feat: 初次提交

.gitignore

+.idea
+chenyh

Dockerfile

+FROM image.sourcefind.cn:5000/gpu/admin/base/jupyterlab-pytorch:2.2.0-python3.10-cuda12.1-ubuntu22.04 as base
+RUN cd /root && git clone -b gpu http://developer.hpccube.com/codes/chenpangpang/photomaker-v2.git
+WORKDIR /root/photomaker-v2/PhotoMaker-V2
+RUN pip install -r requirements.txt && \
+    pip install onnxruntime-gpu==1.18.0 --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/
+
+#########
+# Prod  #
+#########
+FROM image.sourcefind.cn:5000/gpu/admin/base/jupyterlab-pytorch:2.2.0-python3.10-cuda12.1-ubuntu22.04
+COPY chenyh/photomaker/frpc_linux_amd64_v0.2 /opt/conda/lib/python3.10/site-packages/gradio/
+RUN chmod +x /opt/conda/lib/python3.10/site-packages/gradio/frpc_linux_amd64_v0.2
+COPY chenyh/photomaker-v2/TencentARC/PhotoMaker-V2 /root/PhotoMaker-V2/TencentARC/PhotoMaker-V2
+COPY chenyh/photomaker-v2/TencentARC/t2i-adapter-sketch-sdxl-1.0 /root/PhotoMaker-V2/TencentARC/t2i-adapter-sketch-sdxl-1.0
+COPY chenyh/photomaker-v2/SG161222/RealVisXL_V4.0 /root/PhotoMaker-V2/SG161222/RealVisXL_V4.0
+COPY --from=base /opt/conda/lib/python3.10/site-packages /opt/conda/lib/python3.10/site-packages
+COPY --from=base /root/photomaker/PhotoMaker /root/PhotoMaker
+COPY --from=base /root/photomaker/启动器.ipynb /root/photomaker/start.sh /root/
+#RUN python -c "import transformers; transformers.utils.move_cache()"
\ No newline at end of file

PhotoMaker-V2/LICENSE

+Tencent is pleased to support the open source community by making PhotoMaker available.
+
+Copyright (C) 2024 THL A29 Limited, a Tencent company.  All rights reserved.
+
+PhotoMaker is licensed under the Apache License Version 2.0 except for the third-party components listed below.
+
+
+Terms of the Apache License Version 2.0:
+---------------------------------------------
+Apache License
+
+Version 2.0, January 2004
+
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+1. Definitions.
+
+“License” shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.
+
+“Licensor” shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.
+
+“Legal Entity” shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, “control” means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
+
+“You” (or “Your”) shall mean an individual or Legal Entity exercising permissions granted by this License.
+
+“Source” form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
+
+“Object” form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
+
+“Work” shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).
+
+“Derivative Works” shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
+
+“Contribution” shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, “submitted” means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as “Not a Contribution.”
+
+“Contributor” shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
+
+You must give any other recipients of the Work or Derivative Works a copy of this License; and
+
+You must cause any modified files to carry prominent notices stating that You changed the files; and
+
+You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
+
+If the Work includes a “NOTICE” text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
+
+You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS

PhotoMaker-V2/README.md

+---
+title: PhotoMaker V2
+emoji: 📷✏️
+colorFrom: pink
+colorTo: blue
+sdk: gradio
+sdk_version: 4.37.2
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
\ No newline at end of file

