Rinnaから日本語対応のStable Diffusionが出たのでをGoogle Colab上で使ってみました。 コードとしては以下のような形です。bashのコードはJupyterから投げます。
pip install gradio try: from japanese_stable_diffusion import JapaneseStableDiffusionPipeline except: res = subprocess.run(['pip', 'install', 'git+https://github.com/rinnakk/japanese-stable-diffusion'], stdout=subprocess.PIPE).stdout.decode('utf-8') print(res) from japanese_stable_diffusion import JapaneseStableDiffusionPipeline import torch from torch import autocast from diffusers import LMSDiscreteScheduler from PIL import Image from IPython import display import gradio as gr def make_grid_from_pils(pil_images): w, h = pil_images[0].size grid_img = Image.new("RGB", ((len(pil_images)) * w, h)) for idx, image in enumerate(pil_images): grid_img.paste(image, (idx * w, 0)) return grid_img from huggingface_hub import notebook_login notebook_login() model_id = "rinna/japanese-stable-diffusion" device = "cuda" if torch.cuda.is_available() else "cpu" # Use the K-LMS scheduler here instead scheduler = LMSDiscreteScheduler( beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000 ) pipe = JapaneseStableDiffusionPipeline.from_pretrained( pretrained_model_name_or_path=model_id, scheduler=scheduler, torch_dtype=torch.float16, use_auth_token=True ).to(device) #@markdown ###**Inference Setting:** # the number of output images. If you encounter Out Of Memory error, decrease this number. n_samples = 1 #@param{type: 'integer'} # `classifier-free guidance scale` adjusts how much the image will be like your prompt. Higher values keep your image closer to your prompt. guidance_scale = 7.5 #@param {type:"number"} # How many steps to spend generating (diffusing) your image. steps = 50 #@param{type: 'integer'} # The width of the generated image. width = 512 #@param{type: 'integer'} # The height of the generated image. height = 512 #@param{type: 'integer'} # The seed used to generate your image. Enable to manually set a seed. seed = 'random' #@param{type: 'string'} import torch from torch import autocast from diffusers import LMSDiscreteScheduler from japanese_stable_diffusion import JapaneseStableDiffusionPipeline model_id = "rinna/japanese-stable-diffusion" device = "cuda" # Use the K-LMS scheduler here instead scheduler = LMSDiscreteScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000) pipe = JapaneseStableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, use_auth_token=True) pipe = pipe.to(device) prompt = "富士山をバックに二大スーパーロボットががっちりと握手" with autocast("cuda"): image = pipe(prompt, guidance_scale=7.5)["sample"][0] image.save("output.png") image “富士山をバックに二大スーパーロボットががっちりと握手"から画像を作成し、以下のような画像になります。
...