made deepdanbooru optional, added to readme, automatic download of deepbooru model

README.md

@@ -66,6 +66,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
      - separate prompts using uppercase `AND`
      - also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
 - No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
+- DeepDanbooru integration, creates danbooru style tags for anime prompts (add --deepdanbooru to commandline args)
 
 ## Installation and Running
 Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
@@ -123,4 +124,5 @@ The documentation was moved from this README over to the project's [wiki](https:
 - Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
 - CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
+- DeepDanbooru - interrogator for anime diffusors https://github.com/KichangKim/DeepDanbooru
 - (You)

launch.py

@@ -33,6 +33,7 @@ def extract_arg(args, name):
 
 args, skip_torch_cuda_test = extract_arg(args, '--skip-torch-cuda-test')
 xformers = '--xformers' in args
+deepdanbooru = '--deepdanbooru' in args
 
 
 def repo_dir(name):
@@ -132,6 +133,9 @@ if not is_installed("xformers") and xformers:
     elif platform.system() == "Linux":
         run_pip("install xformers", "xformers")
 
+if not is_installed("deepdanbooru") and deepdanbooru:
+    run_pip("install git+https://github.com/KichangKim/DeepDanbooru.git@edf73df4cdaeea2cf00e9ac08bd8a9026b7a7b26#egg=deepdanbooru[tensorflow] tensorflow==2.10.0 tensorflow-io==0.27.0", "deepdanbooru")
+
 os.makedirs(dir_repos, exist_ok=True)
 
 git_clone("https://github.com/CompVis/stable-diffusion.git", repo_dir('stable-diffusion'), "Stable Diffusion", stable_diffusion_commit_hash)

modules/deepbooru.py

@@ -9,16 +9,16 @@ def _load_tf_and_return_tags(pil_image, threshold):
     import numpy as np
 
     this_folder = os.path.dirname(__file__)
-    model_path = os.path.join(this_folder, '..', 'models', 'deepbooru', 'deepdanbooru-v3-20211112-sgd-e28')
+    model_path = os.path.abspath(os.path.join(this_folder, '..', 'models', 'deepbooru'))
-
+    if not os.path.exists(os.path.join(model_path, 'project.json')):
-    model_good = False
+        # there is no point importing these every time
-    for path_candidate in [model_path, os.path.dirname(model_path)]:
+        import zipfile
-        if os.path.exists(os.path.join(path_candidate, 'project.json')):
+        from basicsr.utils.download_util import load_file_from_url
-            model_path = path_candidate
+        load_file_from_url(r"https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/deepdanbooru-v3-20211112-sgd-e28.zip",
-            model_good = True
+                           model_path)
-    if not model_good:
+        with zipfile.ZipFile(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip"), "r") as zip_ref:
-        return ("Download https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/"
+            zip_ref.extractall(model_path)
-                "deepdanbooru-v3-20211112-sgd-e28.zip unpack and put into models/deepbooru")
+        os.remove(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip"))
 
     tags = dd.project.load_tags_from_project(model_path)
     model = dd.project.load_model_from_project(

modules/shared.py

@@ -44,6 +44,7 @@ parser.add_argument("--scunet-models-path", type=str, help="Path to directory wi
 parser.add_argument("--swinir-models-path", type=str, help="Path to directory with SwinIR model file(s).", default=os.path.join(models_path, 'SwinIR'))
 parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with LDSR model file(s).", default=os.path.join(models_path, 'LDSR'))
 parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")
+parser.add_argument("--deepdanbooru", action='store_true', help="enable deepdanbooru interrogator")
 parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")
 parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
 parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")

modules/ui.py

@@ -23,9 +23,10 @@ import gradio.utils
 import gradio.routes
 
 from modules import sd_hijack
-from modules.deepbooru import get_deepbooru_tags
 from modules.paths import script_path
 from modules.shared import opts, cmd_opts
+if cmd_opts.deepdanbooru:
+    from modules.deepbooru import get_deepbooru_tags
 import modules.shared as shared
 from modules.sd_samplers import samplers, samplers_for_img2img
 from modules.sd_hijack import model_hijack
@@ -437,7 +438,10 @@ def create_toprow(is_img2img):
             with gr.Row(scale=1):
                 if is_img2img:
                     interrogate = gr.Button('Interrogate\nCLIP', elem_id="interrogate")
+                    if cmd_opts.deepdanbooru:
                         deepbooru = gr.Button('Interrogate\nDeepBooru', elem_id="deepbooru")
+                    else:
+                        deepbooru = None
                 else:
                     interrogate = None
                     deepbooru = None
@@ -782,6 +786,7 @@ def create_ui(wrap_gradio_gpu_call):
                 outputs=[img2img_prompt],
             )
 
+            if cmd_opts.deepdanbooru:
                 img2img_deepbooru.click(
                     fn=interrogate_deepbooru,
                     inputs=[init_img],

requirements.txt

@@ -23,7 +23,4 @@ resize-right
 torchdiffeq
 kornia
 lark
-deepdanbooru
-tensorflow
-tensorflow-io
 functorch

requirements_versions.txt

@@ -22,7 +22,4 @@ resize-right==0.0.2
 torchdiffeq==0.2.3
 kornia==0.6.7
 lark==1.1.2
-git+https://github.com/KichangKim/DeepDanbooru.git@edf73df4cdaeea2cf00e9ac08bd8a9026b7a7b26#egg=deepdanbooru[tensorflow]
-tensorflow==2.10.0
-tensorflow-io==0.27.0
 functorch==0.2.1