Top Stable Diffusion Jobs

Hello,

I’m looking to work with an engineer who knows Stable Diffusion well to write a program that can convert a word doc, into a piece of art.

Wording triggers on the document will equate to variables that would contribute to the fantasy artwork.

We were thinking Stable Diffusion because we know they have an open api, we are also open to alternatives.

We would work on a project roadmap together.

I need a collection of 150+ AI girls using Stable diffusion

.

I am trying to create Tinder for AI..

- each girl should have 4-5 pictures (some w/ cleavage)

pls send 2-3 models as sample. thnx!

Show me any tools you've already made, with proof.

Send a bid, and explain how you'll build an AI image generator that uses the pictures of people in them using stable diffusion's SDXL model.

I've already had this built once, but I need it rebuilt because the other developer stopped responding after I paid him (feel free to ask me questions)

Anyways, I have a loom video of me going over the project,

https://www.loom.com/share/5b4bc56575024ac398ce8ef0cb23bfba?sid=eea43237-f7b0-4375-97e3-2d3e3ef5eb08

I have figma files and assets for everything. Just looking for a trusted solution that has built something similar, and knows how to use stable diffusion, stripe payments, and who has shipped fast web apps and has the proof.

When you send me your work, prove that you are the one who built it. A LOT of people on Upwork claim work they've never built.

When you send a message and proposal, start the msg with AI VIKING so I know you read to the end of this job post. It speeds up my vetting process.

Thanks.

I want to Build a website that is a Saas service, using OpenAI API and Stable diffusion Api via (https://stablediffusionapi.com)

and also Midjurney Api with this Api - https://docs.imagineapi.dev/

this is a good refrance for the project:

https://codecanyon.net/item/artifism-ai-content-image-generator-saas/47251169

The website should have a Ready to use templates for ChatGpt with the option to categorize them by topic - connected to to API (same like in the reference)

and also image generators based on the provided URLs of api procided

we can provide a design or work with your designer if the price is fair.

I also want an option to charge users for credits and store their images for them in their user section

i will explain further more in a conversation

I would like to find a technician to deploy the stable diffusion on my GPU server and define and write API interfaces for other application calls. Please note that it is necessary to consider the authorization/usage limit of interfaces/queuing issues in GPU server graph generation.

Stable Diffusion Based Virtual Try-On Inference Endpoint Deployment

Background and Context

Project Objective: Deploy a virtual try-on model based on stable diffusion for online inference while minimising costs.

Current Infrastructure: Our main cloud provider is AWS but we are also set up with GCP and Azure. We are flexible towards other solutions based on cost and ease-of-use.

Model Details: Model is a modified version of Stable Diffusion 1.5, with a different conditioning network and a fine-tuned u-net (weights will be compatible with original stable-diffusion-inpainting model after appropriate conversion). It uses the Sd-vae-ft-mse-original vae, which can be found on huggingface. We also use an img2img upscaling step with a different fine-tuned stable diffusion model available on huggingface. This should also be set up for online inference. We have code which deals with the diffusion pipeline so the solution could just create inference endpoints for the unet, conditioning network and vae so that this code can connect to those rather than models loaded via torch.load. We are open to other solutions e.g. wrapping the whole pipeline in a single inference endpoint if that makes technical sense.

Technical Requirements

Programming Language: Python 3.10 if applicable

Cloud Platform: AWS preferred, open to other suggestions

Model Framework: PyTorch - can be converted by you to other formats if necessary

File Types: .pt files for the conditioning network and u-net will be provided. We can also provide original .ckpt files if necessary

Tasks to be Performed

Infrastructure Setup: Configure the cloud-based online inference environment.

Model Integration: Integrate VAE, conditioning network, and unet with the inference system.

Optimization: Ensure the model can handle online/on-demand inference without compromising accuracy or speed.

Testing: Conduct comprehensive testing to validate the deployment for real-world usage.

Documentation: Create detailed documentation for the setup and operation.

Deliverables

A functional online inference system deployed on the cloud which operates with minimal latency.

Source code with comments if applicable.

Documentation detailing the architecture, installation steps, and operational guidelines.

Skills and Experience Required

Expertise in MLOps, with hands-on experience in deploying machine learning models in real-time settings.

Strong knowledge of AWS services or other cloud platforms.

Familiarity with Stable Diffusion models and generative networks.

We are looking for an generative AI expert to help us customize generative AI models.

Skills:

Experienced in Replicate

Experienced with Stable Diffusion

Experienced with models such as codeformer

We are trying to create AI Video Material for our business and the ideal candidate will be proficient in developing video materials using artificial intelligence and machine learning techniques. For this position, you should be familiar with Stable Diffusion, Warp Fusion, and Controlnet. You will be responsible for creating engaging and innovative video content by leveraging AI technologies, contributing to the enhancement of our products, services, and user experiences. The sample videos and detailed requirements will be shared with the right candidate.

Please submit a proposal describing how you can help with this project.

We are in search of a skilled Media Artist/Developer with a focus on leveraging AI models for image diffusion processes.

We are creating a project in which we will be leveraging an extensive athlete-specific training dataset. Our strategy currently combines AI techniques, including stable diffusion for enhanced video fidelity, warp fusion for seamless video integration, and ControlNet for tailored content generation. The result will be a personalised video montage reminiscent of creations like Runway 2, dynamically adapting to user preferences, outputting to a continuous video stream. Each video made will combine to form the continuous stream. While these techniques are at the core of our approach, we remain open to integrating other innovative methods to elevate the user experience further.

What we Require

- Someone who can create beautiful AI video material similar to the attachments

- Learn from the dataset provided, so that the user can do an action based on the type of prompt we input.

- AI-powered video transformations, e.g., motion, changing of backgrounds, clothing, speed, era of content

We have provided examples attached as to what we want to achieve. This needs to be real-time where we generate content based on user input.

Please get in touch with examples of doing this before and how you would be achieve this, collaborating with us. It's important that we obtain a similar creative output.

Thanks

We are in search of a skilled Media Artist/Developer with a focus on leveraging AI models for image diffusion processes.

We are creating a project in which we will be leveraging an extensive athlete-specific training dataset. Our strategy currently combines AI techniques, including stable diffusion for enhanced video fidelity, warp fusion for seamless video integration, and ControlNet for tailored content generation. The result will be a personalised video montage reminiscent of creations like Runway 2, dynamically adapting to user preferences, outputting to a continuous video stream. Each video made will combine to form the continuous stream. While these techniques are at the core of our approach, we remain open to integrating other innovative methods to elevate the user experience further.

What we Require

- Someone who can create beautiful AI video material similar to the attachments

- Learn from the dataset provided, so that the user can do an action based on the type of prompt we input.

- AI-powered video transformations, e.g., motion, changing of backgrounds, clothing, speed, era of content

We have provided examples attached as to what we want to achieve. This needs to be real-time where we generate content based on user input.

Please get in touch with examples of doing this before and how you would be achieve this, collaborating with us. It's important that we obtain a similar creative output.

Thanks

We are looking for qualified developers with expertise and knowledge in new image generators AIs like Stable diffusion and midjourney,

Experience in NFT and social media Platform.

Our goal is to create a web-based platform for influencers to easily turn their favorite social media photos into unique digital artworks and convert them into NFTs, build unique Galerie for each user to display and sell them

Responsibilities:

Integration with social media via OAuth to access influencer media libraries.

Implemented a Ai image generation to turn photos into digital works of art.

Ensure that each generated work is unique, even if the entries are similar.

Blockchain integration for the creation and sale of NFTs.

Build an intuitive and userfriendly UI allowing users to build and customise them galery ( details after )

Create an intuitive and responsive user interface, optimized for mobile.

Incorporate guides and tutorials to help users navigate the process.

Qualifications:

Expertise in web development, preferably with experience in NFT platforms.

Familliare with AI image generation tools on API Lvl,

Previous experience with social media integrations on API lvl,

Attention to detail and commitment to creating a quality user experience.

Ability to work with a team and meet deadlines.

Terms :

This position is remote.

Remunerations will be discussed

Join Us as a Creative AI Artist - Ignite the Magic of Stable Diffusion!

Are you a visionary artist ready to infuse our Minnesota-based startup with the boundless allure of Stable Diffusion AI? We're on the hunt for an exceptional Stable Diffusion AI Artist to spearhead the creation of captivating and unparalleled prompt/design concepts. If you possess an innate ability to craft the extraordinary and are eager to explore the enchantment of AI-powered art, we want to hear from you.

About Us:

We're a dynamic startup, passionately crafting the future from our base in Minnesota, USA. Our mission is to harness the awe-inspiring potential of Stable Diffusion to revolutionize the world of AI Art and printing on physical products. With innovation at our core, we're seeking a brilliant mind to join us in shaping a mesmerizing AI art experience.

Your Role:

As the driving force behind our AI art revolution, you'll wield your creative prowess to conjure unique and mesmerizing prompt/design ideas. Your keen eye for pushing boundaries and penchant for thinking beyond convention will be key to our success. We're not just looking for an artist; we're seeking a trailblazer who comprehends the transformative power of AI-infused artistry.

What We're Looking For:

Creative Visionary: Your imagination knows no bounds, and you're driven to explore the uncharted territory of AI art.

Stable Diffusion Expertise: Proficiency in creating awe-inspiring art through Stable Diffusion is a must. Showcase your skills with samples of your outstanding Stable Diffusion creations.

Communication Skills: Articulate why you're the perfect fit for this role, accompanied by your dazzling portfolio.

What Awaits You:

This role offers the chance to shape the trajectory of AI artistry in a startup environment brimming with potential. As you dazzle us with your creations, you'll find ample room for growth. Our initial discussions will delve into the heart of the project, potentially paving the way for a rewarding full-time position.

Join Us:

Embark on this exhilarating journey by sharing your portfolio of Stable Diffusion creations and conveying why you're the visionary we seek. Together, let's unravel the mysteries of AI art and turn them into mesmerizing realities. Interviews are on the horizon, so reach out now!

Note: This is a startup opportunity laden with possibilities, capable of blossoming into a full-time engagement.

Location: Minnesota, USA

Looking for the brightest and best of the best for a Stable Diffusion Expert using Machine Learning for Image Removal project.

We are a tech company looking someone to lead our AI and Machine learning project, most likely using stable diffusion and other open source technologies to help edit images.

This would include training thousands of models to get the results that we want in the images and setting up this system.

Will inform more information about our company and project if candidate is chosen for

We are seeking a skilled Web Application Engineer to join our team. The ideal candidate should have a deep understanding of web application development and be proficient in front-end and back-end technologies.

The candidate should be able to architect the web application according to Functional Specification and UI Design.

The primary responsibilities of the Web Application Engineer include designing and implementing user-friendly interfaces, developing and maintaining server-side components, and ensuring seamless integration with databases and external APIs. The successful candidate should have strong problem-solving skills and be able to collaborate effectively with cross-functional teams.

Relevant skills:

- Proficient in HTML, CSS, JavaScript, and related frameworks (e.g., React, Angular, Vue)

- Experience with server-side languages is a plus (e.g., Node.js, Python, PHP)

- Knowledge of RESTful APIs and web services

- Experience with AI tools like Midjourney, Stable Diffusion is a huge advantage

We are looking to make a stylistic QR code which points to https://keepers.com which matches the aesthetic of the website and twitter

https://twitter.com/keepers

There are instructions on how to do something like this here https://antfu.me/posts/ai-qrcode

We would like to choose from a variety of options, feel free to send us watermarked examples.

We are in search of an expert in Stable Diffusion API to assist in editing and enhancing our current Stable Diffusion API code. The primary objective is to generate the most realistic photos of people using the API.

**Responsibilities:**

1. Modify and optimize our StableDiffusion API code to produce highly realistic images of people.

2. Provide multiple variations of our script on a weekly basis, adjusting settings to achieve different styles and effects.

3. Draw inspiration from various prompts and styles, especially from https://prompthero.com/stable-diffusion-photorealistic-prompts to create unique and captivating images.

**Compensation:**

- $5 for each approved style.

- Given the ongoing nature of the project, we will be sending you ideas daily, leading to multiple earning opportunities.

**Application Process:**

1. Watch the video instructions: https://www.berrycast.com/conversations/ac6cc1f4-89c5-5096-a79d-55c9deb232b2

2. Answer the questions at the end of the video to proceed with the application.

**Requirements:**

- Proven experience with StableDiffusion API.

- Ability to work with different settings and produce varied results.

- Strong communication skills and responsiveness to daily ideas and feedback.

---

Interested candidates are encouraged to apply with relevant samples of their work with StableDiffusion API. We look forward to collaborating with you!

Hi, I'm an artist that has been working with Stable Diffusion and GANs that is looking for technical help with customising and fine tuning the internal weights of a neural net diffusion model.

Brief:

I create abstract images and I'm looking at ways in which you can alter a model internally in order to produce obscure and abstract results - images that appear in-between noise and output.

You can see an example of what I am aiming to do in the attached image as well as in the link here which explains the idea:

https://writings.stephenwolfram.com/2023/07/generative-ai-space-and-the-mental-imagery-of-alien-minds/

I'm not sure how Stephen Wolfram achieves the results in the link and I'd like to find ways to explore ways of (quoted from the link): " taking the neural net that implements this generative AI, and modifying its insides—say by resetting weights that appear in its neural net."

There are other links in the article that point to other articles that expand on the concepts and the model that's used:

https://resources.wolframcloud.com/NeuralNetRepository/resources/Stable-Diffusion-V1/

Outcomes:

I see this working as a phone call/screen share call or a series of screen recordings as tutorials where you would be able to guide me on how this can be done as well as any follow up questions I may have.

There may be a chance to continue working together on other projects in future.

Hi, I'm an artist that has been working with Stable Diffusion and GANs that is looking for technical help with customising and fine tuning the internal weights of a neural net diffusion model.

Brief:

I create abstract images and I'm looking at ways in which you can alter a model internally in order to produce obscure and abstract results - images that appear in-between noise and output.

You can see an example of what I am aiming to do in the attached image as well as in the link here which explains the idea:

https://writings.stephenwolfram.com/2023/07/generative-ai-space-and-the-mental-imagery-of-alien-minds/

I'm not sure how Stephen Wolfram achieves the results in the link and I'd like to find ways to explore ways of (quoted from the link): " taking the neural net that implements this generative AI, and modifying its insides—say by resetting weights that appear in its neural net."

There are other links in the article that point to other articles that expand on the concepts and the model that's used:

https://resources.wolframcloud.com/NeuralNetRepository/resources/Stable-Diffusion-V1/

Outcomes:

I see this working as a phone call/screen share call or a series of screen recordings as tutorials where you would be able to guide me on how this can be done as well as any follow up questions I may have.

There may be a chance to continue working together on other projects in future.

I'm using the Stable Diffusion web UI and I'm running into a problem.

The problem happens whenever I try to use Variation Strength. I'm trying to use Variation Strength to achieve similar but unique images. I ask the system for, say 100 images with a Variation Strength of, for example, 0.7.

Even though I ask for 100 images, it always gives me just 1 image. It'll give me a grid, and the images within the grid are indeed unique, but then all of the sub-images it gives me are exactly the same picture. In fact, when I look in the directory where the images are being stored, there's only 1 single image instead of the 100 I asked for.

I do wonder if I'm making some sort of amateur mistake or whether it's a bug.

Anyone who can help solve this problem, I'm happy to pay you for your time.

I'm using the Stable Diffusion web UI and I'm running into a problem.

The problem happens whenever I try to use Variation Strength. I'm trying to use Variation Strength to achieve similar but unique images. I ask the system for, say 100 images with a Variation Strength of, for example, 0.7.

Even though I ask for 100 images, it always gives me just 1 image. It'll give me a grid, and the images within the grid are indeed unique, but then all of the sub-images it gives me are exactly the same picture. In fact, when I look in the directory where the images are being stored, there's only 1 single image instead of the 100 I asked for.

I do wonder if I'm making some sort of amateur mistake or whether it's a bug.

Anyone who can help solve this problem, I'm happy to pay you for your time.

I need a collection of 500+ AI girls that is generated w/ Midjourney or Stable diffusion. Either generate the images yourself or you can collect them online.

I want to evaluate requests being sent to stable diffusion, and give them labels. If the request is to produce prohibited imagery (such as nudity of a real-life person) the request should be rejected.

In order to implement this, I think the best way to do it is to use a transformer model like DistilBERT (which is fast and small) to examine requests and assign labels to them, such as 'NSFW'.

Every request to our stable diffusion endpoint will first go through this ethical-AI filter, which will determine if we reject the request or not.

I believe whoever builds this will need some knowledge of transformer models like DistilBERT and Python (neither of which I'm familiar with). I'm open to alternative proposed solutions for this problem!

Thanks for looking; looking forward to hearing from you.

I want to evaluate requests being sent to stable diffusion, and give them labels. If the request is to produce prohibited imagery (such as nudity of a real-life person) the request should be rejected.

In order to implement this, I think the best way to do it is to use a transformer model like DistilBERT (which is fast and small) to examine requests and assign labels to them, such as 'NSFW'.

Every request to our stable diffusion endpoint will first go through this ethical-AI filter, which will determine if we reject the request or not.

I believe whoever builds this will need some knowledge of transformer models like DistilBERT and Python (neither of which I'm familiar with). I'm open to alternative proposed solutions for this problem!

Thanks for looking; looking forward to hearing from you.

We are seeking a highly skilled and motivated Generative AI Stable Diffusion-focused ML Engineer. As a Generative AI Stable Diffusion-focused ML Engineer, you will play a key role in developing and implementing cutting-edge generative AI models, with a specific focus on Stable Diffusion. You will work closely with our research and development teams to design and optimize generative AI algorithms and models for various applications, such as text-to-image and text-to-video.