo_name, ckpt_name))) pipe = DiffusionPipeline.from_pretrained(model_repo_id, unet=unet, torch_dtype=torch_dtype).to(device) pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config) unet = pipe.unet ## Change these parameters based on how you trained your sliderspace sliders train_method = 'xattn-strict' rank = 1 alpha =1 networks = {} modules = DEFAULT_TARGET_REPLACE modules += UNET_TARGET_REPLACE_MODULE_CONV for i in range(1): networks[i] = LoRANetwork( unet, rank=int(rank), multiplier=1.0, alpha=int(alpha), train_method=train_method, fast_init=True, ).to(device, dtype=torch_dtype) MAX_SEED = np.iinfo(np.int32).max MAX_IMAGE_SIZE = 1024 @spaces.GPU #[uncomment to use ZeroGPU] def infer( prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, slider_space, discovered_directions, slider_scale, progress=gr.Progress(track_tqdm=True), ): if randomize_seed: seed = random.randint(0, MAX_SEED) sliderspace_path = f"sliderspace_weights/{slider_space}/slider_{int(discovered_directions[-1])-1}.pt" for net in networks: networks[net].load_state_dict(torch.load(sliderspace_path)) for net in networks: networks[net].set_lora_slider(slider_scale) with networks[0]: pass # original image generator = torch.Generator().manual_seed(seed) image = pipe( prompt=prompt, negative_prompt=negative_prompt, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps, width=width, height=height, generator=generator, ).images[0] # edited image generator = torch.Generator().manual_seed(seed) with networks[0]: slider_image = pipe( prompt=prompt, negative_prompt=negative_prompt, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps, width=width, height=height, generator=generator, ).images[0] return image, slider_image, seed examples = [ "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", "An astronaut riding a green horse", "A delicious ceviche cheesecake slice", ] css = """ #col-container { margin: 0 auto; max-width: 640px; } """ ORIGINAL_SPACE_ID = 'baulab/SliderSpace' SPACE_ID = os.getenv('SPACE_ID') SHARED_UI_WARNING = f'''## You can duplicate and use it with a gpu with at least 24GB, or clone this repository to run on your own machine.