Step-by-Step Guide to Fine-Tune Flux.1 with AI Toolkit and Generate Images for Ecommerce

September 23, 2024

Introduction

AI-generated images have transformed how designers, artists, and content providers produce visual content today. Artists and designers are using AI models to produce high-quality visuals from text prompts in order to enhance creativity and streamline workflows. On the other hand, ecommerce businesses are using this technology to generate customized product visuals and improve engagement. The ability to quickly generate tailored images is helping companies streamline and scale their content-generation pipelines.

A key development is the use of AI models like Flux.1, which can produce detailed, context-based visuals from simple text prompts. This is particularly useful for ecommerce companies, allowing them to create personalized product displays that cater to individual customer preferences, offering a more dynamic and visually appealing shopping experience.

In this article, we will walk you through the process of fine-tuning Flux.1 to generate tailored images for any e-commerce platform.

AI Toolkit

The AI Toolkit is a comprehensive tool created to streamline AI model training, especially for utilizing LoRA and Flux. It has an easy-to-use configuration for activities such as generating images, managing datasets, and training models. This toolkit provides flexibility during training by allowing users to customize particular layers for training and control VRAM usage. Also, it can connect with Hugging Face for sharing models and has a Gradio UI for effortless interaction while training.

Steps to Fine-Tune Flux.1

Step 1: Set Up the Environment and Clone the AI Toolkit

For fine-tuning image generation models like Flux.1, you need a high-end GPU like NVIDIA A100 which you can rent on E2E Cloud.

To get started, sign up to E2E Cloud and launch a cloud GPU node. E2E Cloud offers the most price-performant cloud GPUs in the Indian market. You get blazing-fast performance at a price point that’s far cheaper than AWS, GCP, or Azure. Check the pricing page to learn more.

When launching the cloud GPU, make sure you add your public SSH key (id_rsa.pub). This will allow you to remote SSH into the node in the following way:


$ ssh root@

Once you have logged in, create a user using the adduser command, and add the user to the `sudo-ers` list using `visudo`.


$ adduser username
$ visudo

You can now create a Python virtual environment.


$ python3 -m venv .env
$ source .env/bin/activate

Install Jupyter Lab and then use that to build this example:


$ pip install jupyterlab
$ jupyter lab

Once you have your Jupyter environment set up, clone the ai-toolkit repository and install the following libraries:


git clone https://github.com/ostris/ai-toolkit
cd ai-toolkit
pip install torch peft
pip install -r requirements.txt
git submodule update --init --recursive

Step 2: Provide a Hugging Face Token

Replace xxxxxxxxxxxxx with your own Hugging Face token and make sure it has access to the Flux.1-dev model.


export HF_TOKEN=xxxxxxxxxxxxx

Step 3: Prepare the Dataset

Prepare a dataset for fine-tuning the Flux model. The dataset should contain at least 15-20 images in JPG format; create a corresponding text file containing captions for each image with the same name. In this tutorial, we explore visual representations with an Indian touch.

Example:

Caption:

A girl with long black hair is sitting indoors on a chair, smiling with her mouth slightly open. She is holding a cup or mug in her hand, wearing a wristwatch and bracelet as part of her jewelry. Her outfit is a dress, and the scene has a realistic feel, capturing a casual moment of her enjoying a drink.

Step 4: Set Up the Configurations

After preparing the dataset, you need to set up the configurations for fine-tuning the model. Navigate to ai-tookit/config/examples. There, you will find the train_lora_flux_24gb.yaml configuration file according to your needs. Here are the configurations I used for this project.


