Merge pull request #3511 from bamarillo/master

[API][Feature] Add extras endpoints

modules/api/api.py

@@ -1,46 +1,37 @@
-from modules.api.models import StableDiffusionTxt2ImgProcessingAPI, StableDiffusionImg2ImgProcessingAPI
+import uvicorn
+from gradio.processing_utils import encode_pil_to_base64, decode_base64_to_file, decode_base64_to_image
+from fastapi import APIRouter, HTTPException
+import modules.shared as shared
+from modules.api.models import *
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
 from modules.sd_samplers import all_samplers
-from modules.extras import run_pnginfo
+from modules.extras import run_extras
-import modules.shared as shared
+
-import uvicorn
+def upscaler_to_index(name: str):
-from fastapi import Body, APIRouter, HTTPException
+    try:
-from fastapi.responses import JSONResponse
+        return [x.name.lower() for x in shared.sd_upscalers].index(name.lower())
-from pydantic import BaseModel, Field, Json
+    except:
-from typing import List
+        raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be on of these: {' , '.join([x.name for x in sd_upscalers])}")
-import json
-import io
-import base64
-from PIL import Image
 
 sampler_to_index = lambda name: next(filter(lambda row: name.lower() == row[1].name.lower(), enumerate(all_samplers)), None)
 
-class TextToImageResponse(BaseModel):
+def setUpscalers(req: dict):
-    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    reqDict = vars(req)
-    parameters: Json
+    reqDict['extras_upscaler_1'] = upscaler_to_index(req.upscaler_1)
-    info: Json
+    reqDict['extras_upscaler_2'] = upscaler_to_index(req.upscaler_2)
-
+    reqDict.pop('upscaler_1')
-class ImageToImageResponse(BaseModel):
+    reqDict.pop('upscaler_2')
-    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    return reqDict
-    parameters: Json
-    info: Json
-
 
 class Api:
     def __init__(self, app, queue_lock):
         self.router = APIRouter()
         self.app = app
         self.queue_lock = queue_lock
-        self.app.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"])
+        self.app.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=TextToImageResponse)
-        self.app.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"])
+        self.app.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=ImageToImageResponse)
-
+        self.app.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse)
-    def __base64_to_image(self, base64_string):
+        self.app.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=ExtrasBatchImagesResponse)
-        # if has a comma, deal with prefix
-        if "," in base64_string:
-            base64_string = base64_string.split(",")[1]
-        imgdata = base64.b64decode(base64_string)
-        # convert base64 to PIL image
-        return Image.open(io.BytesIO(imgdata))
 
     def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
         sampler_index = sampler_to_index(txt2imgreq.sampler_index)
@@ -60,15 +51,9 @@ class Api:
         with self.queue_lock:
             processed = process_images(p)
         
-        b64images = []
+        b64images = list(map(encode_pil_to_base64, processed.images))
-        for i in processed.images:
-            buffer = io.BytesIO()
-            i.save(buffer, format="png")
-            b64images.append(base64.b64encode(buffer.getvalue()))
-
-        return TextToImageResponse(images=b64images, parameters=json.dumps(vars(txt2imgreq)), info=processed.js())
-        
         
+        return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
 
     def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI):
         sampler_index = sampler_to_index(img2imgreq.sampler_index)
@@ -83,7 +68,7 @@ class Api:
 
         mask = img2imgreq.mask
         if mask:
-            mask = self.__base64_to_image(mask)
+            mask = decode_base64_to_image(mask)
 
         
         populate = img2imgreq.copy(update={ # Override __init__ params
@@ -98,7 +83,7 @@ class Api:
 
         imgs = []
         for img in init_images:
-            img = self.__base64_to_image(img)
+            img = decode_base64_to_image(img)
             imgs = [img] * p.batch_size
 
         p.init_images = imgs
@@ -106,20 +91,39 @@ class Api:
         with self.queue_lock:
             processed = process_images(p)
         
-        b64images = []
+        b64images = list(map(encode_pil_to_base64, processed.images))
-        for i in processed.images:
-            buffer = io.BytesIO()
-            i.save(buffer, format="png")
-            b64images.append(base64.b64encode(buffer.getvalue()))
 
         if (not img2imgreq.include_init_images):
             img2imgreq.init_images = None
             img2imgreq.mask = None
        
-        return ImageToImageResponse(images=b64images, parameters=json.dumps(vars(img2imgreq)), info=processed.js())
+        return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js())
 