PhotoMaker-V2/app.py

+import torch
+import torchvision.transforms.functional as TF
+import numpy as np
+import random
+import os
+import sys
+
+from diffusers.utils import load_image
+from diffusers import EulerDiscreteScheduler, T2IAdapter
+
+import gradio as gr
+
+from pipeline_t2i_adapter import PhotoMakerStableDiffusionXLAdapterPipeline
+from face_utils import FaceAnalysis2, analyze_faces
+
+from style_template import styles
+from aspect_ratio_template import aspect_ratios
+
+# global variable
+base_model_path = 'SG161222/RealVisXL_V4.0'
+face_detector = FaceAnalysis2(providers=['CPUExecutionProvider', 'CUDAExecutionProvider'],
+                              allowed_modules=['detection', 'recognition'])
+face_detector.prepare(ctx_id=0, det_size=(640, 640))
+
+try:
+    if torch.cuda.is_available():
+        device = "cuda"
+    elif sys.platform == "darwin" and torch.backends.mps.is_available():
+        device = "mps"
+    else:
+        device = "cpu"
+except:
+    device = "cpu"
+
+MAX_SEED = np.iinfo(np.int32).max
+STYLE_NAMES = list(styles.keys())
+DEFAULT_STYLE_NAME = "Photographic (Default)"
+ASPECT_RATIO_LABELS = list(aspect_ratios)
+DEFAULT_ASPECT_RATIO = ASPECT_RATIO_LABELS[0]
+
+enable_doodle_arg = False
+
+if torch.cuda.is_available() and torch.cuda.is_bf16_supported():
+    torch_dtype = torch.bfloat16
+else:
+    torch_dtype = torch.float16
+
+if device == "mps":
+    torch_dtype = torch.float16
+
+# load adapter
+adapter = T2IAdapter.from_pretrained(
+    "TencentARC/t2i-adapter-sketch-sdxl-1.0", torch_dtype=torch_dtype, variant="fp16"
+).to(device)
+
+pipe = PhotoMakerStableDiffusionXLAdapterPipeline.from_pretrained(
+    base_model_path,
+    adapter=adapter,
+    torch_dtype=torch_dtype,
+    use_safetensors=True,
+    variant="fp16",
+).to(device)
+
+pipe.load_photomaker_adapter(
+    "TencentARC/PhotoMaker-V2",
+    subfolder="",
+    weight_name="photomaker-v2.bin",
+    trigger_word="img",
+    pm_version="v2",
+)
+pipe.id_encoder.to(device)
+
+pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config)
+# pipe.set_adapters(["photomaker"], adapter_weights=[1.0])
+pipe.fuse_lora()
+pipe.to(device)
+
+
+def generate_image(
+        upload_images,
+        prompt,
+        negative_prompt,
+        aspect_ratio_name,
+        style_name,
+        num_steps,
+        style_strength_ratio,
+        num_outputs,
+        guidance_scale,
+        seed,
+        use_doodle,
+        sketch_image,
+        adapter_conditioning_scale,
+        adapter_conditioning_factor,
+        progress=gr.Progress(track_tqdm=True)
+):
+    if use_doodle:
+        sketch_image = sketch_image["composite"]
+        r, g, b, a = sketch_image.split()
+        sketch_image = a.convert("RGB")
+        sketch_image = TF.to_tensor(sketch_image) > 0.5  # Inversion
+        sketch_image = TF.to_pil_image(sketch_image.to(torch.float32))
+        adapter_conditioning_scale = adapter_conditioning_scale
+        adapter_conditioning_factor = adapter_conditioning_factor
+    else:
+        adapter_conditioning_scale = 0.
+        adapter_conditioning_factor = 0.
+        sketch_image = None
+
+    # check the trigger word
+    image_token_id = pipe.tokenizer.convert_tokens_to_ids(pipe.trigger_word)
+    input_ids = pipe.tokenizer.encode(prompt)
+    if image_token_id not in input_ids:
+        raise gr.Error(f"Cannot find the trigger word '{pipe.trigger_word}' in text prompt! Please refer to step 2️⃣")
+
+    if input_ids.count(image_token_id) > 1:
+        raise gr.Error(f"Cannot use multiple trigger words '{pipe.trigger_word}' in text prompt!")
+
+    # determine output dimensions by the aspect ratio
+    output_w, output_h = aspect_ratios[aspect_ratio_name]
+    print(f"[Debug] Generate image using aspect ratio [{aspect_ratio_name}] => {output_w} x {output_h}")
+
+    # apply the style template
+    prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
+
+    if upload_images is None:
+        raise gr.Error(f"Cannot find any input face image! Please refer to step 1️⃣")
+
+    input_id_images = []
+    for img in upload_images:
+        input_id_images.append(load_image(img))
+
+    id_embed_list = []
+
+    for img in input_id_images:
+        img = np.array(img)
+        img = img[:, :, ::-1]
+        faces = analyze_faces(face_detector, img)
+        if len(faces) > 0:
+            id_embed_list.append(torch.from_numpy((faces[0]['embedding'])))
+
+    if len(id_embed_list) == 0:
+        raise gr.Error(f"No face detected, please update the input face image(s)")
+
+    id_embeds = torch.stack(id_embed_list)
+
+    generator = torch.Generator(device=device).manual_seed(seed)
+
+    print("Start inference...")
+    print(f"[Debug] Seed: {seed}")
+    print(f"[Debug] Prompt: {prompt}, \n[Debug] Neg Prompt: {negative_prompt}")
+    start_merge_step = int(float(style_strength_ratio) / 100 * num_steps)
+    if start_merge_step > 30:
+        start_merge_step = 30
+    print(start_merge_step)
+    images = pipe(
+        prompt=prompt,
+        width=output_w,
+        height=output_h,
+        input_id_images=input_id_images,
+        negative_prompt=negative_prompt,
+        num_images_per_prompt=num_outputs,
+        num_inference_steps=num_steps,
+        start_merge_step=start_merge_step,
+        generator=generator,
+        guidance_scale=guidance_scale,
+        id_embeds=id_embeds,
+        image=sketch_image,
+        adapter_conditioning_scale=adapter_conditioning_scale,
+        adapter_conditioning_factor=adapter_conditioning_factor,