---
job: extension
config:
 # this name will be the folder and filename name
 name: "Fine_tuned_Flux.1”
 process:
   - type: 'sd_trainer'
     # root folder to save training sessions/samples/weights
     training_folder: "output"
     # uncomment to see performance stats in the terminal every N steps
#      performance_log_every: 1000
     device: cuda:0
     # if a trigger word is specified, it will be added to captions of training data if it does not already exist
     # alternatively, in your captions you can add [trigger] and it will be replaced with the trigger word
#      trigger_word: "p3r5on"
     network:
       type: "lora"
       linear: 16
       linear_alpha: 16
     save:
       dtype: float16 # precision to save
       save_every: 250 # save every this many steps
       max_step_saves_to_keep: 4 # how many intermittent saves to keep
       push_to_hub: false #change this to True to push your trained model to Hugging Face.
       # You can either set up a HF_TOKEN env variable or you'll be prompted to log-in        
#       hf_repo_id: your-username/your-model-slug
#       hf_private: true #whether the repo is private or public
     datasets:
       # datasets are a folder of images. captions need to be txt files with the same name as the image
       # for instance image2.jpg and image2.txt. Only jpg, jpeg, and png are supported currently
       # images will automatically be resized and bucketed into the resolution specified
       # on windows, escape back slashes with another backslash so
       # "C:\\path\\to\\images\\folder"
       - folder_path: "/home/ml/projects/flux.1/ai-toolkit/dataset"
         caption_ext: "txt"
         caption_dropout_rate: 0.05  # will drop out the caption 5% of time
         shuffle_tokens: false  # shuffle caption order, split by commas
         cache_latents_to_disk: true  # leave this true unless you know what you're doing
         resolution: [ 512, 768, 1024 ]  # flux enjoys multiple resolutions
     train:
       batch_size: 1
       steps: 1000  # total number of steps to train 500 - 4000 is a good range
       gradient_accumulation_steps: 1
       train_unet: true
       train_text_encoder: false  # probably won't work with flux
       gradient_checkpointing: true  # need the on unless you have a ton of vram
       noise_scheduler: "flowmatch" # for training only
       optimizer: "adamw8bit"
       lr: 1e-4
       # uncomment this to skip the pre training sample
#        skip_first_sample: true
       # uncomment to completely disable sampling
#        disable_sampling: true
       # uncomment to use new vell curved weighting. Experimental but may produce better results
#        linear_timesteps: true


       # ema will smooth out learning, but could slow it down. Recommended to leave on.
       ema_config:
         use_ema: true
         ema_decay: 0.99


       # will probably need this if gpu supports it for flux, other dtypes may not work correctly
       dtype: bf16
     model:
       # huggingface model name or path
       name_or_path: "black-forest-labs/FLUX.1-dev"
       is_flux: true
       quantize: true  # run 8bit mixed precision
#        low_vram: true  # uncomment this if the GPU is connected to your monitors. It will use less vram to quantize, but is slower.
     sample:
       sampler: "flowmatch" # must match train.noise_scheduler
       sample_every: 250 # sample every this many steps
       width: 1024
       height: 1024
       prompts:
         # you can add [trigger] to the prompts here and it will be replaced with the trigger word
#          - "[trigger] holding a sign that says 'I LOVE PROMPTS!'"\
         - "woman with red hair, playing chess at the park, bomb going off in the background"
         - "a woman holding a coffee cup, in a beanie, sitting at a cafe"
         - "a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini"
         - "a man showing off his cool new t shirt at the beach, a shark is jumping out of the water in the background"
         - "a bear building a log cabin in the snow covered mountains"
         - "woman playing the guitar, on stage, singing a song, laser lights, punk rocker"
         - "hipster man with a beard, building a chair, in a wood shop"
         - "photo of a man, white background, medium shot, modeling clothing, studio lighting, white backdrop"
         - "a man holding a sign that says, 'this is a sign'"
         - "a bulldog, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle"
       neg: ""  # not used on flux
       seed: 42
       walk_seed: true
       guidance_scale: 4
       sample_steps: 20
# you can add any additional meta info here. [name] is replaced with config name at top
meta:
 name: "[name]"
 version: '1.0'

Step 5: Start the Training Process

After the dataset and configurations are ready, start the training process by navigating the AI Toolkit directory and running the following command:


python run.py config/examples/train_lora_flux_24gb.yaml

This process may take some time depending on your GPU and configurations.

