Spaces:
Running
on
Zero
Running
on
Zero
| from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline, EulerAncestralDiscreteScheduler | |
| import gradio as gr | |
| import torch | |
| from PIL import Image | |
| import random | |
| import os | |
| from huggingface_hub import hf_hub_download | |
| import torch | |
| from torch import autocast | |
| from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler | |
| from safetensors import safe_open | |
| from compel import Compel, ReturnedEmbeddingsType | |
| from huggingface_hub import hf_hub_download | |
| model_id = 'aipicasso/emi' | |
| auth_token=os.environ["ACCESS_TOKEN"] | |
| scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler", use_auth_token=auth_token) | |
| pipe = StableDiffusionXLPipeline.from_pretrained( | |
| model_id, | |
| torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, | |
| scheduler=scheduler, use_auth_token=auth_token) | |
| pipe=pipe.to("cuda") | |
| #pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True) | |
| token_num=65 | |
| unaestheticXLv31="" | |
| embeddings_dict = {} | |
| with safe_open("unaestheticXLv31.safetensors", framework="pt") as f: | |
| for k in f.keys(): | |
| embeddings_dict[k] = f.get_tensor(k) | |
| pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128) | |
| pipe.text_encoder_2.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128) | |
| for i in range(len(embeddings_dict["clip_l"])): | |
| token = f"sksd{chr(token_num)}" | |
| token_num+=1 | |
| unaestheticXLv31 += token | |
| pipe.tokenizer.add_tokens(token) | |
| token_id = pipe.tokenizer.convert_tokens_to_ids(token) | |
| pipe.text_encoder.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_l"][i] | |
| pipe.text_encoder_2.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_g"][i] | |
| unaestheticXLv1="" | |
| embeddings_dict = {} | |
| with safe_open("unaestheticXLv1.safetensors", framework="pt") as f: | |
| for k in f.keys(): | |
| embeddings_dict[k] = f.get_tensor(k) | |
| pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128) | |
| pipe.text_encoder_2.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128) | |
| for i in range(len(embeddings_dict["clip_l"])): | |
| token = f"sksd{chr(token_num)}" | |
| token_num+=1 | |
| unaestheticXLv1 += token | |
| pipe.tokenizer.add_tokens(token) | |
| token_id = pipe.tokenizer.convert_tokens_to_ids(token) | |
| pipe.text_encoder.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_l"][i] | |
| pipe.text_encoder_2.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_g"][i] | |
| unaestheticXLv13="" | |
| embeddings_dict = {} | |
| with safe_open("unaestheticXLv13.safetensors", framework="pt") as f: | |
| for k in f.keys(): | |
| embeddings_dict[k] = f.get_tensor(k) | |
| pipe.text_encoder.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128) | |
| pipe.text_encoder_2.resize_token_embeddings(len(pipe.tokenizer),pad_to_multiple_of=128) | |
| for i in range(len(embeddings_dict["clip_l"])): | |
| token = f"sksd{chr(token_num)}" | |
| unaestheticXLv13 += token | |
| token_num+=1 | |
| pipe.tokenizer.add_tokens(token) | |
| token_id = pipe.tokenizer.convert_tokens_to_ids(token) | |
| pipe.text_encoder.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_l"][i] | |
| pipe.text_encoder_2.get_input_embeddings().weight.data[token_id] = embeddings_dict["clip_g"][i] | |
| compel = Compel(tokenizer=[pipe.tokenizer, pipe.tokenizer_2] , | |
| text_encoder=[pipe.text_encoder, pipe.text_encoder_2], | |
| returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED, | |
| requires_pooled=[False, True]) | |
| def error_str(error, title="Error"): | |
| return f"""#### {title} | |
| {error}""" if error else "" | |
| def inference(prompt, guidance, steps, seed=0, neg_prompt="", disable_auto_prompt_correction=False): | |
| global pipe | |
| generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None | |
| prompt,neg_prompt=auto_prompt_correction(prompt,neg_prompt,disable_auto_prompt_correction) | |
| height=1024 | |
| width=1024 | |
| print(prompt,neg_prompt) | |
| return txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator), None | |
| def auto_prompt_correction(prompt_ui,neg_prompt_ui,disable_auto_prompt_correction): | |
| # auto prompt correction | |
| prompt=str(prompt_ui) | |
| neg_prompt=str(neg_prompt_ui) | |
| prompt=prompt.lower() | |
| neg_prompt=neg_prompt.lower() | |
| if(disable_auto_prompt_correction): | |
| return prompt, neg_prompt | |
| if(prompt=="" and neg_prompt==""): | |
| prompt="1girl++, smile--, brown bob+++ hair, brown eyes, sunflowers, sky, transparent++" | |
| neg_prompt=f"({unaestheticXLv31})---, photo, deformed, realism, disfigured, low contrast, bad hand" | |
| return prompt, neg_prompt | |
