[linux-sd-webui]之img2img

AUTOMATIC1111 GUI: A Beginner's Guide - Stable Diffusion ArtAUTOMATIC1111 (A1111 for short) Stable Diffusion webui is the de facto GUI for advanced users. Thanks to the passionate community, most new features come tohttps://stable-diffusion-art.com/automatic1111/#Text-to-image_tab1.参数

id_task='task(w9j5f4nn7lpfojk)',
mode=0, 
prompt='a highly detailed tower designed by Zaha hadid with few metal and lots of glass,roads around with much traffic,in a city with a lot of greenery,aerial view, stunning sunny lighting, foggy atmosphere, vivid colors, Photo-grade rendering, Realistic style,8k,high res,highly detialed, ray tracing,vray render,masterpiece, best quality,rendered by Mir. and Brick visual',
negative_prompt='',
prompt_styles=[],
init_img=Image.open(),
sketch=None, # 可以勾画初始草图
init_img_with_mask=None,
inpaint_color_sketch=None,
inpaint_color_sketch_orig=None,
init_img_inpaint=None,
init_mask_inpaint=None,
steps=20,
sampler_index=0,
mask_blur=4,
mask_alpha=0,
inpainting_fill=1,
restore_faces=False,
tiling=False,
n_iter=1,
batch_size=1,
cfg_scale=7,
image_cfg_scale=1.5,
denoising_strength=0.75,# 控制图像变化的程度，如果=0，没有任何变化，如果=1，则新图像不会跟随输入图像，0.75是个很好的起点
seed=-1,
subseed=-1,
subseed_strength=0,
seed_resize_from_h=0,
seed_resize_from_w=0,
seed_enable_extras=False,
selected_scale_tab=0,
height=512,
width=512,
scale_by=1,
resize_mode=0, # 0(just resize):缩放输入图像以适应新的图像尺寸，会拉伸或者挤压图像，1（crop and resize）:使画布适应输入图像，多余部分删除，保留原始图像的纵横比，3(resize and fill):将输入图像适应画布，额外部分用输入图像平均颜色填充，保留纵横比，4(just resize(latent upscale)):类似于just resize,但缩放是在隐空间中完成，使用>0.5的denoising strength以避免图像模糊。
inpaint_full_res=0,
inpaint_full_res_padding=32,
inpainting_mask_invert=0,
img2img_batch_input_dir="",
img2img_batch_output_dir='',
img2img_batch_inpaint_mask_dir='',
override_settings_texts=[]

inpaint upload：允许上传单独的mask，而不是绘制。

main.py

import sys
import logging

logging.getLogger("xformers").addFilter(lambda record: 'A matching Triton is not available' not in record.getMessage())
from modules import paths, timer, import_hook, errors

startup_timer = timer.Timer()

from modules import shared, devices, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks
import modules.scripts
import modules.sd_models
import modules.img2img
from PIL import Image
from modules.shared import cmd_opts


def initialize():
    extensions.list_extensions()
    localization.list_localizations(cmd_opts.localizations_dir)
    startup_timer.record("list extensions")

    modules.sd_models.setup_model()  # 加载模型
    startup_timer.record("list SD models")

    modules.scripts.load_scripts()
    startup_timer.record("load scripts")

    try:
        modules.sd_models.load_model()
    except Exception as e:
        errors.display(e, "loading stable diffusion model")
        print("", file=sys.stderr)
        print("Stable diffusion model failed to load, exiting", file=sys.stderr)
        exit(1)
    startup_timer.record("load SD checkpoint")


def webui():
    initialize()

