Home Blog Page 575

NJ Unveils Resources for Using AI in Schools

Morgan Tate
-
0
NJ Unveils Resources for Using AI in Schools

New Jersey Unveils Resources for Educators to Use Artificial Intelligence in Schools

The New Jersey Department of Education has released a set of resources to help educators understand, implement, and manage artificial intelligence (AI) in schools, as part of Governor Phil Murphy’s "artificial intelligence moonshot" initiative. The resources include articles, webinars, and guidance for school districts to "responsibly and effectively" integrate AI-powered technology in the classroom.

The state’s new AI resources come as Newark Public Schools takes steps to incorporate more AI in classrooms and surveillance systems. The school district has approved a $12 million project to install over 7,000 AI cameras district-wide, which has raised concerns about privacy and potential misidentification of students or objects.

Concerns Over Safety and Privacy

Randi Weingarten, President of the American Federation of Teachers, emphasized the need for prioritizing safety and privacy in the use of AI in schools. "We know that school districts can’t just say privacy matters," she said. "There has to be a tech translator, there has to be parent information sessions, and there has to be classroom guidance."

AFT’s AI Guardrails

The AFT has released its own set of AI guardrails, which focus on maximizing safety and privacy, empowering educators to make decisions on AI, and advancing fairness and equity. The report lists six core values that school districts should consider when implementing AI in schools.

State’s AI Webinar

The state’s AI webinar introduces the fundamentals of AI technology and explains how it can support and enhance teaching and learning, as well as provide personalized feedback to students. The webinar also prompts school districts to think about how new technology can support student learning and suggests reviewing policies as AI evolves and integrates into learning.

Conclusion

As AI continues to gain popularity in schools, it is crucial for educators, policymakers, and parents to prioritize safety and privacy concerns. The New Jersey Department of Education’s resources provide a good starting point for school districts to navigate the integration of AI in schools. However, more guidance is needed to ensure that AI is used responsibly and effectively in the classroom.

Frequently Asked Questions

Q: What is the purpose of the New Jersey Department of Education’s AI resources?
A: The resources aim to help educators understand, implement, and manage AI in schools.

Q: What are the concerns about AI in schools?
A: Concerns include safety and privacy, potential misidentification of students or objects, and the need for clear guidelines and policies.

Q: What is the AFT’s stance on AI in schools?
A: The AFT prioritizes safety and privacy, emphasizes the need for educator guidance, and advocates for fairness and equity in AI implementation.

Q: What are the potential benefits of AI in schools?
A: AI can support and enhance teaching and learning, provide personalized feedback to students, and streamline administrative tasks.

New Nintendo Switch OLED Bundle Deal

Phil
-
0
New Nintendo Switch OLED Bundle Deal

Nintendo Switch OLED Bundle Deal

Unbeatable Offer: Mario Kart 8 Deluxe OLED Bundle for $275.99

I’ve been following the Nintendo Switch market for a long time, and I know the tiny fluctuations in price across the Switch range. I like to think I know what will happen during Black Friday. However, Target has just blown everything out of the water by slashing a new OLED bundle deal down to a price that’s lower than I’ve ever seen a standalone console on sale for. Get the Mario Kart 8 Deluxe OLED bundle for $275.99 right now, a real-terms saving of $144.

The Bundle Breakdown

The console itself is usually $349, which is the RRP of the bundle. This bundle would normally get you $79.98 of added value in the form of the Mario Kart 8 game AND 12 months of Switch online from Nintendo.

Record Low Price in the UK

In the UK, there’s a record-low price on the Nintendo Switch OLED console, available for just £224 at OnBy.

More Deals to Check Out

Check out our Nintendo Black Friday live blog for more deals. If this isn’t what you’re looking for, see the deals we’ve found below:

Frequently Asked Questions

Q: What is the usual price of the Nintendo Switch OLED console?
A: The usual price of the Nintendo Switch OLED console is $349.

