Top Stable Diffusion Jobs

Looking for Guidance from an expert on how to train a dreambooth model to achieve a consistent ai influencer character.

We are looking for someone who is experienced in the use of AI tools like stable diffusion and who has experience in setting up new tools & infrastructures on our virtual machine.

When we say new tools we often mean new research papers that do not yet have the user-friendliness of existing tools and therefor have more complexity setting up.

Your key goals would be:

1. Setting up tools (installing them and making sure they work)

2. documenting how to use the tools

3. training Stable Diffusion, google colab, foocus and other models based on our own images.

4. Give advice on the best AI tools to use for the job.

5. Creating a streamlined end workflow for people with less AI experience to use.

As this job involves advice we are looking for someone who knows more then just the basics of AI. we are also not looking for AI artists who can just generate images.

If you are interested please reach out.

We are developing an AI image generation app whereby the user will enter photos of themselves. The app will then train the images then allow the user to produce all kinds of AI images of themselves. Currently we have a prototype version of the app which use Stable Diffusion and is currently running off a jupyterlab interface which allows to input parameters, execute and test kohya_ss lora training

What we need is someone with good knowledge of Python and AI image generation to help us fine tune all the parameters and training models so we can achieve the highest quality images that have the strongest resemblance to the user. (IE. When looking at the images generated it actually looks like the person in the inputted photos.) So we are really looking for someone with extensive knowledge/experience of training lora models. (kohya_ss trainer)

New AI Consultancy Business connecting SMBs and Startups to AI Consultants and Experts

- Need someone willing to consult and help businesses in implementing solutions from chatbots to stable diffusion models

- Long Term Partner which I can rely on for multiple clients in full transparency from short-term projects to potentially larger

- Experience in Generative AI, NLP, ML, and DL would be helpful

We are looking for an experienced developer who have worked with Stable Diffusion (Fine tuning Dreambooth) before

We have an existing training and inference codes that runs on A40 NVIDIA and we would like to switch it to NVIDIA T4 and work with latest torch 2.1 and cuda12.1.

Please post the input the and output of the samples dreambooth photos that you have achieved before before bidding on this work (any bidding without samples will be ignored)

Thank you for your time and understanding!

**Job Description**

We are inviting a high-performing and innovative TikTok Video Creator, with exceptional skills in generative AI, to join our team full-time (40-60 hours per week). In this role, you'll be pivotal in producing fun, innovative, humorous, and educational TikTok content that disrupts traditional education paradigms. Your key task is to expertly blend your creative talents with advanced AI technology, crafting both compelling scripts and visually striking content.

**Key Responsibilities**

- Expertly employ a range of generative AI tools to elevate our content creation process. This includes using GPT-4 for nuanced and compelling scriptwriting, harnessing the power of image generation tools like Midjourney, Stable Diffusion, and Dall-E 3, creating realistic voices with ElevenLabs, and leveraging advanced text-to-video platforms such as Pika Labs or Runway.

- Create captivating TikTok videos using AI-generated assets, and masterfully edit them using software like CapCut and Adobe Premiere.

- Continuously stay abreast of and integrate the latest TikTok trends into our content.

- Rapidly adapt to changing requirements and tight deadlines, focusing on high quality and precision.

**Qualifications**

- Demonstrated expertise in generative AI for content creation, including scripting, image generation, voice generation, and video generation.

- Proven track record of producing engaging TikTok content, with a solid understanding of the platform's dynamics.

- Proven expertise in video editing software (Adobe Premiere Pro, CapCut, etc.).

- Strong grasp of TikTok trends, viral content strategies, and the platform's ecosystem.

- Excellent time management, organizational skills, and the ability to thrive under pressure.

- A natural inclination for innovation, quick learning, and adapting to new technologies and concepts.

- Effective communication skills and the capability to work collaboratively in a team.

**We Offer**

- A role at the forefront of AI-driven creative content creation.

- Competitive compensation and a chance to be part of a groundbreaking project in educational content.

- Opportunities for professional growth.

This position is ideal for those passionate about merging AI technology with creative content creation, who thrive in fast-paced and high-demand environments, and who are eager to set new trends in TikTok content. If this resonates with you, we are excited to welcome you aboard!

Please respond with your resume, portfolio, examples of relevant work, and a letter explaining in detail a complete hypothetical workflow you might use to create AI-generated TikTok content.

Dear Video Editor

We're looking for someone to join our youtube team. We're in need of someone that can help us edit video's but also could maybe include ai generated images, (basically a mix of traditional editing and incorporating ai) or stable diffusion.

This is an example channel/ video we need to at least recreate. The budget would be 25 - 35 usd per video:

https://www.youtube.com/@PropheciesintheBible-vi4wh/videos

We have a lot of videos that need to be made and with a fast delivery. If you want us to take you seriously start your proposal with 'Improve" .

Also , if you apply we would want you to make a 10-20 sec sample so we know what we can expect of you. Samples will not be compensated, so only apply if you are confident in the quality.

Hope to speak to you soon!

Description:

We are an innovative team working on an app that specializes in generating AI-enhanced photorealistic images from user-uploaded photos. We're in need of an AI and machine learning expert to guide us in selecting and integrating a robust AI model into our app's backend. The new model should overcome the limitations of our current solution, which lacks the ability to generate unique batches of images from the same inputs.

Key Responsibilities:

Recommend AI Models: Identify and suggest suitable AI models capable of generating unique image batches based on user inputs.

Implementation Strategy: Advise on the best practices for integrating the selected model into our existing app infrastructure.

Ensure Cost-Effectiveness: Propose solutions that are cost-efficient, with a target cost of less than $0.10 USD per batch.

Basic Model Requirements:

- Handles 4-12 user-uploaded photos, including clear selfies and portraits.

- Allows users to choose a "style" which will guide the image transformation.

- Capable of generating 4-6 unique images per batch, with the ability to produce diverse outputs from the same input set and style on subsequent generations.

- Maintains a high standard of photorealism and image quality.

- Operates within a cost of under $0.10 USD per batch.

Ideal Candidate:

Extensive experience and knowledge in AI and machine learning, with a focus on image generation and processing.

Demonstrated understanding of various AI image generation models and their integration into applications.

Strong problem-solving skills, particularly in identifying cost-effective and innovative AI solutions.

Excellent communication and collaboration skills.

Project Goal:

The successful integration of a new AI model that enhances our app’s capability to generate unique, high-quality photorealistic images, thereby improving user experience and distinguishing our app in the market.

We are looking for someone who can provide expert insights and direction in this field. If you have the relevant expertise and are excited about contributing to an innovative image generation project, we encourage you to apply.

Stable diffusion specialist to make a character...

Stable diffusion specialist to make a character...

In this role as a Social Media Manager, you'll:

Manage Social Media Profiles: Take the reins of our social media accounts across platforms like Instagram, Twitter, YouTube, and LinkedIn. Your focus will be on crafting and maintaining a vibrant online presence.

Develop a Content Strategy: Use your knowledge of AI tools like ChatGPT and BART to build a content strategy that resonates with our audience. You should be able to weave AI writing into compelling social media narratives.

Create Engaging Content: Dive into the world of AI and produce captivating content. We're looking for someone who can turn the complex world of AI into accessible, engaging viral posts and videos.

Trendspotting and Experimentation: You have a keen eye for social media trends and aren't afraid to experiment with content. Your creativity will be key in keeping our content fresh and engaging.

Research and Use AI Tools: You're not just familiar with AI tools; you know how to use them to streamline content creation. You'll produce high-quality content more efficiently using tools like ChatGPT and Stable Diffusion, Midjourney.

Project Overview

Our company start AI marketing from now.

At first, Our CEO want to create an AI-generated model for a unique application that involves transforming text descriptions into realistic images of social media.

Then, with the help of the stable diffusion algorithms, Lauras and Vertex AI, I hope that engineers develop AI image generation project .

This should be a cross-platform application.

If you are passionate about developing the boundaries of AI projects and have a strong problem solving ability, please submit your proposal.

Include details about your relevant experience, sample projects, and your approach to achieving consistent results.

Also upload your resume, github and portfolio.

Our CEO only consider engineer that meets our requirements and start work immediately from now.

At last, please add 'cross-platform' at the first of application.

We are an innovative technology company developing a photo AI application. Our app specializes in transforming user-uploaded selfies into AI-generated images, reflecting distinct aesthetics from various eras, currently focusing on the 70s, 80s, and 90s. We aim to expand our thematic range, offering a unique blend of photorealism and period-specific styles.

Role Overview:

We seek a highly skilled Generative AI Expert to join our team as a consultant. The ideal candidate will possess deep expertise in generative AI technologies, with a particular focus on stable diffusion and proficiency in utilizing its checkpoints. Your role will be crucial in enhancing the app’s capability to produce high-quality, stylistically accurate images while addressing common AI-generated image issues like distorted facial features (especially eyes and teeth) and unnatural hand representations.

Key Responsibilities:

Collaborate with our development team to integrate and optimize stable diffusion models into our app.

Provide expert guidance on improving the photorealism and thematic accuracy of generated images.

Develop solutions to common issues in AI-generated images, such as distorted faces and hands.

Assist in expanding the app's thematic range while maintaining high-quality outputs.

Provide ongoing support and consultation for continuous app enhancement.

Qualifications:

Demonstrable experience working with generative AI, especially in stable diffusion models.

Strong proficiency in using and adapting checkpoints for specific thematic outputs.

Knowledge of current trends and advancements in AI-generated imagery.

Ability to troubleshoot and provide innovative solutions for image quality improvements.

Excellent communication skills and a collaborative mindset.

Application Process:

Initial Assessment:

Please describe in detail your approach to generating an image similar to the one that is attached with the face of a person, using 10 different selfies of that person as the basis. This task tests your technical understanding and application methodology.

Consultation Call:

Based on your written response, we will conduct a one-hour initial consultation call. The first 10 minutes of the call will be a decisive period to assess our compatibility. If we choose to proceed, you will be compensated for the full hour; otherwise, the call will conclude after the first 10 minutes.

Looking forward to hearing from you.

🌐 Project Vision:

We are seeking a visionary Generative AI Specialist to craft a brand kit and strategy for our AI Startup (SaaS) via an extensive collection of AI-generated visuals and consulting that will form the backbone of our revamped brand identity.

This project is intended for an individual who possesses business expertise especially in regards to go-to-market and Generative AI who can merge the power of AI with strategy, innovative design concepts and branding strategy to produce a comprehensive suite of images and brand kit that resonate with our brand's core values.

🎯 What We Need:

A track record of success in Generative AI, with a portfolio that includes large-scale AI-projects.

Deep understanding and hands-on experience with AI and machine learning frameworks (Dall-E, MidJourney, Stable Diffusion, etc.).

Proficiency in teaching usage for non-professional users.

A strong grasp of business strategy and go-to marketing relating to startups.

In-depth expertise in Generative AI specific to images.

The ability to create a cohesive visual language across multiple platforms and media.

🔥 Your Role:

You will be responsible for:

Generating an AI generated Brand-Kit encompassing all standard elements of a brand kit, including logo, company documents, social media presence etc.

Generating a cohesive set of 30+ high-quality, AI-driven images that encapsulate our brand's narrative.

Crafting an additional series of 15+ smaller, thematic visuals for use in digital and print media.

Developing a creative AI strategy that aligns with our brand guidelines and marketing objectives.

Producing a dynamic visual identity that can be adapted across various formats and channels.

Provide a teaching session to our team on how to use GenAI to take the above work further into the future.

We're excited to collaborate with a forward-thinking designer and/or GenAI Specialist who is ready to redefine our brand's visual language through the power of generative AI and teach us about this exciting technology. If you are driven by innovation and ready to create something extraordinary, we look forward to your application.

We are on the lookout for talented AI developers to become a part of our dynamic team. Our ideal candidate will have a deep understanding of the entire AI technology stack. Must have proficiency in Generative AI, deep learning - integrating GPT models, designing and building large language models (LLMs) similar to GPT, and creating AI-powered chatbots.

Further, experience with a range of specialized AI technologies is highly desirable. This encompasses familiarity with Llama and Llama2 models, expertise in Stable Diffusion algorithms, a strong background in Core Natural Language Processing (NLP), and a keen understanding of Computer Vision techniques.

Only expert freelancer in AI should apply!!

Please share your resume and portfolio with us to understand your competences better.

We are on the lookout for talented AI developers to become a part of our dynamic team. Our ideal candidate will have a deep understanding of the entire AI technology stack. Must have proficiency in Generative AI, deep learning - integrating GPT models, designing and building large language models (LLMs) similar to GPT, and creating AI-powered chatbots.

Further, experience with a range of specialized AI technologies is highly desirable. This encompasses familiarity with Llama and Llama2 models, expertise in Stable Diffusion algorithms, a strong background in Core Natural Language Processing (NLP), and a keen understanding of Computer Vision techniques.

Only expert freelancer in AI should apply!!

Please share your resume and portfolio with us to understand your competences better.

We are on the lookout for talented AI developers to become a part of our dynamic team. Our ideal candidate will have a deep understanding of the entire AI technology stack. Must have proficiency in Generative AI, deep learning - integrating GPT models, designing and building large language models (LLMs) similar to GPT, and creating AI-powered chatbots.

Further, experience with a range of specialized AI technologies is highly desirable. This encompasses familiarity with Llama and Llama2 models, expertise in Stable Diffusion algorithms, a strong background in Core Natural Language Processing (NLP), and a keen understanding of Computer Vision techniques.

Only expert freelancer in AI should apply!!

Please share your resume and portfolio with us to understand your competences better.

We're seeking a creative software developer who's very experienced with prompt engineering for an exciting gen AI image project*. The ideal candidate has extensive professional experience with the following:

- OpenAI Dall-e 4

- Midjourney AI (prompt engineering and API)

- Stable Diffusion (prompt engineering and API)

Also, experience with python and pytorch is a plus. Please share your relevant experience and recent works related to prompt engineering and generative AI image products.

* This project can become a longterm full-time job.

We are looking for a skilled server-side developer who can deploy stable diffusion APIs on AWS. The ideal candidate should have strong experience in AWS services and a deep understanding of API deployment. Knowledge of Diffusion API is essential for this job. The main responsibilities include configuring and deploying the Diffusion API on AWS, ensuring its stability, and providing documentation for future reference.

Skills required:

Currently working on an app which makes video slideshows using stable diffusion and stock images.

It is also connected via API to collect stock images and get audio.

Its currently using moviepy to stitch everything together.

I have created a working prototype.

I need someone more experienced to finish it off for me.

Would be interested in using a react library to display the slideshow in a editable format, currently not implemented.

Need someone who can work fast and make the next version asap.

I need someone who can take initiative and make the app work well through experimentation without needing too much in the way of guidance and specifications.

Thanks

Hello, I need someone who knows how to work with ConfyUI, Stable Diffusion and AnimateDiff. If you can create a good workflow for me, I will be very grateful. Urgently. Thank you

Hello,

We already have a Stable Diffusion API built by a developer using Runpod with Automatic1111 + Supabase to store generations/API Keys. We're looking to make it scalable and add some more functionality to the project.

We're looking for:

- Add queueing system with a (status), (fetch_url), (position_in_queue) and (eta). When the request is queued it should return these, calling the fetch_url should return the same properties until it's finished generating.

- Add `/animate` endpoint to allow for AnimateDiff creations.

- Add `aDetailer`

- Add Load Balancing so we can handle a large number of users.

- Implement speed improvements such as model caching.

Thanks

We have a finished cartoon which is approximately 20 minutes long. The cartoon consists of a combination of 3D and 2D animation. We want to find a Diffusion Stable specialist who can turn our cartoon into something new in terms of style, we want to get all 20 minutes of our animation in a completely new style.

Our main reference is the Coridor Crew team, you can check their project in YouTube (https://www.youtube.com/watch?v=GVT3WUa-48Y&t=57s).

I want to learn how to fine tune replicate models like

https://replicate.com/jagilley/controlnet-hough/versions/854e8727697a057c525cdb45ab037f64ecca770a1769cc52287c2e56472a247b

The above model is based on stable diffusion with control net.I am imagining it involves training and deploying my private model. I would need the script/process to do this going forward with any models.

Thanks!