stable_diffusion api调用sdxl1.0模型示例_stable diffusion xl 1.0 api

如何使用sd1.0模型

在api使用sdxl1.0时我们会发现在步骤和内容上会和我们使用sd1.5存在不同，同时，sdxl1.0对显卡要求较高。xl1.0拥有出色的句子识别功能（这是对前文儿童故事绘图的一次尝试），强大的风格模块，堪比lora。

0.模型不同（废话）：笔者采用sd_xl_base_1.0.safetensors，现阶段xl1.0微调模型有了一定发展，但在丰富度和数量上还是sd1.5占据优势

1.分辨率扩大：eg512*512 to 1024*1024（不需要放大模型）

2.在关键词上可以识别句子（英文），但也可以采用原有形式，不需要再输入质量画面（masterpice，best quality）等提示词也可以有很好的效果，负面提示词也可以做到少输入。

3.使用风格关键词（很重要）：出现"style"参数，一些可选风格如下（webui中截图）

4.生成时要使用refiner：sd_xl_refiner_1.0.safetensors，refiner有模型选择，选择时机总步数的多少就开始切换，模型（20步，0.8，16步开始后使用refiner选择的模型）

代码实现

代码

import requests
import base64
from PIL  import Image
import io
def stablediffusionXl(file_path,prompt='',nep='',url='http://127.0.0.1:7860'):
    txt2imge_date={
        'prompt':prompt,
        'sampler_name':'Euler a',
        "style": "Fairy Tale",
        'steps':20,
        'batch_size':1,
        'height':1024,
        'width':1024,
        'cfg_scale':7,
        "override_settings": {
            "sd_model_checkpoint": "xd1.0\sd_xl_base_1.0.safetensors [31e35c80fc]",
            "sd_vae":"sdxl_vae.safetensors"
        },
        #下方使用refiner
        "refiner": True,
        'refiner_checkpoint':'xd1.0\sd_xl_refiner_1.0.safetensors [7440042bbd]',
        'refiner_switch_at':0.8,
        #'negative_prompt':'(negative_hand-neg:1.2),(((bad-hands-5))),EasyNegative,FastNegativeV2,BadNegAnatomyV1-neg,EasyNegative,NSFW,logo,text,blurry,low quality,bad anatomy,sketches,lowres,normal quality,monochrome,grayscale,worstquality,signature,watermark,cropped,bad proportions,out of focus,username,bad face'+nep,
    }
    print('\n正在生成图片...')
    response=requests.post(url=f'{url}/sdapi/v1/txt2img',json=txt2imge_date)
    image=Image.open(io.BytesIO(base64.b64decode(response.json()['images'][0])))
    image.show()
    print('图片生成完成！')
    image.save(file_path)
if __name__ == '__main__':
    stablediffusionXl('test.jpg','Two birds, live in the same tree. They are best friends and sing together all day long. However one day suddenly one bird is shot by an arrow from a hunter rendering it unable to fly. The other very worried decides to bring it into the human world for help. Characters: Bird A & Bird B Scenery: Under the tree Emotion: Worry Action: Bird B saves Bird A')

 问题：如何使用我们不知道的api参数

与先前的api模块相比，这里明显多了许多字段，我们在webui中的操作就是打勾选中，调整参数，但在api调用中我们找不到掉用方法怎么办？

只能求助源码了AUTOMATIC1111/stable-diffusion-webui: Stable Diffusion web UI (github.com)这一个是git上的源码，我们可以把它下载下来。这个文件也存在在我们安装的秋叶整合包，位置也是一样的，我们用vscode打开整个文件

便能找到其中stable-diffusion-webui-master\modules\api，这里就是整个说明书了。

找到api下的txt2image：

self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=models.TextToImageResponse)

选中self.text2imgaapi,右键点击后选择转到定义，便可找到它在哪了

同样我们找到这里到底应用的了什么

 展示一部分这里的代码，这里按照这样的格式：字段：类型=初始值

class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
    enable_hr: bool = False
    denoising_strength: float = 0.75
    firstphase_width: int = 0
    firstphase_height: int = 0
    hr_scale: float = 2.0
    hr_upscaler: str = None
    hr_second_pass_steps: int = 0
    hr_resize_x: int = 0
    hr_resize_y: int = 0
    hr_checkpoint_name: str = None
    hr_sampler_name: str = None
    hr_prompt: str = ''
    hr_negative_prompt: str = ''
    force_task_id: str = None
 
    cached_hr_uc = [None, None]
    cached_hr_c = [None, None]
 