Q: What’s included in the Mario Kart 8 Deluxe OLED bundle?
A: The bundle includes the Nintendo Switch OLED console, the Mario Kart 8 Deluxe game, and 12 months of Switch online from Nintendo.

Q: Is this deal available in the UK?
A: Yes, a record-low price is available in the UK at OnBy for £224.

Q: What other deals are available for the Nintendo Switch?
A: Check out our Nintendo Black Friday live blog for more deals.

AI Image Generator Gets Major Upgrade

Emerson Blake
-
0
AI Image Generator Gets Major Upgrade

BlackForestLabs Upgrades FLUX.1 Platform with FLUX.1 Tools

Most AI image generators have guardrails to prevent people from creating harmful images. However, BlackForestLabs’s FLUX.1 platform does not, and — combined with its realistic image generations — has inspired viral image creations. Now, the model is getting a massive upgrade.

New Features for Image Control and Manipulation

On Thursday, the company announced FLUX.1 Tools, a suite of models that can help users modify images created with its FLUX text-to-image model, offering more options for image control and manipulation. The four features of this suite include Fill, Depth, Canny, and Redux.

FLUX.1 Fill: Inpainting and Outpainting Capabilities

With Flux.1 Fill, users can access inpainting and outpainting capabilities on their images, meaning they can seamlessly remove from or add to an image and even expand the image beyond the borders of its original frame. As seen below, the differences are added seamlessly, blending into the background and making it hard to distinguish from the original.

Structural Conditioning with Depth Detection

The FLUX. Tools also allow for structural conditioning, which uses canny edge or depth detection to map the elements of an image’s structure and keep the composition and structure in future generations, as seen in the image below.

Black Forest Labs

Black Forest Labs

Redux: Variations of Existing Images

Lastly, Redux is an adapter for the FLUX.1 models, which enables users to produce a new version of an existing image with slight variations.

BlackForestLabs

BlackForestLabs

State-of-the-Art Performance

BlackForestLabs includes benchmark results for each one of these features; the FLUX 1 Tool outperforms other state-of-the-art models, including Ideogram V2, Stable Diffusion 1.5, Midjourney Retexture, and more, according to the company.

Availability and Pricing

The FLUX.1 Tools are available as open-access models within the FLUX.1 [dev] model series, and in the BFL API supplementing FLUX.1 [pro]. To try out the FLUX.1 generator, you can access it on X via Grok with a Premium or Premium+ subscription, which starts at $7 per month.

Conclusion

The upgrade to FLUX.1 Tools offers more control and manipulation options for users, allowing them to create unique and realistic images. The new features and state-of-the-art performance make the FLUX.1 generator an attractive option for those looking to explore the capabilities of AI image generation.

Frequently Asked Questions

Q: What are the benefits of FLUX.1 Tools?

A: FLUX.1 Tools offer more control and manipulation options for users, allowing them to create unique and realistic images.

Q: How does FLUX.1 Fill work?

A: FLUX.1 Fill allows users to access inpainting and outpainting capabilities, enabling them to seamlessly remove from or add to an image and even expand the image beyond its original frame.

Q: What is structural conditioning?

A: Structural conditioning uses canny edge or depth detection to map the elements of an image’s structure and keep the composition and structure in future generations.

Q: Is the FLUX.1 generator available for free?

A: No, the FLUX.1 generator requires a Premium or Premium+ subscription to X via Grok, which starts at $7 per month. However, the FLUX.1 Tools are available as open-access models within the FLUX.1 [dev] model series.

LoRA Caption Workflow for ComfyUI

Phil
-
0
LoRA Caption Workflow for ComfyUI

ComfyUI LoRA Caption Workflow

I’m very happy to share my LoRA Caption workflow for ComfyUI that will let you run a batch of images through two different captioning methods using Florence 2 model or using Clip Interrogator. Both these are paired with WD14 Tagger node which generates some additional tags/keywords for the caption.

