from diffusers import AutoPipelineForText2Image, EulerAncestralDiscreteScheduler from diffusers import UniPCMultistepScheduler 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 safetensors import safe_open from compel import Compel, ReturnedEmbeddingsType from safetensors.torch import load_file import spaces model_id = "aipicasso/emix-0-5" auth_token=os.environ["ACCESS_TOKEN"] repo = "ByteDance/SDXL-Lightning" ckpt = "sdxl_lightning_8step_lora.safetensors" scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler",token=auth_token) pipe = AutoPipelineForText2Image.from_pretrained( model_id, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, scheduler=scheduler, token=auth_token) pipe.load_lora_weights(hf_hub_download(repo, ckpt)) pipe.fuse_lora() pipe.enable_freeu(s1=0.9, s2=0.2, b1=1.3, b2=1.4) state_dict = load_file("unaestheticXLv31.safetensors") pipe.load_textual_inversion(state_dict["clip_g"], token="unaestheticXLv31", text_encoder=pipe.text_encoder_2, tokenizer=pipe.tokenizer_2) pipe.load_textual_inversion(state_dict["clip_l"], token="unaestheticXLv31", text_encoder=pipe.text_encoder, tokenizer=pipe.tokenizer) 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]) pipe=pipe.to("cuda") def error_str(error, title="Error"): return f"""#### {title} {error}""" if error else "" @spaces.GPU def inference(prompt, guidance, steps, seed=0, neg_prompt="", disable_auto_prompt_correction=False): 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) result=txt_to_img(prompt, neg_prompt, guidance, steps, width, height, generator) return result, 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" 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"{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"{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"{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_conditioning, neg_pooled = compel(neg_prompt) result = pipe( prompt_embeds=conditioning, pooled_prompt_embeds=pooled, negative_prompt_embeds=neg_conditioning, negative_pooled_prompt_embeds=neg_pooled, 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"""

Emix 0.5 Lightning Demo

You can use new model: Emi 2

サンプル： そのままGenerateボタンを押してください。
sample : Click "Generate" button without any prompts.

sample prompt1 : 1girl, cool+, smile--, colorful long hair, colorful eyes, stars, night, pastel color, transparent+

sample prompt2 : 1boy, focus, wavy short hair, blue eyes, black shirt, white background, simple background

Duplicate Space to say goodbye from waiting for the generating.

""" ) 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() 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=1.5, maximum=10, step=0.1) steps = gr.Slider(label="Steps", value=8, minimum=1, maximum=20, 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() demo.launch()