+    ).images
+    return images, gr.update(visible=True)
+
+
+def swap_to_gallery(images):
+    return gr.update(value=images, visible=True), gr.update(visible=True), gr.update(visible=False)
+
+
+def upload_example_to_gallery(images, prompt, style, negative_prompt):
+    return gr.update(value=images, visible=True), gr.update(visible=True), gr.update(visible=False)
+
+
+def remove_back_to_files():
+    return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True)
+
+
+def change_doodle_space(use_doodle):
+    if use_doodle:
+        return gr.update(visible=True)
+    else:
+        return gr.update(visible=False)
+
+
+def remove_tips():
+    return gr.update(visible=False)
+
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    return seed
+
+
+def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str, str]:
+    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
+    return p.replace("{prompt}", positive), n + ' ' + negative
+
+
+def get_image_path_list(folder_name):
+    image_basename_list = os.listdir(folder_name)
+    image_path_list = sorted([os.path.join(folder_name, basename) for basename in image_basename_list])
+    return image_path_list
+
+
+def get_example():
+    case = [
+        [
+            get_image_path_list('./examples/scarletthead_woman'),
+            "instagram photo, portrait photo of a woman img, colorful, perfect face, natural skin, hard shadows, film grain",
+            "(No style)",
+            "(asymmetry, worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
+        ],
+        [
+            get_image_path_list('./examples/newton_man'),
+            "sci-fi, closeup portrait photo of a man img wearing the sunglasses in Iron man suit, face, slim body, high quality, film grain",
+            "(No style)",
+            "(asymmetry, worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
+        ],
+    ]
+    return case
+
+
+### Description and style
+logo = r"""
+<center><img src='https://photo-maker.github.io/assets/logo.png' alt='PhotoMaker logo' style="width:80px; margin-bottom:10px"></center>
+"""
+title = r"""
+<h1 align="center">PhotoMaker V2: Improved ID Fidelity and Better Controllability than PhotoMaker V1</h1>
+"""
+
+description = r"""
+<b>Official 🤗 Gradio demo</b> for <a href='https://github.com/TencentARC/PhotoMaker' target='_blank'><b>PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding</b></a>.<br>
+How to use PhotoMaker V2 can be found in 🎬 <a href='https://photo-maker.github.io/assets/demo_pm_v2_full.mp4' target='_blank'>this video</a> 🎬.
+<br>
+<br>
+For previous version of PhotoMaker, you could use our original gradio demos [PhotoMaker](https://huggingface.co/spaces/TencentARC/PhotoMaker) and [PhotoMaker-Style](https://huggingface.co/spaces/TencentARC/PhotoMaker-Style).
+<br>
+❗️❗️❗️[<b>Important</b>] Personalization steps:<br>
+1️⃣ Upload images of someone you want to customize. One image is ok, but more is better.  Although we do not perform face detection, the face in the uploaded image should <b>occupy the majority of the image</b>.<br>
+2️⃣ Enter a text prompt, making sure to <b>follow the class word</b> you want to customize with the <b>trigger word</b>: `img`, such as: `man img` or `woman img` or `girl img`.<br>
+3️⃣ Choose your preferred style template.<br>
+4️⃣ <b>(Optional: but new feature)</b> Select the ‘Enable Drawing Doodle...’ option and draw on the canvas<br>
+5️⃣ Click the <b>Submit</b> button to start customizing.
+"""
+
+article = r"""
+
+If PhotoMaker V2 is helpful, please help to ⭐ the <a href='https://github.com/TencentARC/PhotoMaker' target='_blank'>Github Repo</a>. Thanks! 
+[![GitHub Stars](https://img.shields.io/github/stars/TencentARC/PhotoMaker?style=social)](https://github.com/TencentARC/PhotoMaker)
+---
+📝 **Citation**
+<br>
+If our work is useful for your research, please consider citing:
+
+```bibtex
+@article{li2023photomaker,
+  title={PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding},
+  author={Li, Zhen and Cao, Mingdeng and Wang, Xintao and Qi, Zhongang and Cheng, Ming-Ming and Shan, Ying},
+  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2024}
+}
+```
+📋 **License**
+<br>
+Apache-2.0 LICENSE. Please refer to the [LICENSE file](https://huggingface.co/TencentARC/PhotoMaker/blob/main/LICENSE) for details.
+
+📧 **Contact**
+<br>
+If you have any questions, please feel free to reach me out at <b>zhenli1031@gmail.com</b>.
+"""
+
+tips = r"""
+### Usage tips of PhotoMaker
+1. Upload **more photos**of the person to be customized to **improve ID fidelty**.
+2. If you find that the image quality is poor when using doodle for control, you can reduce the conditioning scale and factor of the adapter.
+If you have any issues, leave the issue in the discussion page of the space. For a more stable (queue-free) experience, you can duplicate the space.
+"""
+# We have provided some generate examples and comparisons at: [this website]().
+
+css = '''
+.gradio-container {width: 85% !important}
+'''
+with gr.Blocks(css=css) as demo:
+    gr.Markdown(logo)
+    gr.Markdown(title)
+    gr.Markdown(description)
+    # gr.DuplicateButton(
+    #     value="Duplicate Space for private use ",
+    #     elem_id="duplicate-button",
+    #     visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
+    # )
+    with gr.Row():
+        with gr.Column():
+            files = gr.Files(
+                label="Drag (Select) 1 or more photos of your face",
+                file_types=["image"]
+            )