Workflow Overview

The workflow consists of several nodes that work together to generate captions for a batch of images. The images must be in PNG format, as JPEGs are not supported currently in the workflow due to custom node.

LoRA Training "Trigger" Word

You can enter the LoRA training "trigger" word which is added to the prompt.

Node Breakdown

  1. Florence 2 Model: This node uses the Florence 2 model to generate captions for the images.
  2. Clip Interrogator: This node uses the Clip Interrogator to generate captions for the images.
  3. WD14 Tagger: This node generates some additional tags/keywords for the caption.

Useful Tips

  • Caption files generated cannot be overwritten – this is a limitation of the custom node, if you want to re-run, delete the original TXT file.
  • Once all images are run through, you need to Reset the counter. Use the Reset counter (use once) switch – set to true. Remember to turn it off – set to false.
  • List index out of range error – this means you are trying to run it but the txt file caption already exists. Or the counter has reached its limit, you need to reset it.
  • Always review the captions and fine-tune them to ensure you get the best result out of your LoRA.

Conclusion

The ComfyUI LoRA Caption workflow is a powerful tool for generating captions for a batch of images. By using the Florence 2 model and Clip Interrogator, you can generate high-quality captions for your images. Remember to keep the useful tips in mind to get the best results from this workflow.

Frequently Asked Questions

Q: What format should my images be in?
A: Images must be in PNG format.

Q: Can I use JPEGs?
A: No, JPEGs are not supported currently in the workflow due to custom node.

Q: How do I reset the counter?
A: Use the Reset counter (use once) switch – set to true, then turn it off – set to false.

Q: What if I get a List index out of range error?
A: This means you are trying to run it but the txt file caption already exists. Or the counter has reached its limit, you need to reset it.

Building Generative AI Applications on Amazon Bedrock with AWS SDK for Python

Jordan Waverly
-
0
Building Generative AI Applications on Amazon Bedrock with AWS SDK for Python

Solution Overview

The solution uses an AWS SDK for Python script with features that invoke Anthropic’s Claude 3 Sonnet on Amazon Bedrock. By using this FM, it generates an output using a prompt as input. The following diagram illustrates the solution architecture.

Prerequisites

Before you invoke the Amazon Bedrock API, make sure you have the following:

Deploy the Solution

After you complete the prerequisites, you can start using Amazon Bedrock. Begin by scripting with the following steps:

  1. Import the required libraries:
  1. Set up the Boto3 client to use the Amazon Bedrock runtime and specify the AWS Region:

# Set up the Amazon Bedrock client
bedrock_client = boto3.client(
service_name=”bedrock-runtime”,
region_name=”us-east-1″
)

  1. Define the model to invoke using its model ID. In this example, we use Anthropic’s Claude 3 Sonnet on Amazon Bedrock:

# Define the model ID
model_id = “anthropic.claude-3-sonnet-20240229-v1:0”

  1. Assign a prompt, which is your message that will be used to interact with the FM at invocation:

# Prepare the input prompt.
prompt = “Hello, how are you?”

Prompt engineering techniques can improve FM performance and enhance results.

Processing the Payload

Before invoking the Amazon Bedrock model, we need to define a payload, which acts as a set of instructions and information guiding the model’s generation process. This payload structure varies depending on the chosen model. In this example, we use Anthropic’s Claude 3 Sonnet on Amazon Bedrock. Think of this payload as the blueprint for the model, and provide it with the necessary context and parameters to generate the desired text based on your specific prompt. Let’s break down the key elements within this payload:

  • anthropic_version – This specifies the exact Amazon Bedrock version you’re using.
  • max_tokens – This sets a limit on the total number of tokens the model can generate in its response. Tokens are the smallest meaningful unit of text (word, punctuation, subword) processed and generated by large language models (LLMs).
  • temperature – This parameter controls the level of randomness in the generated text. Higher values lead to more creative and potentially unexpected outputs, and lower values promote more conservative and consistent results.
  • top_k – This defines the number of most probable candidate words considered at each step during the generation process.
  • top_p – This influences the sampling probability distribution for selecting the next word. Higher values favor frequent words, whereas lower values allow for more diverse and potentially surprising choices.
  • messages – This is an array containing individual messages for the model to process.
  • role – This defines the sender’s role within the message (the user for the prompt you provide).
  • content – This array holds the actual prompt text itself, represented as a “text” type object.
  1. Define the payload as follows:

payload = {
“anthropic_version”: “bedrock-2023-05-31”,
“max_tokens”: 2048,
“temperature”: 0.9,
“top_k”: 250,
“top_p”: 1,
“messages”: [
{
“role”: “user”,
“content”: [
{
“type”: “text”,
“text”: prompt
}
]
}
]
}

Invoking the Model

You have set the parameters and the FM you want to interact with. Now you send a request to Amazon Bedrock by providing the FM to interact with and the payload that you defined:

# Invoke the Amazon Bedrock model
response = bedrock_client.invoke_model(
modelId=model_id,
body=json.dumps(payload)
)

Processing the Response

After the request is processed, you can display the result of the generated text from Amazon Bedrock:

# Process the response
result = json.loads(response[“body”].read())
generated_text = “”.join([output[“text”] for output in result[“content”]])
print(f”Response: {generated_text}”)

Clean Up

When you’re done using Amazon Bedrock, clean up temporary resources like IAM users and Amazon CloudWatch logs to avoid unnecessary charges. Cost considerations depend on usage frequency, chosen model pricing, and resource utilization while the script runs. See Amazon Bedrock Pricing for pricing details and cost-optimization strategies like selecting appropriate models, optimizing prompts, and monitoring usage.

Conclusion

In this post, we demonstrated how to programmatically interact with Amazon Bedrock FMs using Boto3. We explored invoking a specific FM and processing the generated text, showcasing the potential for developers to use these models in their applications for a variety of use cases, such as:

  • Text generation – Generate creative content like poems, scripts, musical pieces, or even different programming languages
  • Code completion – Enhance developer productivity by suggesting relevant code snippets based on existing code or prompts
  • Data summarization – Extract key insights and generate concise summaries from large datasets
  • Conversational AI – Develop chatbots and virtual assistants that can engage in natural language conversations

About the Author

Merlin Naidoo is a Senior Technical Account Manager at AWS with over 15 years of experience in digital transformation and innovative technical solutions. His passion is connecting with people from all backgrounds and leveraging technology to create meaningful opportunities that empower everyone. When he’s not immersed in the world of tech, you can find him taking part in active sports.

Frequently Asked Questions

Q: What is Amazon Bedrock?

A: Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, and Amazon through a single API.

Q: What is Boto3?
A: Boto3 is an AWS SDK for Python that allows developers to interact with AWS services, including Amazon Bedrock.

Q: How do I invoke an FM using Boto3?
A: You can invoke an FM using Boto3 by defining the model ID, payload, and other parameters, and then sending a request to the Amazon Bedrock API.

Kauê Daiprai

Phil
-
0
Kauê Daiprai

Kauê Daiprai: A Brazilian Artist Inspired by Nature and Imagination

Kauê is a Brazilian artist and teacher driven by a sense of wonder for the natural world and the landscape of imagination. Working predominantly in Photoshop, ZBrush, and Blender, Kauê is developing his own comic and gets his inspiration from artists such as Moebius, Paul Felix, and Claire Wendling.

Old Windmill Shore

“Inspired by the grassy hills near the sea found in southern Brazil, this piece conveys the feelings of freedom and adventure I associate with these beautiful landscapes.”

(Image credit: Kauê Daiprai)

Regression

“Inspired by a regressive experience where I imagined myself as a wounded warrior aided by a river faerie. This reflects my connection to the element of water.”

Kauê Daiprai artwork

(Image credit: Kauê Daiprai)

Bowman vs Iron Hog

“This tells the joy and nostalgia of my childhood playing MapleStory. I wanted to capture the excitement of those times and connect with others who share that.”

Kauê Daiprai artwork

(Image credit: Kauê Daiprai)

Conclusion

Kauê’s artwork is a testament to the power of imagination and the importance of connecting with nature. His use of digital tools allows him to bring his ideas to life in a unique and captivating way. Whether he’s exploring the natural world or drawing inspiration from his childhood, Kauê’s artwork is a reflection of his creativity and passion.

FAQs

Q: What inspires Kauê’s artwork?
A: Kauê’s artwork is inspired by the natural world, his childhood, and his connection to the element of water.

Q: What digital tools does Kauê use?
A: Kauê uses Photoshop, ZBrush, and Blender to create his artwork.

Q: What is the significance of the element of water in Kauê’s artwork?
A: The element of water is significant in Kauê’s artwork as it represents his connection to the natural world and his ability to heal and regenerate.

Q: What is the meaning behind the artwork “Bowman vs Iron Hog”?
A: The artwork “Bowman vs Iron Hog” is a reflection of Kauê’s childhood playing MapleStory and his desire to capture the excitement and nostalgia of those times.

Flux Dev LoRa Collection

Phil
-
0
Flux Dev LoRa Collection

Flux Dev LoRAs: A Collection of Cool and Creative Options

Realism Flux LoRA by XLabs-AI
Adds more realism to your final image with more detail, including finer details like hair, eyes, and skin textures. This LoRA was converted for use with ComfyUI by comfyannonymous. There are no trigger words for this LoRA.

Download Realism Flux Dev LoRA

Antiblur LoRA by Shakker Labs
This LoRA increases the depth of field, controlled by its strength parameter. By default, photographic results have a very shallow depth of field straight out of Flux Dev. This LoRA increases the depth, so you have more details in the background. There is no trigger word, and the samples were taken at Strength 1.0.

Download Antiblur LoRA

Half Illustration by Davisbro
This LoRA is great for photo and illustration combined generation. If you’ve clicked on this post’s thumbnail or some of my YT videos lately, then you’ve seen what this Flux Dev LoRA can do. Trigger word: TOK.

Download Half illustration

Frosting Lane by Araminta
A soft pastel illustration style LoRA for Flux Dev. This LoRA combines the power of Flux and focuses on a beautiful anime style. Trigger word: frostingln illustration.

Download Frosting Lane

Flux Film Foto by Araminta
35mm film style images that take the overcooked photographic outputs of Flux Dev to a whole new level of realism. Trigger word: flmft photo style.

Download Flux Film Foto

Soft Serve Anime by Araminta
Soft color anime style images are produced when you use this LoRA. It combines the power of Flux and focuses on a beautiful anime style. Trigger word: sftsrv style illustration.

Download Soft Serve Anime

Linnea Beta by Araminta
Trained on her own hand-drawn sketches, this cute little character emerges with simple hand-drawn lines and simple color scheme. Trigger word: linnea teal hair.

Download Linnea Beta

Mooniverse by Araminta
Another photographic LoRA with very nice soft aesthetics (soft focus) and muted colors, which produce some very nice results out of Flux Dev.

Download Mooniverse

Sonny Anime Flex by Araminta
Create soft gel line anime style images in a sort of cute lofi aesthetic. This is the FLEX version, which has more flexibility and can be pushed away from true anime towards cartoon art and more complex scenes. However, it is recommended to include the style direction in your trigger. Trigger word: nm22 [style direction] style.

Download Sonny Anime Flex

Koda Diffusion by Araminta
Koda captures the nostalgic essence of early 1990s photography, evoking memories of disposable cameras and carefree travels. It specializes in creating images with a distinct vintage quality, characterized by slightly washed-out colors, soft focus, and the occasional light leak or film grain. Trigger word: flmft style.

Download Koda Diffusion

Midsummer Blues by Jake Dahn
A minimalist yet colorful illustration style LoRA for Flux Dev that gives you a very beautiful, vibrant illustrated result, unlike other models with Flux Dev. You get the correct number of figures and better compositions. Trigger word: MSMRB (but it works better when used like illustrated MSMRB style).

Download Midsummer Blues

Conclusion
These are some of the coolest-looking Flux Dev LoRAs that have been found on the internet. We hope you enjoy using them. They are small enough that you can download them all and achieve wonderful results with Flux Dev.

FAQs

Q: How do I use these LoRAs?
A: Simply copy the LoRA files into the models\loras folder of ComfyUI or models\lora folder of Automatic1111.

Q: What are trigger words?
A: Trigger words are specific words or phrases that can help the LoRA produce the desired output. They can be found in the description of each LoRA.

Q: How do I get the best results with these LoRAs?
A: Experiment with different trigger words, styles, and parameters to achieve the desired output. You can also combine multiple LoRAs to create unique results.

Q: Can I use these LoRAs with other models?
A: Yes, you can use these LoRAs with other models, but the results may vary. It’s recommended to use them with Flux Dev for the best results.

Q: Where can I find more LoRAs?
A: You can find more LoRAs on the internet or create your own using AI models like Flux Dev.

New AI Chatbot Champ Emerges

Emerson Blake
-
0
New AI Chatbot Champ Emerges

AI Rivalry Heats Up: OpenAI and Google Battle for Model Supremacy

The Battle for Chatbot Supremacy

OpenAI and Google, two major players in the artificial intelligence (AI) industry, are engaged in a fierce battle for model supremacy in the public forum. The competition is rapidly intensifying, with both companies constantly pushing the boundaries of what is possible.

GPT-4o Update Boosts OpenAI’s Chatbot

Just a day after OpenAI secured the number one chatbot title in the Chatbot Arena with its GPT-4o update, Google released Gemini Exp 1121, an experimental model that quickly rose to tie with ChatGPT for the top spot.

Gemini Exp 1121: An Experimental Model

Compared with Gemini’s last release, Exp 1114, the model’s update helped it climb from third to first place overall, and specifically improved in hard prompts, coding, math, and creative writing. Gemini had already been in first place in the vision category.

The Rapid Progress of AI Developments

The ranking switch-up illustrates the exponential progress of AI developments, especially considering that ChatGPT has long occupied the top spot in the Chatbot Arena, even with truncated models like GPT-4o mini. Google’s jump marks the third trade of the crown between the two companies in a single week.

Significant Gains in Coding and Visual Comprehension

Logan Kilpatrick, senior product manager at Google, posted on X about the release, noting that the experimental model comes with "significant gains" in coding, as well as better reasoning and visual comprehension.

Testing Gemini Exp 1121

For those who want to test it themselves, users can try Gemini Exp 1121 in the Chatbot Arena itself per usual. The model is available now in Google AI Studio and via the Gemini API.

Conclusion

The battle for AI model supremacy is becoming increasingly intense, with both OpenAI and Google pushing the boundaries of what is possible. As AI continues to advance at an exponential rate, it will be exciting to see how these two companies continue to innovate and improve their models.

Frequently Asked Questions

Q: What is the current ranking in the Chatbot Arena?
A: OpenAI’s GPT-4o and Google’s Gemini Exp 1121 are currently tied for the top spot.

Q: What are the improvements in Gemini Exp 1121?
A: The model has improved in hard prompts, coding, math, and creative writing, as well as better reasoning and visual comprehension.

Q: How can I test Gemini Exp 1121?
A: Users can try Gemini Exp 1121 in the Chatbot Arena itself per usual, and the model is available now in Google AI Studio and via the Gemini API.

Q: Are generally available models on the way?
A: Yes, according to Logan Kilpatrick, but no release date has been provided.

Weird Wonderful AI Art

Phil
-
0
Weird Wonderful AI Art

Flux Dev Artist Study: A Comprehensive Analysis

Flux Dev is an impressive model that produces high-quality images. We decided to run a large-scale experiment to see how well it replicates the art of 4100+ artists. This study aims to provide insights into the model’s capabilities and limitations.

Methodology

To conduct this study, we built a ComfyUI workflow that allowed us to read formatted prompts from a text file and run them one after another. This was a fun experiment to build, as there was no existing solution for batch processing in ComfyUI.

Prompt and Settings

We used the following settings for our experiment:

  • Art: [artist name]
  • Resolution: 1024×1024 px
  • Seed: 88888888
  • Image batch: 4

Results

The study yielded 50 images, which are available in our online gallery. Due to the large size of the full dataset, we have made it available for offline download.

Offline Version

The offline version includes:

  • 2 ZIP files containing all the files
  • 1 PDF overview document with observations

Conclusion

Our Flux Dev Artist Study provides valuable insights into the model’s capabilities and limitations. We hope that this resource will be beneficial for those experimenting with Flux Dev and will encourage others to share their findings.

Frequently Asked Questions

Q: What is the purpose of this study?
A: The purpose of this study is to analyze the Flux Dev model’s ability to reproduce the art of 4100+ artists.

Q: How did you conduct the study?
A: We built a ComfyUI workflow to run the prompts from a text file and process them in batches.

Q: What settings did you use for the study?
A: We used the following settings: art, resolution, seed, and image batch.

Q: How can I access the full study?
A: The full study is available for offline download. You can also view a selection of images in our online gallery.

Add Text Behind Image Workflow

Phil
-
0
Add Text Behind Image Workflow

Adding Text Behind an Image with ComfyUI

Ever in the need of adding some text in the image, well that’s easy with any image editor. Well, the trickiness comes when you want to add the text in between the Subject and the Background so the image is sliced up and then merged back in three layers.

The Layers

  • Layer 1 – Foreground subject of the image
  • Layer 2 – Text you want to insert (behind the subject)
  • Layer 3 – The background of the image

The Process

So, it’s like taking a very sharp sashimi knife and slicing the image by carefully removing the subject and then adding the text behind it. It’s quite easily done in ComfyUI using BirefNet General model which will remove the background from the image thereby giving you a cleanly separate image of the subject.

Now that you have the subject, it’s about building the three layers in ComfyUI Workflow and creating the merged image. For this, we need to utilise a few nodes from the Essentials bundle. Install these using your ComfyUI Manager or when you load the workflow use the Install Missing Nodes option.

The Workflow

For a preview of the resulting image, my workflow only produces a Preview of the resulting image. If you wish to save the final Image, you need to replace the Preview Image with Save Image node.

Download

The download is available here, click on the button to get the Zip file containing the workflow in two formats PNG and JSON.

Results

Here are some of the resulting images I have managed to produce with this workflow. Pretty neat that you can achieve all this just using ComfyUI.

Conclusion

I hope you like using this workflow and have fun extending it to do more.

FAQs

Q: What is the purpose of this workflow?
A: The purpose of this workflow is to add text behind an image using ComfyUI.

Q: How do I use this workflow?
A: You can use this workflow by installing the necessary nodes from the Essentials bundle and following the steps outlined in the article.

Q: What is the output of this workflow?
A: The output of this workflow is a preview of the resulting image, which can be saved as an image using the Save Image node.

1...574575576...740Page 575 of 740

Welcome to MachineDaily.AI, your go-to destination for breaking news, in-depth analysis, and the latest developments in the world of artificial intelligence (AI). Our mission is to provide you with timely and insightful content that explores AI’s vast potential across industries and its growing impact on society. From cutting-edge innovations to ethical debates, MachineDaily.AI is committed to covering AI in all its forms, making complex topics accessible to experts, enthusiasts, and curious minds alike.

Latest

Categories

Useful Links

Our Newsletter

Subscribe Us To Receive Our Latest News Directly In Your Inbox!

© Copyright 2024. All Right Reserved By Machine Daily.