-    def extrasapi(self):
+    def extras_single_image_api(self, req: ExtrasSingleImageRequest):
-        raise NotImplementedError
+        reqDict = setUpscalers(req)
+
+        reqDict['image'] = decode_base64_to_image(reqDict['image'])
+
+        with self.queue_lock:
+            result = run_extras(extras_mode=0, image_folder="", input_dir="", output_dir="", **reqDict)
+
+        return ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1])
+
+    def extras_batch_images_api(self, req: ExtrasBatchImagesRequest):
+        reqDict = setUpscalers(req)
+
+        def prepareFiles(file):
+            file = decode_base64_to_file(file.data, file_path=file.name)
+            file.orig_name = file.name
+            return file
+
+        reqDict['image_folder'] = list(map(prepareFiles, reqDict['imageList']))
+        reqDict.pop('imageList')
+
+        with self.queue_lock:
+            result = run_extras(extras_mode=1, image="", input_dir="", output_dir="", **reqDict)
+
+        return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
     
     def pnginfoapi(self):
         raise NotImplementedError

modules/api/models.py

@@ -1,10 +1,10 @@
-from array import array
-from inflection import underscore
-from typing import Any, Dict, Optional
-from pydantic import BaseModel, Field, create_model
-from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
 import inspect
-
+from pydantic import BaseModel, Field, create_model
+from typing import Any, Optional
+from typing_extensions import Literal
+from inflection import underscore
+from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
+from modules.shared import sd_upscalers
 
 API_NOT_ALLOWED = [
     "self",
@@ -106,3 +106,46 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
     StableDiffusionProcessingImg2Img,
     [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}, {"key": "include_init_images", "type": bool, "default": False, "exclude" : True}]
 ).generate_model()
+
+class TextToImageResponse(BaseModel):
+    images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    parameters: dict
+    info: str
+
+class ImageToImageResponse(BaseModel):
+    images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    parameters: dict
+    info: str
+
+class ExtrasBaseRequest(BaseModel):
+    resize_mode: Literal[0, 1] = Field(default=0, title="Resize Mode", description="Sets the resize mode: 0 to upscale by upscaling_resize amount, 1 to upscale up to upscaling_resize_h x upscaling_resize_w.")
+    show_extras_results: bool = Field(default=True, title="Show results", description="Should the backend return the generated image?")
+    gfpgan_visibility: float = Field(default=0, title="GFPGAN Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of GFPGAN, values should be between 0 and 1.")
+    codeformer_visibility: float = Field(default=0, title="CodeFormer Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of CodeFormer, values should be between 0 and 1.")
+    codeformer_weight: float = Field(default=0, title="CodeFormer Weight", ge=0, le=1, allow_inf_nan=False, description="Sets the weight of CodeFormer, values should be between 0 and 1.")
+    upscaling_resize: float = Field(default=2, title="Upscaling Factor", ge=1, le=4, description="By how much to upscale the image, only used when resize_mode=0.")
+    upscaling_resize_w: int = Field(default=512, title="Target Width", ge=1, description="Target width for the upscaler to hit. Only used when resize_mode=1.")
+    upscaling_resize_h: int = Field(default=512, title="Target Height", ge=1, description="Target height for the upscaler to hit. Only used when resize_mode=1.")
+    upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the choosen size?")
+    upscaler_1: str = Field(default="None", title="Main upscaler", description=f"The name of the main upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}")
+    upscaler_2: str = Field(default="None", title="Secondary upscaler", description=f"The name of the secondary upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}")
+    extras_upscaler_2_visibility: float = Field(default=0, title="Secondary upscaler visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of secondary upscaler, values should be between 0 and 1.")
+
+class ExtraBaseResponse(BaseModel):
+    html_info: str = Field(title="HTML info", description="A series of HTML tags containing the process info.")
+
+class ExtrasSingleImageRequest(ExtrasBaseRequest):
+    image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.")
+
+class ExtrasSingleImageResponse(ExtraBaseResponse):
+    image: str = Field(default=None, title="Image", description="The generated image in base64 format.")
+
+class FileData(BaseModel):
+    data: str = Field(title="File data", description="Base64 representation of the file")
+    name: str = Field(title="File name")
+
+class ExtrasBatchImagesRequest(ExtrasBaseRequest):
+    imageList: list[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
+
+class ExtrasBatchImagesResponse(ExtraBaseResponse):
+    images: list[str] = Field(title="Images", description="The generated images in base64 format.")