Step 6: Test the Fine-Tuned Model

Now the fine-tuned model is ready to be tested. Test it first by loading the model through the Flux pipeline and adding the LoRA weights,

replace /home/vansh/ai-toolkit/output/Fine_tuned_Flux.1/Fine_tuned_Flux.1.safetensors with location and name of your saved model.


import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("/home/vansh/ai-toolkit/output/Fine_tuned_Flux.1/Fine_tuned_Flux.1.safetensors",adapter_name="default")
pipe.enable_model_cpu_offload()

Add the prompt for the image you want to generate – its height, width, and name as you would like to save the image as.


prompt = "A girl wearing pink lehenga-choli in the Indian style, with earrings and necklace."
image = pipe(
   prompt,
   height=1024,
   width=1024
).images[0]
image.save("flux-dev3.png")

Display the image using the `matplotlib` library.


import matplotlib.pyplot as plt
import matplotlib.image as mpimg

img = mpimg.imread('flux-dev3.png') 
plt.imshow(img)
plt.axis('off') 
plt.show()

Outputs:

Prompt 1:

A dark-skinned girl with black hair is wearing a red lehenga, including a red skirt. She is smiling and looking directly at the viewer. Her jewelry includes earrings, a necklace, a bracelet, and a ring. The scene has a realistic feel, with a slightly blurry background that emphasizes her makeup and lipstick, creating a vibrant yet soft appearance.

Prompt 2:

A girl with black hair is standing and looking at the viewer. She is wearing a white lehenga, and adorned with jewelry including a bracelet, necklace, and earrings.

‍

Prompt 3:

A dark-skinned handsome boy with short black hair and a beard is standing against a brick wall. He is wearing a white collared shirt with sleeves rolled up, denim jeans, and sunglasses. His hands are clasped together, and he is adorned with jewelry, including a bracelet. The image is realistic, with his feet out of the frame and his lips slightly parted.

‍

‍

Conclusion

By following this guide, you can easily fine-tune the Flux.1 model to generate high-quality, customized images tailored to your needs. By using tools such as the AI Toolkit, you can simplify the tasks of preparing datasets, configuring models, and generating images for achieving effective and visually appealing outcomes. This can be a very useful tool for ecommerce companies to market products and create personalized shopping experiences.

Sign up for Free Trial

Latest Blogs

November 4, 2024

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.
CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels.

Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

‍

Reference Links

https://www.helpscout.com/customer-acquisition/

https://www.cloudways.com/blog/customer-acquisition-strategy-for-startups/

https://blog.hubspot.com/service/customer-acquisition

This is a decorative image for: Constructing 3D objects through Deep Learning

October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

Highly calibrated cameras that take a photograph of the image from various angles.
Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website.

‍

Reference Links

https://tongtianta.site/paper/68922

https://github.com/natowi/3D-Reconstruction-with-Deep-Learning-Methods

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts

October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

https://analyticsindiamag.com/comprehensive-guide-to-deep-q-learning-for-data-science-enthusiasts/

https://medium.com/@jereminuerofficial/a-comprehensive-guide-to-deep-q-learning-8aeed632f52f

October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
GAUDI also removes GANs pathologies like mode collapse and improved GAN.
GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
The scenes are thus synthesized by interpolation within the hidden space.
The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

‍

Reference Links

https://www.researchgate.net/publication/362323995_GAUDI_A_Neural_Architect_for_Immersive_3D_Scene_Generation

https://www.technology.org/2022/07/31/gaudi-a-neural-architect-for-immersive-3d-scene-generation/

https://www.patentlyapple.com/2022/08/apple-has-unveiled-gaudi-a-neural-architect-for-immersive-3d-scene-generation.html