| splited_prompt=prompt.replace(","," ").replace("_"," ").replace("+"," ").split(" ") | |
| human_words=["1girl","girl","maid","maids","female","1woman","woman","girls","2girls","3girls","4girls","5girls","a couple of girls","women","1boy","boy","boys","a couple of boys","2boys","male","1man","1handsome","1bishounen","man","men","guy","guys"] | |
| for word in human_words: | |
| if( word in splited_prompt): | |
| prompt=f"anime artwork, anime style, {prompt}" | |
| neg_prompt=f"({unaestheticXLv31})---,{neg_prompt}, photo, deformed, realism, disfigured, low contrast, bad hand" | |
| return prompt, neg_prompt | |
| animal_words=["cat","dog","bird","pigeon","rabbit","bunny","horse"] | |
| for word in animal_words: | |
| if( word in splited_prompt): | |
| prompt=f"anime style, a {prompt}, 4k, detailed" | |
| neg_prompt=f"{neg_prompt},({unaestheticXLv31})---" | |
| return prompt, neg_prompt | |
| background_words=["mount fuji","mt. fuji","building", "buildings", "tokyo", "kyoto", "nara", "shibuya", "shinjuku"] | |
| for word in background_words: | |
| if( word in splited_prompt): | |
| prompt=f"anime artwork, anime style, {prompt}, highly detailed" | |
| neg_prompt=f"girl, deformed+++, {neg_prompt}, girl, boy, photo, people, low quality, ui, error, lowres, jpeg artifacts, 2d, 3d, cg, text" | |
| return prompt, neg_prompt | |
| return prompt,neg_prompt | |
| def txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator): | |
| conditioning, pooled = compel([prompt, neg_prompt]) | |
| result = pipe( | |
| prompt_embeds=conditioning[0:1], | |
| pooled_prompt_embeds=pooled[0:1], | |
| negative_prompt_embeds=conditioning[1:2], | |
| negative_pooled_prompt_embeds=pooled[1:2], | |
| num_inference_steps = int(steps), | |
| guidance_scale = guidance, | |
| width = width, | |
| height = height, | |
| generator = generator) | |
| return result.images[0] | |
| css = """.main-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.main-div div h1{font-weight:900;margin-bottom:7px}.main-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem} | |
| """ | |
| with gr.Blocks(css=css) as demo: | |
| gr.HTML( | |
| f""" | |
| <div class="main-div"> | |
| <div> | |
| <h1>Emi Demo</h1> | |
| </div> | |
| <p> | |
| Demo for <a href="https://huggingface.co/aipicasso/emi">Emi</a><br> | |
| </p> | |
| <p> | |
| サンプル： そのままGenerateボタンを押してください。<br> | |
| sample : Click "Generate" button without any prompts. | |
| </p> | |
| <p> | |
| sample prompt1 : 1girl++, cool+, smile--, colorful long hair, colorful eyes, stars, night, pastel color, transparent+ | |
| </p> | |
| <p> | |
| sample prompt2 : 1man+, focus, wavy short hair, blue eyes, black shirt, white background, simple background | |
| </p> | |
| <p> | |
| sample prompt3 : anime style, 1girl++ | |
| </p> | |
| <p> | |
| 共有ボタンを押してみんなに画像を共有しましょう。Please push share button to share your image. | |
| </p> | |
| <p> | |
| Running on {"<b>GPU 🔥</b>" if torch.cuda.is_available() else f"<b>CPU 🥶</b>. For faster inference it is recommended to <b>upgrade to GPU in <a href='https://huggingface.co/spaces/akhaliq/cool-japan-diffusion-2-1-0/settings'>Settings</a></b>"} <br> | |
| <a style="display:inline-block" href="https://huggingface.co/spaces/aipicasso/emi-latest-demo?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a> to say goodbye from waiting for the generating. | |
| <h2> | |
| <a href="https://e5b26b1151bf4a7fe2.gradio.live"> | Emi Demo (Sub) | </a> | |
| <a href="https://e4f3a9ae48c8c4921e.gradio.live"> Emi Stable Demo | </a> | |
| <a href="https://07f0307923ad05d680.gradio.live"> Emix Demo 1 |</a> | |
| <a href="https://471d8ebdaf5d5c5aa5.gradio.live/"> Emix Demo 2 |</a> | |
| </h2> | |
| </div> | |
| """ | |
| ) | |
| with gr.Row(): | |
| with gr.Column(scale=55): | |
| with gr.Group(): | |
| with gr.Row(): | |
| prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="[your prompt]") | |
| generate = gr.Button(value="Generate") | |
| image_out = gr.Image(height=1024,width=1024) | |
| error_output = gr.Markdown() | |
| with gr.Column(scale=45): | |
| with gr.Group(): | |
| neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image") | |
| disable_auto_prompt_correction = gr.Checkbox(label="Disable auto prompt corretion.") | |
| with gr.Row(): | |
| guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=25) | |
| steps = gr.Slider(label="Steps", value=20, minimum=2, maximum=75, step=1) | |
| seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1) | |
| inputs = [prompt, guidance, steps, seed, neg_prompt, disable_auto_prompt_correction] | |
| outputs = [image_out, error_output] | |
| prompt.submit(inference, inputs=inputs, outputs=outputs) | |
| generate.click(inference, inputs=inputs, outputs=outputs) | |
| demo.queue(concurrency_count=1) | |
| demo.launch() |