    image, _, _, _ = modules.img2img.img2img(
        id_task='task(w9j5f4nn7lpfojk)',
        mode=0,
        prompt='a highly detailed tower designed by Zaha hadid with few metal and lots of glass,roads around with much traffic,in a city with a lot of greenery,aerial view, stunning sunny lighting, foggy atmosphere, vivid colors, Photo-grade rendering, Realistic style,8k,high res,highly detialed, ray tracing,vray render,masterpiece, best quality,rendered by Mir. and Brick visual',
        negative_prompt='',
        prompt_styles=[],
        init_img=Image.open(),
        sketch=None,
        init_img_with_mask=None,
        inpaint_color_sketch=None,
        inpaint_color_sketch_orig=None,
        init_img_inpaint=None,
        init_mask_inpaint=None,
        steps=20,
        sampler_index=0,
        mask_blur=4,
        mask_alpha=0,
        inpainting_fill=1,
        restore_faces=False,
        tiling=False,
        n_iter=1,
        batch_size=1,
        cfg_scale=7,
        image_cfg_scale=1.5,
        denoising_strength=0.75,
        seed=-1,
        subseed=-1,
        subseed_strength=0,
        seed_resize_from_h=0,
        seed_resize_from_w=0,
        seed_enable_extras=False,
        selected_scale_tab=0,
        height=512,
        width=512,
        scale_by=1,
        resize_mode=0,
        inpaint_full_res=0,
        inpaint_full_res_padding=32,
        inpainting_mask_invert=0,
        img2img_batch_input_dir="",
        img2img_batch_output_dir='',
        img2img_batch_inpaint_mask_dir='',
        override_settings_texts=[]
    )

    for i in range(len(image)):
        image[i].save(f"{i}.png")


if __name__ == "__main__":
    webui()

modules/img2img.py

import math
import os
import sys
import traceback

import numpy as np
from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops, UnidentifiedImageError

from modules import devices, sd_samplers
from modules.generation_parameters_copypaste import create_override_settings_dict
from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
from modules.shared import opts, state
import modules.shared as shared
import modules.processing as processing
from modules.ui import plaintext_to_html
import modules.images as images
import modules.scripts


def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args):
    processing.fix_seed(p)

    images = shared.listfiles(input_dir)

    is_inpaint_batch = False
    if inpaint_mask_dir:
        inpaint_masks = shared.listfiles(inpaint_mask_dir)
        is_inpaint_batch = len(inpaint_masks) > 0
    if is_inpaint_batch:
        print(f"\nInpaint batch is enabled. {len(inpaint_masks)} masks found.")

    print(f"Will process {len(images)} images, creating {p.n_iter * p.batch_size} new images for each.")

    save_normally = output_dir == ''

    p.do_not_save_grid = True
    p.do_not_save_samples = not save_normally

    state.job_count = len(images) * p.n_iter

    for i, image in enumerate(images):
        state.job = f"{i+1} out of {len(images)}"
        if state.skipped:
            state.skipped = False

        if state.interrupted:
            break

        try:
            img = Image.open(image)
        except UnidentifiedImageError:
            continue
        # Use the EXIF orientation of photos taken by smartphones.
        img = ImageOps.exif_transpose(img)
        p.init_images = [img] * p.batch_size

        if is_inpaint_batch:
            # try to find corresponding mask for an image using simple filename matching
            mask_image_path = os.path.join(inpaint_mask_dir, os.path.basename(image))
            # if not found use first one ("same mask for all images" use-case)
            if not mask_image_path in inpaint_masks:
                mask_image_path = inpaint_masks[0]
            mask_image = Image.open(mask_image_path)
            p.image_mask = mask_image

        proc = modules.scripts.scripts_img2img.run(p, *args)
        if proc is None:
            proc = process_images(p)

        for n, processed_image in enumerate(proc.images):
            filename = os.path.basename(image)

            if n > 0:
                left, right = os.path.splitext(filename)
                filename = f"{left}-{n}{right}"

            if not save_normally:
                os.makedirs(output_dir, exist_ok=True)
                if processed_image.mode == 'RGBA':
                    processed_image = processed_image.convert("RGB")
                processed_image.save(os.path.join(output_dir, filename))


def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args):
    args = (
        (0, '
\n
CFG Scale should be 2 or lower.
\n
\n', True, True, '', '', True, 50, True, 1, 0, False, 4, 0.5, 'Linear', 'None', '
Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8
', 128, 8, ['left', 'right', 'up', 'down'], 1, 0.05, 128, 4, 0, ['left', 'right', 'up', 'down'], False, False, 'positive', 'comma', 0, False, False, '', '
Will upscale the image by the selected scale factor; use width and height sliders to set tile size
', 64, 0, 2, 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0))

