from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline, EulerAncestralDiscreteScheduler
from diffusers import LCMScheduler, AutoPipelineForText2Image
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, DPMSolverMultistepScheduler
from safetensors import safe_open
from compel import Compel, ReturnedEmbeddingsType
from safetensors.torch import load_file
model_id = 'aipicasso/emi'
auth_token=os.environ["ACCESS_TOKEN"]
adapter_id = "latent-consistency/lcm-lora-sdxl"
#scheduler=DPMSolverMultistepScheduler()
#pipe = StableDiffusionXLPipeline.from_pretrained(
# model_id,
# torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
# use_auth_token=auth_token)
pipe = AutoPipelineForText2Image.from_pretrained(
model_id,
torch_dtype=torch.float16,
use_auth_token=auth_token
)
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe=pipe.to("cuda")
pipe.load_lora_weights(adapter_id)
pipe.fuse_lora()
#pipe.enable_freeu(s1=0.9, s2=0.2, b1=1.3, b2=1.4)
#pipe.enable_freeu(s1=0.6, s2=0.4, b1=1.1, b2=1.2)
#pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
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])
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"
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"""
Emi + LCM-LoRA Demo
Demo for Emi
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 : 1man+, focus, wavy short hair, blue eyes, black shirt, white background, simple background
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=25)
steps = gr.Slider(label="Steps", value=6, minimum=2, maximum=30, 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()