    hr_checkpoint_info: dict = field(default=None, init=False)
    hr_upscale_to_x: int = field(default=0, init=False)
    hr_upscale_to_y: int = field(default=0, init=False)
    truncate_x: int = field(default=0, init=False)
    truncate_y: int = field(default=0, init=False)
    applied_old_hires_behavior_to: tuple = field(default=None, init=False)
    latent_scale_mode: dict = field(default=None, init=False)
    hr_c: tuple | None = field(default=None, init=False)
    hr_uc: tuple | None = field(default=None, init=False)
    all_hr_prompts: list = field(default=None, init=False)
    all_hr_negative_prompts: list = field(default=None, init=False)
    hr_prompts: list = field(default=None, init=False)
    hr_negative_prompts: list = field(default=None, init=False)
    hr_extra_network_data: list = field(default=None, init=False)

 我们找到了StableDiffusionProcessingTxt2Img，下面就是一些特有的参数，但上面还有一层StableDiffusionProcessing我们往下，找到最源头的类代码

class StableDiffusionProcessing:
    sd_model: object = None
    outpath_samples: str = None
    outpath_grids: str = None
    prompt: str = ""
    prompt_for_display: str = None
    negative_prompt: str = ""
    styles: list[str] = None
    seed: int = -1
    subseed: int = -1
    subseed_strength: float = 0
    seed_resize_from_h: int = -1
    seed_resize_from_w: int = -1
    seed_enable_extras: bool = True
    sampler_name: str = None
    batch_size: int = 1
    n_iter: int = 1
    steps: int = 50
    cfg_scale: float = 7.0
    width: int = 512
    height: int = 512
    restore_faces: bool = None
    tiling: bool = None
    do_not_save_samples: bool = False
    do_not_save_grid: bool = False
    extra_generation_params: dict[str, Any] = None
    overlay_images: list = None
    eta: float = None
    do_not_reload_embeddings: bool = False
    denoising_strength: float = None
    ddim_discretize: str = None
    s_min_uncond: float = None
    s_churn: float = None
    s_tmax: float = None
    s_tmin: float = None
    s_noise: float = None
    override_settings: dict[str, Any] = None
    override_settings_restore_afterwards: bool = True
    sampler_index: int = None
    refiner_checkpoint: str = None
    refiner_switch_at: float = None
    token_merging_ratio = 0
    token_merging_ratio_hr = 0
    disable_extra_networks: bool = False
    firstpass_image: Image = None
 
    scripts_value: scripts.ScriptRunner = field(default=None, init=False)
    script_args_value: list = field(default=None, init=False)
    scripts_setup_complete: bool = field(default=False, init=False)
 
    cached_uc = [None, None]
    cached_c = [None, None]
 
    comments: dict = None
    sampler: sd_samplers_common.Sampler | None = field(default=None, init=False)
    is_using_inpainting_conditioning: bool = field(default=False, init=False)
    paste_to: tuple | None = field(default=None, init=False)
 
    is_hr_pass: bool = field(default=False, init=False)
 
    c: tuple = field(default=None, init=False)
    uc: tuple = field(default=None, init=False)
 
    rng: rng.ImageRNG | None = field(default=None, init=False)
    step_multiplier: int = field(default=1, init=False)
    color_corrections: list = field(default=None, init=False)
 
    all_prompts: list = field(default=None, init=False)
    all_negative_prompts: list = field(default=None, init=False)
    all_seeds: list = field(default=None, init=False)
    all_subseeds: list = field(default=None, init=False)
    iteration: int = field(default=0, init=False)
    main_prompt: str = field(default=None, init=False)
    main_negative_prompt: str = field(default=None, init=False)
 
    prompts: list = field(default=None, init=False)
    negative_prompts: list = field(default=None, init=False)
    seeds: list = field(default=None, init=False)
    subseeds: list = field(default=None, init=False)
    extra_network_data: dict = field(default=None, init=False)
 
    user: str = field(default=None, init=False)
 
    sd_model_name: str = field(default=None, init=False)
    sd_model_hash: str = field(default=None, init=False)
    sd_vae_name: str = field(default=None, init=False)
    sd_vae_hash: str = field(default=None, init=False)
 
    is_api: bool = field(default=False, init=False)

refiner_checkpoint: str = None
    refiner_switch_at: float = None

我们找到了refiner字段，明白了如何使用refiner，调用时的各种参数设置。明白如何查资料，便可以调用源代码作者的各种方法模型了