+            uploaded_files = gr.Gallery(label="Your images", visible=False, columns=5, rows=1, height=200)
+            with gr.Column(visible=False) as clear_button:
+                remove_and_reupload = gr.ClearButton(value="Remove and upload new ones", components=files, size="sm")
+            prompt = gr.Textbox(label="Prompt",
+                                info="Try something like 'a photo of a man/woman img', 'img' is the trigger word.",
+                                placeholder="A photo of a [man/woman img]...")
+            style = gr.Dropdown(label="Style template", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
+            aspect_ratio = gr.Dropdown(label="Output aspect ratio", choices=ASPECT_RATIO_LABELS,
+                                       value=DEFAULT_ASPECT_RATIO)
+            submit = gr.Button("Submit")
+
+            enable_doodle = gr.Checkbox(
+                label="Enable Drawing Doodle for Control", value=enable_doodle_arg,
+                info="After enabling this option, PhotoMaker will generate content based on your doodle on the canvas, driven by the T2I-Adapter (Quality may be decreased)",
+            )
+            with gr.Accordion("T2I-Adapter-Doodle (Optional)", visible=False) as doodle_space:
+                with gr.Row():
+                    sketch_image = gr.Sketchpad(
+                        label="Canvas",
+                        type="pil",
+                        crop_size=[1024, 1024],
+                        layers=False,
+                        canvas_size=(350, 350),
+                        brush=gr.Brush(default_size=5, colors=["#000000"], color_mode="fixed")
+                    )
+                    with gr.Group():
+                        adapter_conditioning_scale = gr.Slider(
+                            label="Adapter conditioning scale",
+                            minimum=0.5,
+                            maximum=1,
+                            step=0.1,
+                            value=0.7,
+                        )
+                        adapter_conditioning_factor = gr.Slider(
+                            label="Adapter conditioning factor",
+                            info="Fraction of timesteps for which adapter should be applied",
+                            minimum=0.5,
+                            maximum=1,
+                            step=0.1,
+                            value=0.8,
+                        )
+            with gr.Accordion(open=False, label="Advanced Options"):
+                negative_prompt = gr.Textbox(
+                    label="Negative Prompt",
+                    placeholder="low quality",
+                    value="nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
+                )
+                num_steps = gr.Slider(
+                    label="Number of sample steps",
+                    minimum=20,
+                    maximum=100,
+                    step=1,
+                    value=50,
+                )
+                style_strength_ratio = gr.Slider(
+                    label="Style strength (%)",
+                    minimum=15,
+                    maximum=50,
+                    step=1,
+                    value=20,
+                )
+                num_outputs = gr.Slider(
+                    label="Number of output images",
+                    minimum=1,
+                    maximum=4,
+                    step=1,
+                    value=2,
+                )
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.1,
+                    maximum=10.0,
+                    step=0.1,
+                    value=5,
+                )
+                seed = gr.Slider(
+                    label="Seed",
+                    minimum=0,
+                    maximum=MAX_SEED,
+                    step=1,
+                    value=0,
+                )
+                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        with gr.Column():
+            gallery = gr.Gallery(label="Generated Images")
+            usage_tips = gr.Markdown(label="Usage tips of PhotoMaker", value=tips, visible=False)
+
+        files.upload(fn=swap_to_gallery, inputs=files, outputs=[uploaded_files, clear_button, files])
+        remove_and_reupload.click(fn=remove_back_to_files, outputs=[uploaded_files, clear_button, files])
+        enable_doodle.select(fn=change_doodle_space, inputs=enable_doodle, outputs=doodle_space)
+
+        input_list = [
+            files,
+            prompt,
+            negative_prompt,
+            aspect_ratio,
+            style,
+            num_steps,
+            style_strength_ratio,
+            num_outputs,
+            guidance_scale,
+            seed,
+            enable_doodle,
+            sketch_image,
+            adapter_conditioning_scale,
+            adapter_conditioning_factor
+        ]
+
+        submit.click(
+            fn=remove_tips,
+            outputs=usage_tips,
+        ).then(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+            queue=False,
+            api_name=False,
+        ).then(
+            fn=generate_image,
+            inputs=input_list,
+            outputs=[gallery, usage_tips]
+        )
+
+    gr.Examples(
+        examples=get_example(),
+        inputs=[files, prompt, style, negative_prompt],
+        run_on_click=True,
+        fn=upload_example_to_gallery,
+        outputs=[uploaded_files, clear_button, files],
+    )
+
+    gr.Markdown(article)
+
+demo.launch(server_name='0.0.0.0', share=True)

