zsxkib / flux-pulid

⚡️FLUX PuLID: FLUX-dev based Pure and Lightning ID Customization via Contrastive Alignment🎭

replicate.com
Total runs: 601.2K
24-hour runs: 5.6K
7-day runs: 38.0K
30-day runs: 173.9K
Github
Model's Last Updated: September 16 2024

Introduction of flux-pulid

Model Details of flux-pulid

Readme

PuLID for FLUX

Welcome to PuLID-FLUX-v0.9.0 , a tuning-free ID customization solution for FLUX.1-dev.

About PuLID

PuLID (Pure and Lightning ID customization) is an AI model that customizes images, especially faces, while keeping important identity features. Here’s what PuLID does:

  • It adds a specific identity (like a person’s face) to a text-to-image model without changing how the model usually works.
  • It creates images with high identity similarity.
  • It lets you change things like attributes, styles, and backgrounds using text prompts.
  • It keeps image elements like background, lighting, and style consistent.
  • It gives you lots of options to edit and change the generated images.

PuLID uses some cool tech stuff: - It has two main parts: a regular diffusion training part and a new Lightning T2I part. - It uses special ways to understand facial identity. - It uses a technique called “contrastive alignment” to keep images consistent. - It can create images quickly while still getting the identity right.

You can use PuLID for things like: - Making avatars and characters - Editing and improving faces - Creating digital art - Making prototypes and visualizations

How to Use This Replicate Demo
  1. Upload an image with the identity you want to use.
  2. Write a prompt describing the image you want to create.
  3. Adjust the settings if you need to (check out the “Useful Tips” below).
  4. Click to generate your customized image!
Useful Tips

Two important settings to think about:

  1. Timestep to start inserting ID :
  2. This decides when to start adding the identity during image creation.
  3. Lower numbers (0-1) make the identity look more similar but might be harder to edit.
  4. Higher numbers (like 4) are easier to edit but might make the identity less similar.
  5. We suggest using 4 for realistic images, and 0-1 for stylized images.

  6. True CFG scale :

  7. FLUX.1-dev uses something called a “fake CFG” usually.
  8. You can choose to use either fake CFG or true CFG.
  9. Fake CFG often works well for realistic-looking scenes.
  10. True CFG might make the identity look more similar in some cases.
  11. Try true CFG for stylized scenes if the identity doesn’t look similar enough or the style isn’t quite right.
Limitations

This is a test version. We’ve noticed that it might not work as well for some male faces. We’re working on making it better, so check back for updates!

Learn More

If you want to know more about the tech stuff and see some example images, visit our GitHub repository .

If PuLID-FLUX is helpful, please star our repo or tell your friends about it!

Questions or Suggestions?

If you have questions or ideas, please open an issue on our GitHub repository.

Citation

If you use PuLID in your work, please cite:

@article{guo2024pulid,
  title={PuLID: Pure and Lightning ID Customization via Contrastive Alignment},
  author={Guo, Zinan and Wu, Yanze and Chen, Zhuowei and Chen, Lang and He, Qian},
  journal={arXiv preprint arXiv:2404.16022},
  year={2024}
}
Support

If you like my work, please follow me! @zsakib_

Runs of zsxkib flux-pulid on replicate.com

601.2K
Total runs
5.6K
24-hour runs
17.5K
3-day runs
38.0K
7-day runs
173.9K
30-day runs

More Information About flux-pulid replicate.com Model

flux-pulid replicate.com

flux-pulid replicate.com is an AI model on replicate.com that provides flux-pulid's model effect (⚡️FLUX PuLID: FLUX-dev based Pure and Lightning ID Customization via Contrastive Alignment🎭), which can be used instantly with this zsxkib flux-pulid model. replicate.com supports a free trial of the flux-pulid model, and also provides paid use of the flux-pulid. Support call flux-pulid model through api, including Node.js, Python, http.

flux-pulid replicate.com Url

https://replicate.com/zsxkib/flux-pulid

zsxkib flux-pulid online free

flux-pulid replicate.com is an online trial and call api platform, which integrates flux-pulid's modeling effects, including api services, and provides a free online trial of flux-pulid, you can try flux-pulid online for free by clicking the link below.

zsxkib flux-pulid online free url in replicate.com:

https://replicate.com/zsxkib/flux-pulid

flux-pulid install

flux-pulid is an open source model from GitHub that offers a free installation service, and any user can find flux-pulid on GitHub to install. At the same time, replicate.com provides the effect of flux-pulid install, users can directly use flux-pulid installed effect in replicate.com for debugging and trial. It also supports api for free installation.

flux-pulid install url in replicate.com:

https://replicate.com/zsxkib/flux-pulid

Url of flux-pulid

Provider of flux-pulid replicate.com

Other API from zsxkib

replicate

📖 PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Total runs: 1.2M
Run Growth: 278.6K
Growth Rate: 23.22%
Updated: May 16 2024
replicate

Blip 3 / XGen-MM, Answers questions about images ({blip3,xgen-mm}-phi3-mini-base-r-v1)

Total runs: 1.0M
Run Growth: 30.8K
Growth Rate: 3.08%
Updated: May 13 2024
replicate

Make realistic images of real people instantly

Total runs: 762.2K
Run Growth: 31.3K
Growth Rate: 4.11%
Updated: December 11 2024
replicate

Create song covers with any RVC v2 trained AI voice from audio files.

