Disty0/sotediffusion-v2

your prompt goes here
very aesthetic, best quality, newest,

very displeasing, displeasing, worst quality, bad quality, low quality, realistic, monochrome, comic, sketch, oldest, early, artist name, signature, blurry, simple background, upside down,

pip install git+https://github.com/huggingface/diffusers

import torch
import diffusers

device = "cuda"
dtype = torch.float16
model_path = "Disty0/sotediffusion-v2"
pipe = diffusers.AutoPipelineForText2Image.from_pretrained(model_path, torch_dtype=dtype)

# de-dupe
pipe.decoder_pipe.text_encoder = pipe.text_encoder = None # nothing uses this
del pipe.decoder_pipe.text_encoder
del pipe.prior_prior
del pipe.prior_text_encoder
del pipe.prior_tokenizer
del pipe.prior_scheduler
del pipe.prior_feature_extractor
del pipe.prior_image_encoder

pipe = pipe.to(device, dtype=dtype)
pipe.prior_pipe = pipe.prior_pipe.to(device, dtype=dtype)


def encode_prompt(
    prior_pipe,
    device,
    num_images_per_prompt,
    prompt=""
    ):

    if prompt == "":
        text_inputs = prior_pipe.tokenizer(
            prompt,
            padding="max_length",
            max_length=77,
            truncation=False,
            return_tensors="pt",
        )
        input_ids = text_inputs.input_ids
        attention_mask=None
    else:   
        text_inputs = prior_pipe.tokenizer(
            prompt,
            padding="longest",
            truncation=False,
            return_tensors="pt",
        )
        chunk = []
        padding = []
        max_len = 75
        start_token = text_inputs.input_ids[:,0].unsqueeze(0)
        end_token = text_inputs.input_ids[:,-1].unsqueeze(0)
        raw_input_ids = text_inputs.input_ids[:,1:-1]
        prompt_len = len(raw_input_ids[0])
        last_lenght = prompt_len % max_len
        
        for i in range(int((prompt_len - last_lenght) / max_len)):
            chunk.append(torch.cat([start_token, raw_input_ids[:,i*max_len:(i+1)*max_len], end_token], dim=1))
        for i in range(max_len - last_lenght):
            padding.append(text_inputs.input_ids[:,-1])
        
        last_chunk = torch.cat([raw_input_ids[:,prompt_len-last_lenght:], torch.tensor([padding])], dim=1)
        chunk.append(torch.cat([start_token, last_chunk, end_token], dim=1))
        input_ids = torch.cat(chunk, dim=0)
        attention_mask = torch.ones(input_ids.shape, device=device, dtype=torch.int64)
        attention_mask[-1,last_lenght+1:] = 0

    text_encoder_output = prior_pipe.text_encoder(
        input_ids.to(device), attention_mask=attention_mask, output_hidden_states=True
    )

    prompt_embeds = text_encoder_output.hidden_states[-1].reshape(1,-1,1280)
    prompt_embeds = prompt_embeds.to(dtype=prior_pipe.text_encoder.dtype, device=device)
    prompt_embeds = prompt_embeds.repeat_interleave(num_images_per_prompt, dim=0)

    prompt_embeds_pooled = text_encoder_output.text_embeds[0].unsqueeze(0).unsqueeze(1)
    prompt_embeds_pooled = prompt_embeds_pooled.to(dtype=prior_pipe.text_encoder.dtype, device=device)
    prompt_embeds_pooled = prompt_embeds_pooled.repeat_interleave(num_images_per_prompt, dim=0)

    return prompt_embeds, prompt_embeds_pooled


prompt = "1girl, solo, looking at viewer, open mouth, blue eyes, medium breasts, blonde hair, gloves, dress, bow, hair between eyes, bare shoulders, upper body, hair bow, indoors, elbow gloves, hand on own chest, bridal gauntlets, candlestand, smile, rim lighting, from side, castle interior, looking side,"
quality_prompt = "very aesthetic, best quality, newest"
negative_prompt = "very displeasing, displeasing, worst quality, bad quality, low quality, realistic, monochrome, comic, sketch, oldest, early, artist name, signature, blurry, simple background, upside down,"
num_images_per_prompt=1

# Encode prompts and quality prompts eperately, long prompt support and don't use attention masks for empty prompts:
# pipe, device, num_images_per_prompt, prompt
empty_prompt_embeds, _ = encode_prompt(pipe.prior_pipe, device, num_images_per_prompt, prompt="")

prompt_embeds, prompt_embeds_pooled = encode_prompt(pipe.prior_pipe, device, num_images_per_prompt, prompt=prompt)
quality_prompt_embeds, _ = encode_prompt(pipe.prior_pipe, device, num_images_per_prompt, prompt=quality_prompt)
prompt_embeds = torch.cat([prompt_embeds, quality_prompt_embeds], dim=1)

negative_prompt_embeds, negative_prompt_embeds_pooled = encode_prompt(pipe.prior_pipe, device, num_images_per_prompt, prompt=negative_prompt)

while prompt_embeds.shape[1] < negative_prompt_embeds.shape[1]:
    prompt_embeds = torch.cat([prompt_embeds, empty_prompt_embeds], dim=1)

while negative_prompt_embeds.shape[1] < prompt_embeds.shape[1]:
    negative_prompt_embeds = torch.cat([negative_prompt_embeds, empty_prompt_embeds], dim=1)

output = pipe(
    width=1024,
    height=1536,
    decoder_guidance_scale=1.0,
    prior_guidance_scale=5.0,
    prior_num_inference_steps=28,
    num_inference_steps=14,
    output_type="pil",
    prompt=prompt + " " + quality_prompt,
    negative_prompt=negative_prompt,
    prompt_embeds=prompt_embeds,
    prompt_embeds_pooled=prompt_embeds_pooled,
    negative_prompt_embeds=negative_prompt_embeds,
    negative_prompt_embeds_pooled=negative_prompt_embeds_pooled,
    num_images_per_prompt=num_images_per_prompt,
).images[0]

display(output)

aesthetic tags, quality tags, date tags, custom tags, rating tags, character, series, rest of the tags