修改 Stable Diffusion 使 api 接口增加模型参数

参考:https://zhuanlan.zhihu.com/p/644545784

1、修改 modules/api/models.py 中的 StableDiffusionTxt2ImgProcessingAPI 增加模型名称

python 复制代码
StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
    "StableDiffusionProcessingTxt2Img",
    StableDiffusionProcessingTxt2Img,
    [
        {"key": "sampler_index", "type": str, "default": "Euler"},
        {"key": "script_name", "type": str, "default": None},
        {"key": "script_args", "type": list, "default": []},
        {"key": "send_images", "type": bool, "default": True},
        {"key": "save_images", "type": bool, "default": False},
        {"key": "alwayson_scripts", "type": dict, "default": {}},
        {"key": "model_name", "type": str, "default": None},
    ]
).generate_model()

2、修改 modules/processing.py 中的 StableDiffusionProcessingTxt2Img,增加模型名称接收

python 复制代码
@dataclass(repr=False)
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 = ''
    model_name: str = None

3.修改 modules/api/api.py 中 text2imgapi 代码:

python 复制代码
......

from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, \
    postprocessing, errors, restart, shared_items, sd_models
from modules.api import models
from modules.shared import opts, models_path

......

def text2imgapi(self, txt2imgreq: models.StableDiffusionTxt2ImgProcessingAPI):
        ......
        model_name = txt2imgreq.model_name
        if model_name is None:
            raise HTTPException(status_code=404, detail="model_name not found")
        ......
        with self.queue_lock:
            checkpoint_info = sd_models.CheckpointInfo(os.path.join(models_path, 'Stable-diffusion', model_name))
            sd_models.reload_model_weights(info=checkpoint_info)
            with closing(StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)) as p:
            ......
相关推荐
孟健5 小时前
Karpathy 用 200 行纯 Python 从零实现 GPT:代码逐行解析
python
码路飞7 小时前
写了个 AI 聊天页面,被 5 种流式格式折腾了一整天 😭
javascript·python
曲幽10 小时前
FastAPI压力测试实战:Locust模拟真实用户并发及优化建议
python·fastapi·web·locust·asyncio·test·uvicorn·workers
敏编程14 小时前
一天一个Python库:jsonschema - JSON 数据验证利器
python
前端付豪14 小时前
LangChain记忆:通过Memory记住上次的对话细节
人工智能·python·langchain
databook14 小时前
ManimCE v0.20.1 发布:LaTeX 渲染修复与动画稳定性提升
python·动效
花酒锄作田1 天前
使用 pkgutil 实现动态插件系统
python
前端付豪1 天前
LangChain链 写一篇完美推文?用SequencialChain链接不同的组件
人工智能·python·langchain
曲幽1 天前
FastAPI实战:打造本地文生图接口,ollama+diffusers让AI绘画更听话
python·fastapi·web·cors·diffusers·lcm·ollama·dreamshaper8·txt2img
老赵全栈实战1 天前
Pydantic配置管理最佳实践(一)
python