Total runs: 546.6K
Run Growth: 58.1K
Growth Rate: 10.63%
Updated: November 15 2023
replicate

🎨 Fill in masked parts of images with FLUX.1-dev 🖌️

Total runs: 316.0K
Run Growth: 116.9K
Growth Rate: 36.99%
Updated: August 19 2024
replicate

Age prediction using CLIP - Patched version of `https://replicate.com/andreasjansson/clip-age-predictor` that works with the new version of cog!

Total runs: 177.5K
Run Growth: 5.9K
Growth Rate: 3.32%
Updated: June 06 2023
replicate

✍️✨Prompts to auto-magically relights your images

Total runs: 165.2K
Run Growth: 13.4K
Growth Rate: 8.11%
Updated: May 21 2024
replicate

✨DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

Total runs: 131.4K
Run Growth: 800
Growth Rate: 0.61%
Updated: October 12 2023
replicate

allenai/Molmo-7B-D-0924, Answers questions and caption about images

Total runs: 60.3K
Run Growth: 10.7K
Growth Rate: 22.91%
Updated: September 26 2024
replicate

🎨 AnimateDiff (w/ MotionLoRAs for Panning, Zooming, etc): Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

Total runs: 54.5K
Run Growth: 1.3K
Growth Rate: 2.39%
Updated: October 05 2023
replicate

Add sound to video. An advanced AI model that synthesizes high-quality audio from video content, enabling seamless video-to-audio transformation

Total runs: 54.1K
Run Growth: 6.1K
Growth Rate: 94.91%
Updated: December 12 2024
replicate

📽️ Increase Framerate 🎬 ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation

Total runs: 51.3K
Run Growth: 300
Growth Rate: 0.58%
Updated: October 09 2023
replicate

Monster Labs' Controlnet QR Code Monster v2 For SD-1.5 on top of AnimateDiff Prompt Travel (Motion Module SD 1.5 v2)

Total runs: 10.0K
Run Growth: 100
Growth Rate: 1.00%
Updated: October 31 2023
replicate

🖼️✨Background images + prompts to auto-magically relights your images (+normal maps🗺️)

Total runs: 8.6K
Run Growth: 1.8K
Growth Rate: 20.93%
Updated: May 21 2024
replicate

Real-Time Open-Vocabulary Object Detection

Total runs: 7.8K
Run Growth: 400
Growth Rate: 5.13%
Updated: February 12 2024
replicate

Text-to-Video + Image-to-Video: Pyramid Flow Autoregressive Video Generation method based on Flow Matching

Total runs: 7.7K
Run Growth: 800
Growth Rate: 10.96%
Updated: October 10 2024
replicate

Create your own Realistic Voice Cloning (RVC v2) dataset using a YouTube link

Total runs: 6.9K
Run Growth: 400
Growth Rate: 5.80%
Updated: November 20 2023
replicate

🎨AnimateDiff Prompt Travel🧭 Seamlessly Navigate and Animate Between Text-to-Image Prompts for Dynamic Visual Narratives

Total runs: 5.6K
Run Growth: 0
Growth Rate: 0.00%
Updated: October 19 2023
replicate

🎨 Fill in masked parts of images with FLUX.1-schnell 🖌️

Total runs: 5.5K
Run Growth: 400
Growth Rate: 7.27%
Updated: August 15 2024
replicate

AuraSR v2: Second-gen GAN-based Super-Resolution for real-world applications

Total runs: 5.1K
Run Growth: 1.4K
Growth Rate: 27.45%
Updated: July 31 2024
replicate

Hunyuan-Video LoRA Explorer + Trainer

Total runs: 4.8K
Run Growth: 0
Growth Rate: 0.00%
Updated: January 17 2025
replicate

FlashFace: Human Image Personalization with High-fidelity Identity Preservation

Total runs: 3.5K
Run Growth: 200
Growth Rate: 5.71%
Updated: April 22 2024
replicate

Make realistic images of real people instantly (w/ ip-adapter-plus-face_sdxl_vit-h)

Total runs: 3.3K
Run Growth: 300
Growth Rate: 9.09%
Updated: July 14 2024
replicate

🖼️ Super fast 1.5B Image Captioning/VQA Multimodal LLM (Image-to-Text) 🖋️

Total runs: 2.2K
Run Growth: 100
Growth Rate: 4.55%
Updated: February 01 2024
replicate

MimicMotion: High-quality human motion video generation with pose-guided control

Total runs: 2.1K
Run Growth: 200
Growth Rate: 9.52%
Updated: July 16 2024
replicate

Idefics3-8B-Llama3, Answers questions and caption about images

Total runs: 2.0K
Run Growth: 0
Growth Rate: 0.00%
Updated: August 15 2024
replicate

AuraSR: GAN-based Super-Resolution for real-world

Total runs: 1.9K
Run Growth: 100
Growth Rate: 5.26%
Updated: June 27 2024
replicate

Qwen 2: A 7 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Total runs: 1.6K
Run Growth: 0
Growth Rate: 0.00%
Updated: June 25 2024
replicate

Cubiq's ComfyUI InstantID node running `instantid_basic.json` example

Total runs: 1.3K
Run Growth: 0
Growth Rate: 0.00%
Updated: August 19 2024
replicate

✨Stable Diffusion 3 w/ ⚡InstantX's Canny, Pose, and Tile ControlNets🖼️

Total runs: 1.1K
Run Growth: 100
Growth Rate: 9.09%
Updated: June 21 2024
replicate

Jina-CLIP v2: 0.9B multimodal embedding model with 89-language multilingual support, 512x512 image resolution, and Matryoshka representations

Total runs: 1000
Run Growth: 998
Growth Rate: 99.80%
Updated: November 28 2024
replicate

Image tagger fine-tuned on WaifuDiffusion w/ (SwinV2, SwinV2, ConvNext, and ViT)

Total runs: 969
Run Growth: 50
Growth Rate: 5.16%
Updated: May 22 2024
replicate

🫦 Realistic facial expression manipulation (lip-syncing) using audio or video

Total runs: 889
Run Growth: 93
Growth Rate: 10.46%
Updated: June 12 2024
replicate

Unofficial Re-Trained AnimateAnyone (Image + DWPose Video → Animated Video of Image)

Total runs: 833
Run Growth: 8
Growth Rate: 0.96%
Updated: January 18 2024
replicate

🎼FluxMusic Text-to-Music Generation with Rectified Flow Transformer🎶

Total runs: 739
Run Growth: 107
Growth Rate: 21.79%
Updated: September 26 2024
replicate

A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions

Total runs: 709
Run Growth: 224
Growth Rate: 97.82%
Updated: December 11 2024
replicate

🐲 DragGAN 🐉 - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold"

Total runs: 583
Run Growth: 0
Growth Rate: 0.00%
Updated: July 07 2023
replicate

Surrealist digital art featuring whimsical, anthropomorphic characters with exaggerated textures and vibrant color blocking

Total runs: 479
Run Growth: 94
Growth Rate: 22.87%
Updated: October 08 2024
replicate

Transform your text into a beautiful two-tone color gradient that represents your emotions.

Total runs: 416
Run Growth: 15
Growth Rate: 3.61%
Updated: June 06 2023
replicate

Super High Quality Depth Maps 🗺️: An End-to-End Tile-Based Framework 🏗️ for High-Resolution Monocular Metric Depth Estimation 🔍📏

Total runs: 345
Run Growth: 7
Growth Rate: 2.03%
Updated: December 27 2023
replicate

🎙️Hololive text-to-speech and voice-to-voice (Japanese🇯🇵 + English🇬🇧)

Total runs: 304
Run Growth: 68
Growth Rate: 22.37%
Updated: June 03 2024
replicate

MEMO is a state-of-the-art open-weight model for audio-driven talking video generation.

Total runs: 267
Run Growth: 111
Growth Rate: 82.84%
Updated: December 11 2024
replicate

Qwen 2: A 1.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Total runs: 204
Run Growth: 2
Growth Rate: 0.98%
Updated: June 25 2024
replicate

Qwen 2: A 0.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Total runs: 189
Run Growth: 1
Growth Rate: 0.53%
Updated: June 24 2024
replicate

Convert speech in audio to text w/ `tiny`, `small`, `base`, and `large-v3` models

Total runs: 125
Run Growth: 2
Growth Rate: 1.60%
Updated: July 01 2024
replicate

Powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text prompt

Total runs: 118
Run Growth: 11
Growth Rate: 11.46%
Updated: October 23 2024
replicate

🗣️ TalkNet-ASD: Detect who is speaking in a video

Total runs: 78
Run Growth: 8
Growth Rate: 10.26%
Updated: May 01 2024
replicate

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

Total runs: 50
Run Growth: 14
Growth Rate: 56.00%
Updated: November 28 2024
replicate

A "Hello World" model for me to get to grips with `cog` and Replicate

Total runs: 44
Run Growth: 1
Growth Rate: 2.27%
Updated: June 05 2023
replicate

SAM 2: Segment Anything v2 (for in Images + Videos)

Total runs: 19
Run Growth: 0
Growth Rate: 0.00%
Updated: July 31 2024
replicate

Easily create video datasets with auto-captioning for Hunyuan-Video LoRA finetuning

Total runs: 13
Run Growth: 0
Growth Rate: 0.00%
Updated: January 17 2025
replicate

Remove background from images using BRIA-RMBG-2.0

Total runs: 2
Run Growth: 0
Growth Rate: 0.00%
Updated: November 25 2024