PhotoMaker-V2/aspect_ratio_template.py

+# From https://github.com/TencentARC/PhotoMaker/pull/120 written by https://github.com/DiscoNova
+# Note: Since output width & height need to be divisible by 8, the w & h -values do
+#       not exactly match the stated aspect ratios... but they are "close enough":)
+
+aspect_ratio_list = [
+    {
+        "name": "Instagram (1:1)",
+        "w": 1024,
+        "h": 1024,
+    },
+    {
+        "name": "35mm film / Landscape (3:2)",
+        "w": 1024,
+        "h": 680,
+    },
+    {
+        "name": "35mm film / Portrait (2:3)",
+        "w": 680,
+        "h": 1024,
+    },
+    {
+        "name": "CRT Monitor / Landscape (4:3)",
+        "w": 1024,
+        "h": 768,
+    },
+    {
+        "name": "CRT Monitor / Portrait (3:4)",
+        "w": 768,
+        "h": 1024,
+    },
+    {
+        "name": "Widescreen TV / Landscape (16:9)",
+        "w": 1024,
+        "h": 576,
+    },
+    {
+        "name": "Widescreen TV / Portrait (9:16)",
+        "w": 576,
+        "h": 1024,
+    },
+    {
+        "name": "Widescreen Monitor / Landscape (16:10)",
+        "w": 1024,
+        "h": 640,
+    },
+    {
+        "name": "Widescreen Monitor / Portrait (10:16)",
+        "w": 640,
+        "h": 1024,
+    },
+    {
+        "name": "Cinemascope (2.39:1)",
+        "w": 1024,
+        "h": 424,
+    },
+    {
+        "name": "Widescreen Movie (1.85:1)",
+        "w": 1024,
+        "h": 552,
+    },
+    {
+        "name": "Academy Movie (1.37:1)",
+        "w": 1024,
+        "h": 744,
+    },
+    {
+        "name": "Sheet-print (A-series) / Landscape (297:210)",
+        "w": 1024,
+        "h": 720,
+    },
+    {
+        "name": "Sheet-print (A-series) / Portrait (210:297)",
+        "w": 720,
+        "h": 1024,
+    },
+]
+
+aspect_ratios = {k["name"]: (k["w"], k["h"]) for k in aspect_ratio_list}

PhotoMaker-V2/face_utils.py

+import numpy as np
+# pip install insightface==0.7.3
+from insightface.app import FaceAnalysis
+from insightface.data import get_image as ins_get_image
+
+### 
+# https://github.com/cubiq/ComfyUI_IPAdapter_plus/issues/165#issue-2055829543
+###
+class FaceAnalysis2(FaceAnalysis):
+    # NOTE: allows setting det_size for each detection call.
+    # the model allows it but the wrapping code from insightface
+    # doesn't show it, and people end up loading duplicate models
+    # for different sizes where there is absolutely no need to
+    def get(self, img, max_num=0, det_size=(640, 640)):
+        if det_size is not None:
+            self.det_model.input_size = det_size
+
+        return super().get(img, max_num)
+
+def analyze_faces(face_analysis: FaceAnalysis, img_data: np.ndarray, det_size=(640, 640)):
+    # NOTE: try detect faces, if no faces detected, lower det_size until it does
+    detection_sizes = [None] + [(size, size) for size in range(640, 256, -64)] + [(256, 256)]
+
+    for size in detection_sizes:
+        faces = face_analysis.get(img_data, det_size=size)
+        if len(faces) > 0:
+            return faces
+
+    return []

PhotoMaker-V2/module/model_v2.py

+# Merge image encoder and fuse module to create an ID Encoder
+# send multiple ID images, we can directly obtain the updated text encoder containing a stacked ID embedding
+
+import torch
+import torch.nn as nn
+from transformers.models.clip.modeling_clip import CLIPVisionModelWithProjection
+from transformers.models.clip.configuration_clip import CLIPVisionConfig
+
+from .resampler import FacePerceiverResampler
+
+VISION_CONFIG_DICT = {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+}
+
+
+class MLP(nn.Module):
+    def __init__(self, in_dim, out_dim, hidden_dim, use_residual=True):
+        super().__init__()
+        if use_residual:
+            assert in_dim == out_dim
+        self.layernorm = nn.LayerNorm(in_dim)
+        self.fc1 = nn.Linear(in_dim, hidden_dim)
+        self.fc2 = nn.Linear(hidden_dim, out_dim)
+        self.use_residual = use_residual
+        self.act_fn = nn.GELU()
+
+    def forward(self, x):
+        residual = x
+        x = self.layernorm(x)
+        x = self.fc1(x)
+        x = self.act_fn(x)
+        x = self.fc2(x)
+        if self.use_residual:
+            x = x + residual
+        return x
+
+
+class QFormerPerceiver(nn.Module):
+    def __init__(self, id_embeddings_dim, cross_attention_dim, num_tokens, embedding_dim=1024, use_residual=True, ratio=4):
+        super().__init__()
+
+        self.num_tokens = num_tokens
+        self.cross_attention_dim = cross_attention_dim
+        self.use_residual = use_residual
+        print(cross_attention_dim*num_tokens)
+        self.token_proj = nn.Sequential(
+            nn.Linear(id_embeddings_dim, id_embeddings_dim*ratio),
+            nn.GELU(),
+            nn.Linear(id_embeddings_dim*ratio, cross_attention_dim*num_tokens),
+        )
+        self.token_norm = nn.LayerNorm(cross_attention_dim)
+        self.perceiver_resampler = FacePerceiverResampler(
+            dim=cross_attention_dim,
+            depth=4,
+            dim_head=128,
+            heads=cross_attention_dim // 128,
+            embedding_dim=embedding_dim,
+            output_dim=cross_attention_dim,
+            ff_mult=4,
+        )
+
+    def forward(self, x, last_hidden_state):
+        x = self.token_proj(x)
+        x = x.reshape(-1, self.num_tokens, self.cross_attention_dim)
+        x = self.token_norm(x) # cls token
+        out = self.perceiver_resampler(x, last_hidden_state) # retrieve from patch tokens
+        if self.use_residual: # TODO: if use_residual is not true
+            out = x + 1.0 * out 
+        return out
+
+
+class FuseModule(nn.Module):
+    def __init__(self, embed_dim):
+        super().__init__()
+        self.mlp1 = MLP(embed_dim * 2, embed_dim, embed_dim, use_residual=False)
+        self.mlp2 = MLP(embed_dim, embed_dim, embed_dim, use_residual=True)
+        self.layer_norm = nn.LayerNorm(embed_dim)
+
+    def fuse_fn(self, prompt_embeds, id_embeds):
+        stacked_id_embeds = torch.cat([prompt_embeds, id_embeds], dim=-1)
+        stacked_id_embeds = self.mlp1(stacked_id_embeds) + prompt_embeds
+        stacked_id_embeds = self.mlp2(stacked_id_embeds)
+        stacked_id_embeds = self.layer_norm(stacked_id_embeds)
+        return stacked_id_embeds
+
+    def forward(
+        self,
+        prompt_embeds,
+        id_embeds,
+        class_tokens_mask,
+    ) -> torch.Tensor:
+        # id_embeds shape: [b, max_num_inputs, 1, 2048]
+        id_embeds = id_embeds.to(prompt_embeds.dtype)
+        num_inputs = class_tokens_mask.sum().unsqueeze(0) # TODO: check for training case
+        batch_size, max_num_inputs = id_embeds.shape[:2]
+        # seq_length: 77
+        seq_length = prompt_embeds.shape[1]
+        # flat_id_embeds shape: [b*max_num_inputs, 1, 2048]
+        flat_id_embeds = id_embeds.view(
+            -1, id_embeds.shape[-2], id_embeds.shape[-1]
+        )
+        # valid_id_mask [b*max_num_inputs]
+        valid_id_mask = (
+            torch.arange(max_num_inputs, device=flat_id_embeds.device)[None, :]
+            < num_inputs[:, None]
+        )
+        valid_id_embeds = flat_id_embeds[valid_id_mask.flatten()]
+
+        prompt_embeds = prompt_embeds.view(-1, prompt_embeds.shape[-1])
+        class_tokens_mask = class_tokens_mask.view(-1)
+        valid_id_embeds = valid_id_embeds.view(-1, valid_id_embeds.shape[-1])
+        # slice out the image token embeddings
+        image_token_embeds = prompt_embeds[class_tokens_mask]
+        stacked_id_embeds = self.fuse_fn(image_token_embeds, valid_id_embeds)
+        assert class_tokens_mask.sum() == stacked_id_embeds.shape[0], f"{class_tokens_mask.sum()} != {stacked_id_embeds.shape[0]}"
+        prompt_embeds.masked_scatter_(class_tokens_mask[:, None], stacked_id_embeds.to(prompt_embeds.dtype))
+        updated_prompt_embeds = prompt_embeds.view(batch_size, seq_length, -1)
+        return updated_prompt_embeds
+
+
+class PhotoMakerIDEncoder_CLIPInsightfaceExtendtoken(CLIPVisionModelWithProjection):
+    def __init__(self, id_embeddings_dim=512):
+        super().__init__(CLIPVisionConfig(**VISION_CONFIG_DICT))
+        self.fuse_module = FuseModule(2048)
+        self.visual_projection_2 = nn.Linear(1024, 1280, bias=False)
+
+        cross_attention_dim = 2048
+        # projection
+        self.num_tokens = 2
+        self.cross_attention_dim = cross_attention_dim
+        self.qformer_perceiver = QFormerPerceiver(
+                                    id_embeddings_dim, 
+                                    cross_attention_dim, 
+                                    self.num_tokens,
+                                )
+
+    def forward(self, id_pixel_values, prompt_embeds, class_tokens_mask, id_embeds):
+        b, num_inputs, c, h, w = id_pixel_values.shape
+        id_pixel_values = id_pixel_values.view(b * num_inputs, c, h, w)
+
+        last_hidden_state = self.vision_model(id_pixel_values)[0]
+        id_embeds = id_embeds.view(b * num_inputs, -1)
+
+        id_embeds = self.qformer_perceiver(id_embeds, last_hidden_state)
+        id_embeds = id_embeds.view(b, num_inputs, self.num_tokens, -1)
+        updated_prompt_embeds = self.fuse_module(prompt_embeds, id_embeds, class_tokens_mask)
+
+        return updated_prompt_embeds
+
+if __name__ == "__main__":
+    PhotoMakerIDEncoder_CLIPInsightfaceExtendtoken()
\ No newline at end of file

PhotoMaker-V2/module/resampler.py

+#### Borrowed from https://github.com/tencent-ailab/IP-Adapter/blob/main/ip_adapter/resampler.py 
+# modified from https://github.com/mlfoundations/open_flamingo/blob/main/open_flamingo/src/helpers.py
+# and https://github.com/lucidrains/imagen-pytorch/blob/main/imagen_pytorch/imagen_pytorch.py
+
+import math
+
+import torch
+import torch.nn as nn
+from einops import rearrange
+from einops.layers.torch import Rearrange
+
+
+class FacePerceiverResampler(torch.nn.Module):
+    def __init__(
+        self,
+        *,
+        dim=768,
+        depth=4,
+        dim_head=64,
+        heads=16,
+        embedding_dim=1280,
+        output_dim=768,
+        ff_mult=4,
+    ):
+        super().__init__()
+        
+        self.proj_in = torch.nn.Linear(embedding_dim, dim)
+        self.proj_out = torch.nn.Linear(dim, output_dim)
+        self.norm_out = torch.nn.LayerNorm(output_dim)
+        self.layers = torch.nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(
+                torch.nn.ModuleList(
+                    [
+                        PerceiverAttention(dim=dim, dim_head=dim_head, heads=heads),
+                        FeedForward(dim=dim, mult=ff_mult),
+                    ]
+                )
+            )
+
+    def forward(self, latents, x):
+        x = self.proj_in(x)
+        for attn, ff in self.layers:
+            latents = attn(x, latents) + latents
+            latents = ff(latents) + latents
+        latents = self.proj_out(latents)
+        return self.norm_out(latents)
+
+# FFN
+def FeedForward(dim, mult=4):
+    inner_dim = int(dim * mult)
+    return nn.Sequential(
+        nn.LayerNorm(dim),
+        nn.Linear(dim, inner_dim, bias=False),
+        nn.GELU(),
+        nn.Linear(inner_dim, dim, bias=False),
+    )
+
+
+def reshape_tensor(x, heads):
+    bs, length, width = x.shape
+    # (bs, length, width) --> (bs, length, n_heads, dim_per_head)
+    x = x.view(bs, length, heads, -1)
+    # (bs, length, n_heads, dim_per_head) --> (bs, n_heads, length, dim_per_head)
+    x = x.transpose(1, 2)
+    # (bs, n_heads, length, dim_per_head) --> (bs*n_heads, length, dim_per_head)
+    x = x.reshape(bs, heads, length, -1)
+    return x
+
+
+class PerceiverAttention(nn.Module):
+    def __init__(self, *, dim, dim_head=64, heads=8):
+        super().__init__()
+        self.scale = dim_head**-0.5
+        self.dim_head = dim_head
+        self.heads = heads
+        inner_dim = dim_head * heads
+
+        self.norm1 = nn.LayerNorm(dim)
+        self.norm2 = nn.LayerNorm(dim)
+
+        self.to_q = nn.Linear(dim, inner_dim, bias=False)
+        self.to_kv = nn.Linear(dim, inner_dim * 2, bias=False)
+        self.to_out = nn.Linear(inner_dim, dim, bias=False)
+
+    def forward(self, x, latents):
+        """
+        Args:
+            x (torch.Tensor): image features
+                shape (b, n1, D)
+            latent (torch.Tensor): latent features
+                shape (b, n2, D)
+        """
+        x = self.norm1(x)
+        latents = self.norm2(latents)
+
+        b, l, _ = latents.shape
+
+        q = self.to_q(latents)
+        kv_input = torch.cat((x, latents), dim=-2)
+        k, v = self.to_kv(kv_input).chunk(2, dim=-1)
+
+        q = reshape_tensor(q, self.heads)
+        k = reshape_tensor(k, self.heads)
+        v = reshape_tensor(v, self.heads)
+
+        # attention
+        scale = 1 / math.sqrt(math.sqrt(self.dim_head))
+        weight = (q * scale) @ (k * scale).transpose(-2, -1)  # More stable with f16 than dividing afterwards
+        weight = torch.softmax(weight.float(), dim=-1).type(weight.dtype)
+        out = weight @ v
+
+        out = out.permute(0, 2, 1, 3).reshape(b, l, -1)
+
+        return self.to_out(out)
+
+
+class Resampler(nn.Module):
+    def __init__(
+        self,
+        dim=1024,
+        depth=8,
+        dim_head=64,
+        heads=16,
+        num_queries=8,
+        embedding_dim=768,
+        output_dim=1024,
+        ff_mult=4,
+        max_seq_len: int = 257,  # CLIP tokens + CLS token
+        apply_pos_emb: bool = False,
+        num_latents_mean_pooled: int = 0,  # number of latents derived from mean pooled representation of the sequence
+    ):
+        super().__init__()
+        self.pos_emb = nn.Embedding(max_seq_len, embedding_dim) if apply_pos_emb else None
+
+        self.latents = nn.Parameter(torch.randn(1, num_queries, dim) / dim**0.5)
+
+        self.proj_in = nn.Linear(embedding_dim, dim)
+
+        self.proj_out = nn.Linear(dim, output_dim)
+        self.norm_out = nn.LayerNorm(output_dim)
+
+        self.to_latents_from_mean_pooled_seq = (
+            nn.Sequential(
+                nn.LayerNorm(dim),
+                nn.Linear(dim, dim * num_latents_mean_pooled),
+                Rearrange("b (n d) -> b n d", n=num_latents_mean_pooled),
+            )
+            if num_latents_mean_pooled > 0
+            else None
+        )
+
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(
+                nn.ModuleList(
+                    [
+                        PerceiverAttention(dim=dim, dim_head=dim_head, heads=heads),
+                        FeedForward(dim=dim, mult=ff_mult),
+                    ]
+                )
+            )
+
+    def forward(self, x):
+        if self.pos_emb is not None:
+            n, device = x.shape[1], x.device
+            pos_emb = self.pos_emb(torch.arange(n, device=device))
+            x = x + pos_emb
+
+        latents = self.latents.repeat(x.size(0), 1, 1)
+
+        x = self.proj_in(x)
+
+        if self.to_latents_from_mean_pooled_seq:
+            meanpooled_seq = masked_mean(x, dim=1, mask=torch.ones(x.shape[:2], device=x.device, dtype=torch.bool))
+            meanpooled_latents = self.to_latents_from_mean_pooled_seq(meanpooled_seq)
+            latents = torch.cat((meanpooled_latents, latents), dim=-2)
+
+        for attn, ff in self.layers:
+            latents = attn(x, latents) + latents
+            latents = ff(latents) + latents
+
+        latents = self.proj_out(latents)
+        return self.norm_out(latents)
+
+
+def masked_mean(t, *, dim, mask=None):
+    if mask is None:
+        return t.mean(dim=dim)
+
+    denom = mask.sum(dim=dim, keepdim=True)
+    mask = rearrange(mask, "b n -> b n 1")
+    masked_t = t.masked_fill(~mask, 0.0)
+
+    return masked_t.sum(dim=dim) / denom.clamp(min=1e-5)

PhotoMaker-V2/requirements.txt

+diffusers
+torch
+torchvision
+transformers
+accelerate
+safetensors
+einops
+omegaconf
+peft
+huggingface-hub
+insightface==0.7.3
\ No newline at end of file

PhotoMaker-V2/style_template.py

+style_list = [
+    {
+        "name": "(No style)",
+        "prompt": "{prompt}",
+        "negative_prompt": "",
+    },
+    {
+        "name": "Cinematic",
+        "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
+        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
+    },
+    {
+        "name": "Disney Charactor",
+        "prompt": "A Pixar animation character of {prompt} . pixar-style, studio anime, Disney, high-quality",
+        "negative_prompt": "lowres, bad anatomy, bad hands, text, bad eyes, bad arms, bad legs, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, blurry, grayscale, noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo",
+    },
+    {
+        "name": "Digital Art",
+        "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed",
+        "negative_prompt": "photo, photorealistic, realism, ugly",
+    },
+    {
+        "name": "Photographic (Default)",
+        "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed",
+        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly",
+    },
+    {
+        "name": "Fantasy art",
+        "prompt": "ethereal fantasy concept art of  {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy",
+        "negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white",
+    },
+    {
+        "name": "Neonpunk",
+        "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional",
+        "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured",
+    },
+    {
+        "name": "Enhance",
+        "prompt": "breathtaking {prompt} . award-winning, professional, highly detailed",
+        "negative_prompt": "ugly, deformed, noisy, blurry, distorted, grainy",
+    },
+    {
+        "name": "Comic book",
+        "prompt": "comic {prompt} . graphic illustration, comic art, graphic novel art, vibrant, highly detailed",
+        "negative_prompt": "photograph, deformed, glitch, noisy, realistic, stock photo",
+    },
+    {
+        "name": "Lowpoly",
+        "prompt": "low-poly style {prompt} . low-poly game art, polygon mesh, jagged, blocky, wireframe edges, centered composition",
+        "negative_prompt": "noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo",
+    },
+    {
+        "name": "Line art",
+        "prompt": "line art drawing {prompt} . professional, sleek, modern, minimalist, graphic, line art, vector graphics",
+        "negative_prompt": "anime, photorealistic, 35mm film, deformed, glitch, blurry, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, mutated, realism, realistic, impressionism, expressionism, oil, acrylic",
+    }
+]
+
+styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
\ No newline at end of file