    override_settings = create_override_settings_dict(override_settings_texts)

    is_batch = mode == 5

    if mode == 0:  # img2img
        image = init_img.convert("RGB")
        mask = None
    elif mode == 1:  # img2img sketch
        image = sketch.convert("RGB")
        mask = None
    elif mode == 2:  # inpaint
        image, mask = init_img_with_mask["image"], init_img_with_mask["mask"]
        alpha_mask = ImageOps.invert(image.split()[-1]).convert('L').point(lambda x: 255 if x > 0 else 0, mode='1')
        mask = ImageChops.lighter(alpha_mask, mask.convert('L')).convert('L')
        image = image.convert("RGB")
    elif mode == 3:  # inpaint sketch
        image = inpaint_color_sketch
        orig = inpaint_color_sketch_orig or inpaint_color_sketch
        pred = np.any(np.array(image) != np.array(orig), axis=-1)
        mask = Image.fromarray(pred.astype(np.uint8) * 255, "L")
        mask = ImageEnhance.Brightness(mask).enhance(1 - mask_alpha / 100)
        blur = ImageFilter.GaussianBlur(mask_blur)
        image = Image.composite(image.filter(blur), orig, mask.filter(blur))
        image = image.convert("RGB")
    elif mode == 4:  # inpaint upload mask
        image = init_img_inpaint
        mask = init_mask_inpaint
    else:
        image = None
        mask = None

    # Use the EXIF orientation of photos taken by smartphones.
    if image is not None:
        image = ImageOps.exif_transpose(image)

    if selected_scale_tab == 1:
        assert image, "Can't scale by because no image is selected"

        width = int(image.width * scale_by)
        height = int(image.height * scale_by)

    assert 0. <= denoising_strength <= 1., 'can only work with strength in [0.0, 1.0]'

    p = StableDiffusionProcessingImg2Img(
        sd_model=shared.sd_model,
        outpath_samples=opts.outdir_samples or opts.outdir_img2img_samples,
        outpath_grids=opts.outdir_grids or opts.outdir_img2img_grids,
        prompt=prompt,
        negative_prompt=negative_prompt,
        styles=prompt_styles,
        seed=seed,
        subseed=subseed,
        subseed_strength=subseed_strength,
        seed_resize_from_h=seed_resize_from_h,
        seed_resize_from_w=seed_resize_from_w,
        seed_enable_extras=seed_enable_extras,
        sampler_name=sd_samplers.samplers_for_img2img[sampler_index].name,
        batch_size=batch_size,
        n_iter=n_iter,
        steps=steps,
        cfg_scale=cfg_scale,
        width=width,
        height=height,
        restore_faces=restore_faces,
        tiling=tiling,
        init_images=[image],
        mask=mask,
        mask_blur=mask_blur,
        inpainting_fill=inpainting_fill,
        resize_mode=resize_mode,
        denoising_strength=denoising_strength,
        image_cfg_scale=image_cfg_scale,
        inpaint_full_res=inpaint_full_res,
        inpaint_full_res_padding=inpaint_full_res_padding,
        inpainting_mask_invert=inpainting_mask_invert,
        override_settings=override_settings,
    )

    p.scripts = modules.scripts.scripts_img2img  # scriptrunner
    p.script_args = args

    if shared.cmd_opts.enable_console_prompts:
        print(f"\nimg2img: {prompt}", file=shared.progress_print_out)

    if mask:
        p.extra_generation_params["Mask blur"] = mask_blur

    if is_batch:
        assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"

        process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args)

        processed = Processed(p, [], p.seed, "")
    else:
        processed = modules.scripts.scripts_img2img.run(p, *args)
        if processed is None:
            processed = process_images(p)

    p.close()

    shared.total_tqdm.clear()

    generation_info_js = processed.js()
    if opts.samples_log_stdout:
        print(generation_info_js)

    if opts.do_not_show_images:
        processed.images = []

    return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments)