Skip to content

GitLab

Commit 58964237 authored by chenpangpang's avatar chenpangpang
Browse files

feat: InstantID初始化提交

parent 2efb0e2f
Show whitespace changes
Inline Side-by-side
Showing with 765 additions and 0 deletions
InstantID/LICENSE 0 → 100644
View file @ 58964237
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:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) 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
(d) 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
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
\ No newline at end of file
InstantID/README.md 0 → 100644
View file @ 58964237
<div align="center">
<h1>InstantID: Zero-shot Identity-Preserving Generation in Seconds</h1>
[**Qixun Wang**](https://github.com/wangqixun)<sup>12</sup> · [**Xu Bai**](https://huggingface.co/baymin0220)<sup>12</sup> · [**Haofan Wang**](https://haofanwang.github.io/)<sup>12*</sup> · [**Zekui Qin**](https://github.com/ZekuiQin)<sup>12</sup> · [**Anthony Chen**](https://antonioo-c.github.io/)<sup>123</sup>
Huaxia Li<sup>2</sup> · Xu Tang<sup>2</sup> · Yao Hu<sup>2</sup>
<sup>1</sup>InstantX Team · <sup>2</sup>Xiaohongshu Inc · <sup>3</sup>Peking University
<sup>*</sup>corresponding authors
<a href='https://instantid.github.io/'><img src='https://img.shields.io/badge/Project-Page-green'></a>
<a href='https://arxiv.org/abs/2401.07519'><img src='https://img.shields.io/badge/Technique-Report-red'></a>
<a href='https://huggingface.co/papers/2401.07519'><img src='https://img.shields.io/static/v1?label=Paper&message=Huggingface&color=orange'></a>
[![GitHub](https://img.shields.io/github/stars/InstantID/InstantID?style=social)](https://github.com/InstantID/InstantID)
<a href='https://huggingface.co/spaces/InstantX/InstantID'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'></a>
[![ModelScope](https://img.shields.io/badge/ModelScope-Studios-blue)](https://modelscope.cn/studios/instantx/InstantID/summary)
[![Open in OpenXLab](https://cdn-static.openxlab.org.cn/app-center/openxlab_app.svg)](https://openxlab.org.cn/apps/detail/InstantX/InstantID)
</div>
InstantID is a new state-of-the-art tuning-free method to achieve ID-Preserving generation with only single image, supporting various downstream tasks.
<img src='assets/applications.png'>
## Release
- [2024/04/03] 🔥 We release our recent work [InstantStyle](https://github.com/InstantStyle/InstantStyle) for style transfer, compatible with InstantID!
- [2024/02/01] 🔥 We have supported LCM acceleration and Multi-ControlNets on our [Huggingface Spaces Demo](https://huggingface.co/spaces/InstantX/InstantID)! Our depth estimator is supported by [Depth-Anything](https://github.com/LiheYoung/Depth-Anything).
- [2024/01/31] 🔥 [OneDiff](https://github.com/siliconflow/onediff?tab=readme-ov-file#easy-to-use) now supports accelerated inference for InstantID, check [this](https://github.com/siliconflow/onediff/blob/main/benchmarks/instant_id.py) for details!
- [2024/01/23] 🔥 Our pipeline has been merged into [diffusers](https://github.com/huggingface/diffusers/blob/main/examples/community/pipeline_stable_diffusion_xl_instantid.py)!
- [2024/01/22] 🔥 We release the [pre-trained checkpoints](https://huggingface.co/InstantX/InstantID), [inference code](https://github.com/InstantID/InstantID/blob/main/infer.py) and [gradio demo](https://huggingface.co/spaces/InstantX/InstantID)!
- [2024/01/15] 🔥 We release the [technical report](https://arxiv.org/abs/2401.07519).
- [2023/12/11] 🔥 We launch the [project page](https://instantid.github.io/).
## Demos
### Stylized Synthesis
<p align="center">
<img src="assets/StylizedSynthesis.png">
</p>
### Comparison with Previous Works
<p align="center">
<img src="assets/compare-a.png">
</p>
Comparison with existing tuning-free state-of-the-art techniques. InstantID achieves better fidelity and retain good text editability (faces and styles blend better).
<p align="center">
<img src="assets/compare-c.png">
</p>
Comparison with pre-trained character LoRAs. We don't need multiple images and still can achieve competitive results as LoRAs without any training.
<p align="center">
<img src="assets/compare-b.png">
</p>
Comparison with InsightFace Swapper (also known as ROOP or Refactor). However, in non-realistic style, our work is more flexible on the integration of face and background.
## Download
You can directly download the model from [Huggingface](https://huggingface.co/InstantX/InstantID).
You also can download the model in python script:
```python
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="InstantX/InstantID", filename="ControlNetModel/config.json", local_dir="./checkpoints")
hf_hub_download(repo_id="InstantX/InstantID", filename="ControlNetModel/diffusion_pytorch_model.safetensors", local_dir="./checkpoints")
hf_hub_download(repo_id="InstantX/InstantID", filename="ip-adapter.bin", local_dir="./checkpoints")
```
Or run the following command to download all models:
```python
pip install -r gradio_demo/requirements.txt
python gradio_demo/download_models.py
```
If you cannot access to Huggingface, you can use [hf-mirror](https://hf-mirror.com/) to download models.
```python
export HF_ENDPOINT=https://hf-mirror.com
huggingface-cli download --resume-download InstantX/InstantID --local-dir checkpoints --local-dir-use-symlinks False
```
For face encoder, you need to manually download via this [URL](https://github.com/deepinsight/insightface/issues/1896#issuecomment-1023867304) to `models/antelopev2` as the default link is invalid. Once you have prepared all models, the folder tree should be like:
```
.
├── models
├── checkpoints
├── ip_adapter
├── pipeline_stable_diffusion_xl_instantid.py
└── README.md
```
## Usage
If you want to reproduce results in the paper, please refer to the code in [infer_full.py](infer_full.py). If you want to compare the results with other methods, even without using depth-controlnet, it is recommended that you use this code.
If you are pursuing better results, it is recommended to follow [InstantID-Rome](https://github.com/instantX-research/InstantID-Rome).
The following code👇 comes from [infer.py](infer.py). If you want to quickly experience InstantID, please refer to the code in [infer.py](infer.py).
```python
# !pip install opencv-python transformers accelerate insightface
import diffusers
from diffusers.utils import load_image
from diffusers.models import ControlNetModel
import cv2
import torch
import numpy as np
from PIL import Image
from insightface.app import FaceAnalysis
from pipeline_stable_diffusion_xl_instantid import StableDiffusionXLInstantIDPipeline, draw_kps
# prepare 'antelopev2' under ./models
app = FaceAnalysis(name='antelopev2', root='./', providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
app.prepare(ctx_id=0, det_size=(640, 640))
# prepare models under ./checkpoints
face_adapter = f'./checkpoints/ip-adapter.bin'
controlnet_path = f'./checkpoints/ControlNetModel'
# load IdentityNet
controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)
base_model = 'wangqixun/YamerMIX_v8' # from https://civitai.com/models/84040?modelVersionId=196039
pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
base_model,
controlnet=controlnet,
torch_dtype=torch.float16
)
pipe.cuda()
# load adapter
pipe.load_ip_adapter_instantid(face_adapter)
```
Then, you can customized your own face images
```python
# load an image
face_image = load_image("./examples/yann-lecun_resize.jpg")
# prepare face emb
face_info = app.get(cv2.cvtColor(np.array(face_image), cv2.COLOR_RGB2BGR))
face_info = sorted(face_info, key=lambda x:(x['bbox'][2]-x['bbox'][0])*(x['bbox'][3]-x['bbox'][1]))[-1] # only use the maximum face
face_emb = face_info['embedding']
face_kps = draw_kps(face_image, face_info['kps'])
# prompt
prompt = "film noir style, ink sketch|vector, male man, highly detailed, sharp focus, ultra sharpness, monochrome, high contrast, dramatic shadows, 1940s style, mysterious, cinematic"
negative_prompt = "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, vibrant, colorful"
# generate image
image = pipe(
prompt,
negative_prompt=negative_prompt,
image_embeds=face_emb,
image=face_kps,
controlnet_conditioning_scale=0.8,
ip_adapter_scale=0.8,
).images[0]
```
To save VRAM, you can enable CPU offloading
```python
pipe.enable_model_cpu_offload()
pipe.enable_vae_tiling()
```
## Speed Up with LCM-LoRA
Our work is compatible with [LCM-LoRA](https://github.com/luosiallen/latent-consistency-model). First, download the model.
```python
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="latent-consistency/lcm-lora-sdxl", filename="pytorch_lora_weights.safetensors", local_dir="./checkpoints")
```
To use it, you just need to load it and infer with a small num_inference_steps. Note that it is recommendated to set guidance_scale between [0, 1].
```python
from diffusers import LCMScheduler
lcm_lora_path = "./checkpoints/pytorch_lora_weights.safetensors"
pipe.load_lora_weights(lcm_lora_path)
pipe.fuse_lora()
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
num_inference_steps = 10
guidance_scale = 0
```
## Start a local gradio demo <a href='https://github.com/gradio-app/gradio'><img src='https://img.shields.io/github/stars/gradio-app/gradio'></a>
Run the following command:
```python
python gradio_demo/app.py
```
or MultiControlNet version:
```python
gradio_demo/app-multicontrolnet.py
```
## Usage Tips
- For higher similarity, increase the weight of controlnet_conditioning_scale (IdentityNet) and ip_adapter_scale (Adapter).
- For over-saturation, decrease the ip_adapter_scale. If not work, decrease controlnet_conditioning_scale.
- For higher text control ability, decrease ip_adapter_scale.
- For specific styles, choose corresponding base model makes differences.
- We have not supported multi-person yet, only use the largest face as reference facial landmarks.
- We provide a [style template](https://github.com/ahgsql/StyleSelectorXL/blob/main/sdxl_styles.json) for reference.
## Community Resources
### Replicate Demo
- [zsxkib/instant-id](https://replicate.com/zsxkib/instant-id)
### WebUI
- [Mikubill/sd-webui-controlnet](https://github.com/Mikubill/sd-webui-controlnet/discussions/2589)
### ComfyUI
- [cubiq/ComfyUI_InstantID](https://github.com/cubiq/ComfyUI_InstantID)
- [ZHO-ZHO-ZHO/ComfyUI-InstantID](https://github.com/ZHO-ZHO-ZHO/ComfyUI-InstantID)
- [huxiuhan/ComfyUI-InstantID](https://github.com/huxiuhan/ComfyUI-InstantID)
### Windows
- [sdbds/InstantID-for-windows](https://github.com/sdbds/InstantID-for-windows)
## Acknowledgements
- InstantID is developed by InstantX Team, all copyright reserved.
- Our work is highly inspired by [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter) and [ControlNet](https://github.com/lllyasviel/ControlNet). Thanks for their great works!
- Thanks [Yamer](https://civitai.com/user/Yamer) for developing [YamerMIX](https://civitai.com/models/84040?modelVersionId=196039), we use it as base model in our demo.
- Thanks [ZHO-ZHO-ZHO](https://github.com/ZHO-ZHO-ZHO), [huxiuhan](https://github.com/huxiuhan), [sdbds](https://github.com/sdbds), [zsxkib](https://replicate.com/zsxkib) for their generous contributions.
- Thanks to the [HuggingFace](https://github.com/huggingface) gradio team for their free GPU support!
- Thanks to the [ModelScope](https://github.com/modelscope/modelscope) team for their free GPU support!
- Thanks to the [OpenXLab](https://openxlab.org.cn/apps/detail/InstantX/InstantID) team for their free GPU support!
- Thanks to [SiliconFlow](https://github.com/siliconflow) for their OneDiff integration of InstantID!
## Disclaimer
The code of InstantID is released under [Apache License](https://github.com/InstantID/InstantID?tab=Apache-2.0-1-ov-file#readme) for both academic and commercial usage. **However, both manual-downloading and auto-downloading face models from insightface are for non-commercial research purposes only** according to their [license](https://github.com/deepinsight/insightface?tab=readme-ov-file#license). **Our released checkpoints are also for research purposes only**. Users are granted the freedom to create images using this tool, but they are obligated to comply with local laws and utilize it responsibly. The developers will not assume any responsibility for potential misuse by users.
## Star History
[![Star History Chart](https://api.star-history.com/svg?repos=InstantID/InstantID&type=Date)](https://star-history.com/#InstantID/InstantID&Date)
## Sponsor Us
If you find this project useful, you can buy us a coffee via Github Sponsor! We support [Paypal](https://ko-fi.com/instantx) and [WeChat Pay](https://tinyurl.com/instantx-pay).
## Cite
If you find InstantID useful for your research and applications, please cite us using this BibTeX:
```bibtex
@article{wang2024instantid,
title={InstantID: Zero-shot Identity-Preserving Generation in Seconds},
author={Wang, Qixun and Bai, Xu and Wang, Haofan and Qin, Zekui and Chen, Anthony},
journal={arXiv preprint arXiv:2401.07519},
year={2024}
}
```
For any question, please feel free to contact us via haofanwang.ai@gmail.com or wangqixun.ai@gmail.com.
InstantID/assets/applications.png 0 → 100644
View file @ 58964237
This image diff could not be displayed because it is too large. You can view the blob instead.
InstantID/cog.yaml 0 → 100644
View file @ 58964237
# Configuration for Cog ⚙️
# Reference: https://github.com/replicate/cog/blob/main/docs/yaml.md
build:
# set to true if your model requires a GPU
gpu: true
# cuda: "12.1"
# a list of ubuntu apt packages to install
system_packages:
- "libgl1-mesa-glx"
- "libglib2.0-0"
# python version in the form '3.11' or '3.11.4'
python_version: "3.11"
# a list of packages in the format <package-name>==<version>
python_packages:
- "opencv-python==4.9.0.80"
- "transformers==4.37.0"
- "accelerate==0.26.1"
- "insightface==0.7.3"
- "diffusers==0.25.1"
- "onnxruntime==1.16.3"
# commands run after the environment is setup
run:
- curl -o /usr/local/bin/pget -L "https://github.com/replicate/pget/releases/download/v0.6.0/pget_linux_x86_64" && chmod +x /usr/local/bin/pget
# predict.py defines how predictions are run on your model
predict: "cog/predict.py:Predictor"
InstantID/cog/README.md 0 → 100644
View file @ 58964237
# InstantID Cog Model
[![Replicate](https://replicate.com/zsxkib/instant-id/badge)](https://replicate.com/zsxkib/instant-id)
## Overview
This repository contains the implementation of [InstantID](https://github.com/InstantID/InstantID) as a [Cog](https://github.com/replicate/cog) model.
Using [Cog](https://github.com/replicate/cog) allows any users with a GPU to run the model locally easily, without the hassle of downloading weights, installing libraries, or managing CUDA versions. Everything just works.
## Development
To push your own fork of InstantID to [Replicate](https://replicate.com), follow the [Model Pushing Guide](https://replicate.com/docs/guides/push-a-model).
## Basic Usage
To make predictions using the model, execute the following command from the root of this project:
```bash
cog predict \
-i image=@examples/sam_resize.png \
-i prompt="analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality" \
-i negative_prompt="nsfw" \
-i width=680 \
-i height=680 \
-i ip_adapter_scale=0.8 \
-i controlnet_conditioning_scale=0.8 \
-i num_inference_steps=30 \
-i guidance_scale=5
```
<table>
<tr>
<td>
<p align="center">Input</p>
<img src="https://replicate.delivery/pbxt/KGy0R72cMwriR9EnCLu6hgVkQNd60mY01mDZAQqcUic9rVw4/musk_resize.jpeg" alt="Sample Input Image" width="90%"/>
</td>
<td>
<p align="center">Output</p>
<img src="https://replicate.delivery/pbxt/oGOxXELcLcpaMBeIeffwdxKZAkuzwOzzoxKadjhV8YgQWk8IB/result.jpg" alt="Sample Output Image" width="100%"/>
</td>
</tr>
</table>
## Input Parameters
The following table provides details about each input parameter for the `predict` function:
| Parameter | Description | Default Value | Range |
| ------------------------------- | ---------------------------------- | -------------------------------------------------------------------------------------------------------------- | ----------- |
| `image` | Input image | A path to the input image file | Path string |
| `prompt` | Input prompt | "analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, ... " | String |
| `negative_prompt` | Input Negative Prompt | (empty string) | String |
| `width` | Width of output image | 640 | 512 - 2048 |
| `height` | Height of output image | 640 | 512 - 2048 |
| `ip_adapter_scale` | Scale for IP adapter | 0.8 | 0.0 - 1.0 |
| `controlnet_conditioning_scale` | Scale for ControlNet conditioning | 0.8 | 0.0 - 1.0 |
| `num_inference_steps` | Number of denoising steps | 30 | 1 - 500 |
| `guidance_scale` | Scale for classifier-free guidance | 5 | 1 - 50 |
This table provides a quick reference to understand and modify the inputs for generating predictions using the model.
InstantID/cog/predict.py 0 → 100644
View file @ 58964237
# Prediction interface for Cog ⚙️
# https://github.com/replicate/cog/blob/main/docs/python.md
import os
import sys
import time
import subprocess
from cog import BasePredictor, Input, Path
import cv2
import torch
import numpy as np
from PIL import Image
from diffusers.utils import load_image
from diffusers.models import ControlNetModel
from insightface.app import FaceAnalysis
sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
from pipeline_stable_diffusion_xl_instantid import (
StableDiffusionXLInstantIDPipeline,
draw_kps,
)
# for `ip-adaper`, `ControlNetModel`, and `stable-diffusion-xl-base-1.0`
CHECKPOINTS_CACHE = "./checkpoints"
CHECKPOINTS_URL = (
"https://weights.replicate.delivery/default/InstantID/checkpoints.tar"
)
# for `models/antelopev2`
MODELS_CACHE = "./models"
MODELS_URL = "https://weights.replicate.delivery/default/InstantID/models.tar"
def resize_img(
input_image,
max_side=1280,
min_side=1024,
size=None,
pad_to_max_side=False,
mode=Image.BILINEAR,
base_pixel_number=64,
):
w, h = input_image.size
if size is not None:
w_resize_new, h_resize_new = size
else:
ratio = min_side / min(h, w)
w, h = round(ratio * w), round(ratio * h)
ratio = max_side / max(h, w)
input_image = input_image.resize([round(ratio * w), round(ratio * h)], mode)
w_resize_new = (round(ratio * w) // base_pixel_number) * base_pixel_number
h_resize_new = (round(ratio * h) // base_pixel_number) * base_pixel_number
input_image = input_image.resize([w_resize_new, h_resize_new], mode)
if pad_to_max_side:
res = np.ones([max_side, max_side, 3], dtype=np.uint8) * 255
offset_x = (max_side - w_resize_new) // 2
offset_y = (max_side - h_resize_new) // 2
res[
offset_y : offset_y + h_resize_new, offset_x : offset_x + w_resize_new
] = np.array(input_image)
input_image = Image.fromarray(res)
return input_image
def download_weights(url, dest):
start = time.time()
print("downloading url: ", url)
print("downloading to: ", dest)
subprocess.check_call(["pget", "-x", url, dest], close_fds=False)
print("downloading took: ", time.time() - start)
class Predictor(BasePredictor):
def setup(self) -> None:
"""Load the model into memory to make running multiple predictions efficient"""
if not os.path.exists(CHECKPOINTS_CACHE):
download_weights(CHECKPOINTS_URL, CHECKPOINTS_CACHE)
if not os.path.exists(MODELS_CACHE):
download_weights(MODELS_URL, MODELS_CACHE)
self.width, self.height = 640, 640
self.app = FaceAnalysis(
name="antelopev2",
root="./",
providers=["CUDAExecutionProvider", "CPUExecutionProvider"],
)
self.app.prepare(ctx_id=0, det_size=(self.width, self.height))
# Path to InstantID models
face_adapter = f"./checkpoints/ip-adapter.bin"
controlnet_path = f"./checkpoints/ControlNetModel"
# Load pipeline
self.controlnet = ControlNetModel.from_pretrained(
controlnet_path,
torch_dtype=torch.float16,
cache_dir=CHECKPOINTS_CACHE,
local_files_only=True,
)
base_model_path = "stabilityai/stable-diffusion-xl-base-1.0"
self.pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
base_model_path,
controlnet=self.controlnet,
torch_dtype=torch.float16,
cache_dir=CHECKPOINTS_CACHE,
local_files_only=True,
)
self.pipe.cuda()
self.pipe.load_ip_adapter_instantid(face_adapter)
def predict(
self,
image: Path = Input(description="Input image"),
prompt: str = Input(
description="Input prompt",
default="analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality",
),
negative_prompt: str = Input(
description="Input Negative Prompt",
default="",
),
width: int = Input(
description="Width of output image",
default=640,
ge=512,
le=2048,
),
height: int = Input(
description="Height of output image",
default=640,
ge=512,
le=2048,
),
ip_adapter_scale: float = Input(
description="Scale for IP adapter",
default=0.8,
ge=0,
le=1,
),
controlnet_conditioning_scale: float = Input(
description="Scale for ControlNet conditioning",
default=0.8,
ge=0,
le=1,
),
num_inference_steps: int = Input(
description="Number of denoising steps",
default=30,
ge=1,
le=500,
),
guidance_scale: float = Input(
description="Scale for classifier-free guidance",
default=5,
ge=1,
le=50,
),
) -> Path:
"""Run a single prediction on the model"""
if self.width != width or self.height != height:
print(f"[!] Resizing output to {width}x{height}")
self.width = width
self.height = height
self.app.prepare(ctx_id=0, det_size=(self.width, self.height))
face_image = load_image(str(image))
face_image = resize_img(face_image)
face_info = self.app.get(cv2.cvtColor(np.array(face_image), cv2.COLOR_RGB2BGR))
face_info = sorted(
face_info,
key=lambda x: (x["bbox"][2] - x["bbox"][0]) * (x["bbox"][3] - x["bbox"][1]),
reverse=True,
)[
0
] # only use the maximum face
face_emb = face_info["embedding"]
face_kps = draw_kps(face_image, face_info["kps"])
self.pipe.set_ip_adapter_scale(ip_adapter_scale)
image = self.pipe(
prompt=prompt,
negative_prompt=negative_prompt,
image_embeds=face_emb,
image=face_kps,
controlnet_conditioning_scale=controlnet_conditioning_scale,
num_inference_steps=num_inference_steps,
guidance_scale=guidance_scale,
).images[0]
output_path = "result.jpg"
image.save(output_path)
return Path(output_path)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment