AI Image Generation Project Leads

Hey there!

We're on the lookout for a creative Facebook ads whiz to help us whip up some unique UGC-style static ads for our upcoming campaigns. If you know your way around social media advertising and have a knack for designing ads that grab attention and get results, we want to chat!

You’ll be teaming up with our marketing crew to get a feel for our brand vibe and who we’re trying to reach. It’s super important that you’re comfortable using graphic design tools and Facebook Ads Manager.

Note: This initial rate is for the test assignment only. Upon successful completion, we'll discuss compensation for ongoing work.

Skills: Graphic Design, AI Image Generation, Advertising Design, AI-Generated Art, Facebook, Social Media Marketing, Facebook Advertising

Job Title: Remote Graphic Designer (with AI Image Generation Experience)
Reports to: Associate Director of Creative
Location: Remote (Working close to Dubai standard work hours)
Employment Type: Freelance/Contract with potential for full-time
Start Date: ASAP

About Capital D STUDIO
Capital D STUDIO is a next-gen creative house shaping bold content, elevated branding, and smart strategy for brands that want to lead the conversation. With roots in fashion, lifestyle, beauty, entertainment, and culture, we move fast, create fearlessly, and deliver with impact.

We don’t believe in cookie-cutter content. We believe in crafting visuals that stop the scroll, stir emotion, and start trends.

The Role
We’re on the hunt for a Remote Graphic Designer with a strong visual eye, fast execution skills, and fluency in AI image generation tools. This role combines aesthetic instinct, cultural awareness, and the technical know-how to create content that feels editorial, unexpected, and always on-brand. You’ll be working closely with our in-house team to bring campaigns, social content, brand decks, and concept visuals to life.

This is a perfect fit for someone who’s tapped into visual trends, thrives on variety, and isn’t afraid to experiment with new tools like Midjourney, DALL·E, or Firefly.

Key Responsibilities
Design high-impact visual content for social media, decks, campaigns, and digital channels
Use AI tools (e.g. Midjourney, DALL·E, Runway, Firefly) to generate concept art, moodboards, and production-ready visuals
Adapt visual identities into fresh, scroll-stopping formats
Collaborate with the Creative Director and wider team to interpret briefs into strong creative
Stay current on design and AI trends, using them to push our creative output forward
Maintain quality control across multiple projects and formats
Work quickly and efficiently to meet fast-moving deadlines
Requirements
3+ years of graphic design experience with a strong portfolio (content, branding, campaigns)
Proficiency in Adobe Creative Suite (Photoshop, Illustrator, InDesign) and/or Figma
Proven experience using AI image generation tools creatively and effectively
Strong aesthetic sensibility – layout, type, color, storytelling
Motion graphics skills (After Effects, Premiere, CapCut, or Canva video) are a bonus
Highly organized, independent, and collaborative
Comfortable working across multiple brands, styles, and tones
Fluent in English (Arabic is a plus)
Nice to Have
Background in fashion, beauty, or lifestyle brands
UI/UX or web design experience
Experience creating content for TikTok and IG Reels
Obsessed with moodboards, editorial design, and emerging visual culture
What You’ll Love
Full creative expression, no pixel-pushing
The chance to shape some of the region’s coolest campaigns
Flexible hours, remote setup, and a tight-knit creative team
Constant exposure to new tools, formats, and ideas
A creative playground where good taste meets great strategy

Skills: Web Design, Advertising Design, Adobe Photoshop, Graphic Design, Adobe Illustrator, Adobe InDesign, Logo Design, Brand Identity & Guidelines, Social Media Imagery, Infographic

Hello Estaban,

I am looking for someone that can remove the background from the picture and replace it.
The new background should look more or less like a sandy, bushy surrounding with stones.
The picture is from a simulator.
I need to get the result in high resolution to print it in big sizes on shows.

Are you able to do so on 1 day's notice? And what would be the costs?

Regards,

Caroline

Skills: Adobe Photoshop, Adobe Lightroom, Retouching & Enhancement, Background Removal, Image Editing, Manipulation & Compositing, Fashion Photography, Photography, Photo Restoration, Photo Manipulation, Photo Retouching, Image Processing, Photo Color Correction, Photo Editing, AI Image Generation

Hey there! We're on the lookout for a creative person to help us with social media content. If you love coming up with fun ideas and have a knack for making cool graphics and writing catchy captions, we want you!

We're especially interested in someone who's excited about AI and how it can be used in social media marketing. Your job will be all about brainstorming cool content, designing eye-catching visuals, and crafting messages that really connect with our audience. If you're into innovative tech and have a creative spark, reach out!

HIRING PROCESS

- Applications generated using Chat GPT will not be considered (does not apply for image generation examples)
- Shortlisted candidates will be invited to complete a short task and conduct two short interviews

Skills: AI Image Editing, Social Media Imagery, AI Image Generation, Midjourney AI, Content Writing, Social Media Marketing, Social Media Content, Instagram, Social Media Content Creation, Facebook

I'm looking for a skilled professional who can create realistic AI-generated images of our trucks/vans for our restoration business website.

Key Requirements:
- Create images of our trucks/vans in front of our current building.
- Render the trucks/vans in a realistic style.

Ideal Skills:
- Expertise in AI image generation.
- Experience with creating realistic vehicle images.
- Ability to understand and replicate specific locations.

These images will be crucial for our website, helping potential customers visualize our fleet (4 ford transit vans and 2 Box trucks) and the scale of our operations. Please provide examples of similar work you've done in the past.

Pictures show our headquarters building. and examples of fleet pictures.

Skills: Graphic Design, Logo Design, Photoshop, Illustrator, Illustration

AI Specialist for Custom Line-Art Image Generator (Mountains, Landscapes, Cities)

We're looking for an AI image specialist to help us build a stylized image generation tool for landscapes and skylines. The goal is to transform real-world images (e.g. mountains, surf waves, city skylines) into minimalist line-art illustrations in a consistent visual style. These will be used for a creative digital and physical product line.

What We Need
- Development or fine-tuning of a model that takes reference images and outputs clean, consistent line-art illustrations
- The style will be provided (example images/sketches), and must be maintained consistently across outputs
- The system should also allow for easy changes in style (e.g. different line weights, color accents, layout)
- Ability to organize a dataset (images + metadata) from open sources like Wikipedia or other image libraries
- A simple backend tool that lets users request a location (e.g. “Mount Fuji”) and receive a styled image
- Output images should be in fixed resolution, consistent look, and print-ready format

Optional but Valuable
- Experience with SVG generation or sketch-based image processing
- Ideas on how to balance preprocessing vs real-time generation
- Experience with stylized AI model training (e.g. LoRA, ControlNet, Diffusion)

How to Apply
Please share:
- Relevant experience with AI-based image generation or sketch-style rendering
- Links to past projects or models you’ve worked on
- Your thoughts on how you might approach this (briefly)

We have a strong visual direction and are open to expert suggestions. This project may lead to longer-term collaboration as we expand the scope to more locations and visual themes.

Skills: AI Image Generation, Graphic Design, Illustration, Python, LoRa

We’re working inside FLUX AI and have already followed the LoRA training process using a carefully curated photo set and step-by-step guide. However, the generated images aren’t coming out close enough to the actual person’s likeness (even though we’ve done everything correctly from the setup side).

We’re looking for someone with real experience training LoRA models—especially for facial likeness and branding use—to help us get this working flawlessly.

We Already Have:
An active FLUX AI account

API credentials

15+ high-quality, well-lit selfies of our subject

The trigger word already set up and ready to test

What We Need:
Help reviewing or re-training our LoRA model to get accurate, consistent likeness results in FLUX

Guidance on tuning prompts and fixing issues like off-looking facial features or mismatched styling

Delivery of a clean working model or updated settings we can use to reliably generate images

Tools/Platform:
FLUX + LoRA

Stable Diffusion concepts preferred

Prompting and model parameter tuning expertise a must

These images will be used for marketing funnels, opt-in pages, social media, and brand design—so accuracy and personality matter a lot. This is NOT a general concept image—we need it to actually look like the real person in a wide variety of generated scenes.

To Apply please send:

Examples of likenesses you’ve trained using LoRA or similar tools

What your process looks like (audit vs. retrain)

Estimated time to complete

Any additional support you offer (prompt sets, clean-up, format conversion, etc.)

Skills: AI Image Editing, AI Image Generation, Generative AI Prompt Engineering, Stable Diffusion, Midjourney AI, DreamBooth

We are seeking a talented and creative graphic designer to produce a professional, eye-catching Facebook banner for our business page. The banner should reflect our brand, engage our audience, and align with our social media goals.

Scope of Work:- Design a high-quality Facebook banner (820x312 pixels for desktop, 640x360 for mobile optimization).- Ensure the design is visually appealing and consistent with our brand identity.- Incorporate our logo, brand colors, and relevant imagery or taglines.- Provide the final design in .JPG/.PNG format and an editable source file (e.g., PSD or AI).- Offer 1-2 rounds of revisions based on feedback.

Requirements:- Proven experience with social media design, especially Facebook banners (please share your portfolio).- Proficiency in Adobe Photoshop, Illustrator, or other graphic design tools.- Ability to communicate clearly and deliver on time.- A creative eye and attention to detail.

Bonus Skills (Nice to Have):- Experience with Facebook ad creatives.- Understanding of current social media design trends.

Skills: AI Image Generation, Brochure Design, Graphic Design, Social Media Imagery, Adobe Photoshop, Adobe Illustrator, Banner Ad Design, Adobe InDesign, Facebook

We are looking for a skilled and creative freelancer to help us generate high-quality images of jewelry items for our website.

Each time we will send you either:

A photo of a jewelry piece, or

A link to a product page (from another website)

Based on that, we expect you to deliver a full set of visuals for our version of the jewelry.

Deliverables per jewelry item:
3 product images – from different angles, showing the jewelry in:

White gold

Yellow gold

Rose gold

2 model images – showing the jewelry worn by a realistic female model (can be AI-generated)

1 lifestyle image – showcasing the jewelry in an aspirational or elegant setting (can also be AI-generated)

Requirements:
Experience editing jewelry images (changing metal colors accurately)

Ability to use AI tools (e.g. Midjourney, Leonardo AI, DALL·E) or Photoshop

Realistic rendering and strong attention to proportion and detail

Clean, high-resolution output

Familiarity with product-style backgrounds (white), lifestyle mood, and model realism

Project Type:
Ongoing project: 3–10 jewelry items per week

Budget:
Please quote your price per jewelry item (for all 6 images).

To Apply:
Please include:

Examples of jewelry work you’ve done

Which tools or software you use

Your estimated turnaround time per item

Skills: Adobe Photoshop, Product Photography, Color Correction, Jewelry Design, Photo Retouching, 3D Rendering, AI Image Generation

Hi, I am in charge of IT and automation for an online English school.
I'm being asked to create a bot so they can integrate it into the school, which is built on WordPress (so they can put the bot on a page in each unit).
So, if the student is in Unit 1, they should be able to talk to the bot using vocabulary and verb tenses from Unit 1.
The bot should be able to be used as embedded code on the WordPress website itself.

The bot requirements are:
- The bot should be able to detect when the student has finished the sentence and then respond. This way, the user doesn't have to press the audio record button every time they speak.
- There should be a certain amount of memory so that the conversation makes sense.
- At the end of the conversation, the conversation can be summarized into strong and weak points for the student to review (we could send this summary by email, for example, or save it in a database for future conversations).

Let me know if you think it's feasible.

Best regards and thanks.

Skills: Python, Machine Learning, Midjourney AI, AI Image Generation, Generative AI, Artificial Intelligence, Natural Language Processing, ChatGPT, LLM Prompt Engineering, Computer Vision, Large Language Model, Stable Diffusion, Deep Learning, Retrieval Augmented Generation, Machine Learning Algorithm

Hiring: Graphic Designer for Paid Ad Creatives (Facebook + Pinterest Focused)

We’re Hiring: Graphic Designer for Paid Ad Creatives
We’re a fast-scaling e-commerce brand looking for a conversion-focused graphic designer to join our team and take ownership of static ad creatives for Facebook and Pinterest campaigns.
This role is 100% dedicated to performance-based design — no logo work, no packaging, no fluff. You’ll be transforming raw UGC, product photos, and copy hooks into high-performing image ads that stop scrolls and drive clicks.

What You’ll Be Doing:
Designing static image ads for Facebook and Pinterest


Working closely with our in-house Creative Strategist who will guide briefs, angles, and data


Analyzing top-performing ads in our niche for reference and inspiration


Creating new concepts weekly based on trends, hooks, and our content library


Iterating based on performance data (CTR, ROAS, scroll rate)



You’re a Fit If You:
Have experience creating ad creatives that convert, not just look good


Understand direct-response design psychology


Are fast, reliable, and can handle feedback without ego


Are comfortable analyzing a niche and coming up with visual concepts


Are fluent in design tools like Photoshop, Illustrator, Canva, or Figma


Have experience designing for Facebook Ads and/or Pinterest Ads (bonus if both)



Your Responsibilities:
Receive briefs and raw content (UGC, product shots, past winners)


Research competing ads in the niche


Design multiple static image ad variations per week


Deliver fully exportable assets (PSD, Canva, or similar format) + ad-ready formats


Hit deadlines consistently and communicate in a fast-paced team



To Apply: Include the following in your application:
A short intro about your experience in ad creative design


A portfolio of relevant Facebook/Pinterest image ads (don’t send logos or posters — we want to see ad creatives)


Your availability + turnaround time


A few tools or techniques you use to research what’s performing in a niche


Why performance-driven creative work excites you



Important:
Your application will not be reviewed unless you start with this keyword:
👉 At the top of your resume, please write (iPhone 2) — this lets us know you’ve read the full post and pay attention to detail.

We’re looking to hire immediately. If you love the psychology of design, are obsessed with ad performance, and want a long-term role with a fast-growing brand — we want to hear from you.

Skills: Image Prompt, Icon Design, Advertising Design, AI Image Generation, Fashion & Beauty, Banner Ad Design, Adobe Photoshop, Graphic Design, Facebook, Social Media Imagery

We need someone who can create fashion photos using AI then refine them in Photoshop. The models must look perfectly real and the clothing details must match the photos we give you.

You must be able to...
•⁠ ⁠⁠work fast
•⁠ ⁠⁠have access to the best AI image generators and editing software
•⁠ ⁠⁠have latest version of Photoshop
•⁠ ⁠⁠communicative
•⁠ ⁠⁠fast learner
•⁠ ⁠⁠speak good English

If the first few jobs go well, we'd like to hire you long-term, full-time. We have a high volume of work available.

Skills: AI-Generated Art, AI-Generated Image, AI Image Generation, Midjourney AI, Leonardo Ai, Midjourney Prompt, Enhanced Detailing, AI Chatbot, AI Image Editing, AI Image Generator, Adobe Illustrator, Graphic Design, Product Photography, Adobe Photoshop, Photo Editing, Image Editing, ChatGPT, ChatGPT Prompt, Fashion & Apparel, Fashion Photography

Need a weekly YouTube video editor for a 30min main video + 5 YouTube Shorts.

Skills: Video Editing, Adobe Premiere Pro, Adobe After Effects, CapCut, AI Video Generation, AI Image Generation, Adobe Animate, Scriptwriting, Adobe Creative Cloud, Graphic Design

Image Generation Brief: Detailed Visualization of the Business Evolution Framework (BEF) - Brand Consistent with Creative Freedom

Overall Concept: Generate a visually engaging, intricate, and informative diagram representing the Business Evolution Framework (BEF) as a multi-layered target. The design must adhere to the provided brand color palette and typography but allows for creative interpretation in the visual arrangement and styling of elements to effectively communicate the framework's structure and the journey towards FULFILMENT. The surrounding DAPER Cycle should be seamlessly integrated to emphasize continuous improvement.

Brand Guidelines:

Colour Palette:

Primary: #08054d (Deep Blue)

Secondary/Supporting (Pink): #fc0886 (Bright Pink)

Accent: #e4b505 (Yellow/Gold)

Background: #f7f2f2 (Light Gray/Off-White) or #ffffff (White)

Additional Accent (Teal): #00e5e9 (Bright Teal)

(Refer to previous detailed section for suggested usage)

Typography:

Headlines & Main Info: Aura Regular (Substitute: Impact)

Paragraph/Full Body Copy/Descriptors: Poppins (Substitute: ITC Avant Garde Gothic)

Italic Accent Text: Begum SemiBold (Italicized) (Substitute: Playfair Display Bold Italicized)

Hierarchical Structure (For Reference):

Level Category/Element Sub-Elements (If Applicable)
Level 1 (Core) FULFILMENT
Level 2 (Engine) Triad of Success CLARITY, SIMPLICITY, GROWTH
Level 3 (Outcomes & Enablers) Outer Core RESULTS, CAPACITY, FREEDOM
Level 4 (Infrastructure & Focus) Support Systems CLARITY (Mindset, Alignment, Strategy), GROWTH (Brand, Sales, Marketing), SIMPLICITY (Money, Systems, People)
Level 5 (Foundation) The Foundation EVOLUTION, RESILIENCE, EMPOWERMENT, SYNERGY, LEGACY
Level 6 (Process) The DAPER Cycle DEFINE, ASSESS, PLAN, EXECUTE, REFINE

Visual Structure (Creative Freedom within Brand):

Target Analogy: The layered target structure should be maintained to represent the progression towards FULFILMENT.

Ring and Segment Arrangement: The exact proportions, spacing, and visual division of the rings and segments are open to creative interpretation. Consider innovative ways to present the information clearly and engagingly.

Iconography: The use and style of icons for the DAPER cycle and within the "Support Systems" and "Foundation" rings can be creatively explored, ensuring they are consistent with the overall visual style and brand.

Visual Connections: Explore different visual techniques (lines, arrows, subtle shapes, layering) to emphasize the relationships and flow between the different levels and elements of the BEF.

Text Placement and Styling: While adhering to the font guidelines, experiment with text placement, emphasis (using color and italicization), and visual hierarchy to enhance readability and impact.

DAPER Cycle Integration: Be creative in how the DAPER cycle is positioned and visually connected to the main target diagram. Consider options beyond simple surrounding circles.

Key Considerations for Creative Interpretation:

Clarity of Information: Ensure the visual design, while creative, does not obscure the structure and key elements of the BEF. The information should be easily understandable.

Brand Consistency: All color and typography choices must strictly adhere to the provided brand guidelines.

Emphasis on Progression: The visual should subtly guide the viewer towards the central goal of FULFILMENT.

Dynamic and Engaging: Aim for a visually appealing and dynamic design that captures the essence of business evolution.

Key Message: The diagram should clearly and creatively illustrate the layered structure of the BEF, the specific elements within each layer, their relationships, and the ongoing role of the DAPER Cycle, all while adhering to the brand's visual identity.

Skills: AI Image Generation, Adobe Illustrator, AI-Generated Art, Graphic Design

AI Image Generation Expert (LoRA + Photoshop) – Ultra-Realistic Model Portraits with Consistent Identity

We’re looking for an experienced and detail-obsessed AI image generation specialist to help us create a hyperrealistic digital model using Stable Diffusion, LoRA training, and professional retouching in Photoshop. Our goal: to build a consistently recognizable virtual model that looks indistinguishable from real humans – across multiple poses, environments, and contexts.

The model will be used across Instagram-style content, lifestyle shoots, and eventually commercial campaigns. A successful candidate will play a key role in crafting this digital personality from the ground up – beginning with one female model and expanding into a larger character network.

As reference, the quality and vibe should be comparable to virtual influencers like Aitana Lopez.


Your Responsibilities:
• Train a LoRA model based on a curated dataset to match facial features, body type, skin tone, hair, and style
• Ensure the model remains visually identical and consistent across:
• different poses (standing, sitting, mirror selfies, etc.)
• different backgrounds and lighting environments (indoor, outdoor, casual, cinematic)
• Use ControlNet (OpenPose) to replicate reference photo poses accurately
• Optimize sampling settings, CFG, upscalers, denoising strength, and render quality (AUTOMATIC1111 / ComfyUI)
• Use Photoshop (or equivalent) to professionally clean up hands, facial asymmetries, skin texture, shadows, lighting and background inconsistencies
• Create commercial-ready outputs that can be used in ads, reels, and digital campaigns
• Work with us iteratively to refine prompts, styles, and technical setup

What You Bring:
• Expert-level experience with Stable Diffusion, LoRA training, ControlNet, and advanced prompting
• Strong sense for beauty photography, visual storytelling, lighting and realism
• Deep experience in retouching AI images in Photoshop (hands, skin, shadows, background cleanup)
• Ability to work with a fixed character and maintain look, vibe and identity across dozens of images
• Portfolio of hyperrealistic AI portraits that resemble high-end fashion or influencer content
• Bonus: background in Instagram aesthetics, fashion visuals, or advertising visuals


What We Offer:
• A long-term partnership with a growing digital brand
• Creative freedom, clear vision, and an aesthetic-driven workflow
• Fair and competitive compensation
• The chance to define the visual DNA of our virtual model brand
• Opportunity to work on a long-term multi-model expansion


To Apply:
Please include:
• Examples of your most realistic AI-generated model images
• A brief overview of your LoRA training and post-processing pipeline
• Availability and estimated pricing per batch/project


We are aiming for world-class photorealism, brand-ready visuals, and a consistent digital identity that can scale to a full influencer portfolio.
If you know how to make AI look alive — let’s build something big together.

Skills: Social Media Imagery, Stable Diffusion, Image Processing, Adobe Illustrator, Graphic Design, Fashion & Beauty

This is a very straight forward task - I have title of ebook, you have to generate AI based images that can match the title of those ebook.

I have pasted all the titles of the book in this figma file.
https://www.figma.com/design/bOgydIfMEtUpAEOzPSH46q/Upwork---Job-Post?node-id=0-1&t=mO8lMt732cLx2YXM-1

Guidelines for images:
1. The image should be transparent PNG
2. The image should be of high quality, 4K
3. The image should be modern and classy with some type of style.
4. The image should have main character surrounded by widgets and elements that should represent the title theme of the book.
5. The overall composition of the image should look coherent.
6. The overall image should represent the idea of the book title.

Skills: AI Image Generation, AI Image Editing

Project Overview

Seeking a versatile digital marketing specialist who excels in branding, design, and content creation, with experience in AI-powered image generation. The ideal candidate is a creative problem-solver who can enhance our website's effectiveness through compelling storytelling, strategic design, and conversion optimization.

Core Competencies Required

- Visual & Design Skills
- Strong eye for visual design and layout
- Proficiency with AI image generation tools (e.g., Midjourney, DALL-E, Stable Diffusion)
- Ability to create and direct visual brand assets
- Experience in creating professional, on-brand imagery
- Understanding of UI/UX best practices

Brand & Marketing
- Brand development and strategy
- Compelling narrative creation
- Content strategy development
- Lead generation expertise
- Conversion optimization

Content Creation
- Strong B2B copywriting skills
- Ability to simplify complex topics
- Creating action-driving marketing copy
- Understanding of SEO best practices

Technical Skills
- Working knowledge of WordPress
- Familiarity with Elementor page builder
- Basic understanding of The7 theme
- Experience with lead generation tools

Key Qualities
- Creative Vision: Ability to conceptualize and execute compelling visual content
- Strategic Mindset: Can see the big picture while managing details
- Self-Directed: Takes initiative and drives projects forward independently
- Versatile Skillset: Comfortable wearing multiple hats
- Strong Communicator: Clear and proactive in updates and recommendations

Ideal Candidate Profile
You should be a marketing generalist who:
- Has proven experience in brand development and visual storytelling
- Is proficient with AI image generation tools for creating professional visuals
- Excels in writing compelling marketing copy
- Can balance aesthetics with conversion goals
- Takes ownership of projects from concept to completion
- Provides strategic direction with confidence

Project Scope
- Immediate start needed
- Initial 2-3 week engagement
- Potential for ongoing relationship
- Regular strategy and progress updates

Required Portfolio Elements
- Examples of AI-generated images for business use
- Brand development work
- Content writing samples
- Website optimization projects
- Before/after marketing improvements

Skills: Art & Design, Branding, Website Copywriting, Digital Marketing Strategy, WordPress

Project goal
Create a comprehensive 20-30 minute YouTube video that translates and recreates French stories into Spanish using AI images and voice narration.

Video Style and Tone
The video should be educational and engaging, tailored for language learning with clear and precise narration.

Script and Storyboard
- Select engaging stories from an existing YouTube channel focused on French language learning.
- Translate the verbal and textual story content from French to Spanish.
- Recreate the stories using AI-generated still images to visually represent the narrative (Midjourney / Leonardo / Chat GPT ...)
- Narrate the stories in Spanish using advanced voice tools for clarity and appeal. (Eleven Labs...)
- Integrate the translated text as subtitles, synchronized with the voiceover and images.
- Upload to Youtube channel

Timeline
Ongoing project - if the first video is good, we would expect at least 2 videos each week

Skills: Video Editing, AI-Generated Video, AI Audio Generation, AI Image Generation

I’m looking for a skilled AI freelancer who can take a select few photos and generate hundreds of high-quality, realistic images based on them. The goal is to create images that depict natural, real-life scenarios, ensuring consistency in facial features, lighting, and overall realism.

The AI-generated photos should capture various real-life settings, such as:
• Outdoor scenes: Walking on the beach, driving a car at sunset, sitting in a park.
• Indoor settings: Relaxing on a couch, cooking in the kitchen, reading in bed.
• Social environments: At a casino, at a restaurant, hanging out with friends.

What I Need from You:
• Utilize AI tools (e.g., Stable Diffusion, MidJourney, DALL·E, or similar) to generate hundreds of realistic images based on provided reference photos.
• Ensure facial features and overall appearance remain consistent across all images.
• Create diverse, high-resolution images in various settings with different lighting, poses, and angles.
• Deliver a large batch of photos that look authentic, as if they were taken in real-life situations.

Ideal Candidate:
• Experienced in AI-generated imagery and photo manipulation.
• Skilled in using advanced AI tools to create lifelike, high-quality images.
• Able to maintain consistency in subject appearance across all generated images.
• Strong attention to detail and ability to create images that don’t look artificial or overly AI-generated.

Deliverables:
• At least 100+ AI-generated images in different real-life scenarios.
• High-resolution, photo-realistic images (no cartoonish or unrealistic styles).
• A variety of settings, lighting conditions, and natural poses.

If you have experience with AI image generation and can deliver high-quality, realistic images in bulk, please apply with examples of your work or a brief overview of your approach.

Skills: AI Image Editing, AI Image Generation, Graphic Design, Image Editing, Adobe Photoshop, Photo Editing

We need someone who can create fashion photos using AI then refine them in Photoshop. The models must look perfectly real and the clothing details must match the photos we give you.

You must be able to...
•⁠ ⁠⁠work fast
•⁠ ⁠⁠have access to the best AI image generators and editing software
•⁠ ⁠⁠have latest version of Photoshop
•⁠ ⁠⁠communicative
•⁠ ⁠⁠fast learner
•⁠ ⁠⁠speak good English

If the first few jobs go well, we'd like to hire you long-term, full-time. We have a high volume of work available.

Skills: AI-Generated Art, AI-Generated Image, AI Image Generation, Midjourney AI, Leonardo Ai, Midjourney Prompt, Enhanced Detailing, AI Chatbot, AI Image Editing, AI Image Generator, Adobe Illustrator, Graphic Design, Product Photography, Adobe Photoshop, Photo Editing, Image Editing, ChatGPT, ChatGPT Prompt, Fashion & Apparel, Fashion Photography

We’re looking for a visionary AI animator and motion designer to bring deeply imaginative metaphysical concepts to life across our social platforms.

Think:
✨ Quantum timelines collapsing
🌀 Past-life visions unfolding
🌠 Galactic contact sequences
🌿 Soul awakenings in ancient forests
👁️ The Higher Self speaking through light and form

If this makes your creative soul buzz… we want to meet you.

💡 About Us

We’re QHHT (Quantum Healing Hypnosis Technique), founded on the groundbreaking work of Dolores Cannon. Our audience is a fast-growing global collective of spiritually curious seekers, starseeds, and conscious creators. We produce course content, retreats, and viral metaphysical videos that inspire soul remembrance and timeline activation.

🔮 What We’re Looking For:
AI-powered animator / video producer with experience in generative tools (Runway, Kaiber, Pika, AnimateDiff, Midjourney, Gen-2, etc.)

Dreamlike, cinematic, and emotionally resonant animation style (like “Golden Boy” or Studio Ghibli meets the Akashic Records)

Ability to work with spiritual themes (sacred geometry, light codes, consciousness, time travel, etc.)

Fluency in motion design, creative storytelling, and sound/sfx layering

Bonus: Comfort with voiceovers, character animation, or cosmic-inspired typography

🚀 What You'll Create:
30–60 second reels and shorts for Instagram, TikTok, YouTube

Visual journeys based on real QHHT sessions, FB and IG live streams, sections from Dolores Cannon books...ect (we’ll mostly provide voiceover)

Animations for online course trailers, retreat promos, and sacred announcements

🎯 Our Ideal Partner:
Wildly imaginative

Meticulous with visual quality and emotion

Collaborative, professional, and excited about consciousness evolution

Let’s create the most awe-inspiring, share-worthy metaphysical animations on the internet.

💌 To apply, please send:

A few samples of your animation work (AI or not – we want to feel your vision)

A quick note on what inspires you creatively

Your favorite tool(s) or technique for AI + motion

We’re ready to collaborate with someone extraordinary.
Let’s make magic together. 🌟

Skills: AI Image Generation, AI-Generated Image, 3D Image, Social Media Imagery, Animation, 2D Animation

We are looking for a highly skilled and creative graphic designer who works with AI image generation tools (such as Midjourney, DALL·E, Firefly, etc.) to help us produce static visuals for Facebook Ads.

You must master the art of prompt crafting and be highly demanding with visual quality. We’re not looking for average — we want stunning, scroll-stopping creatives that convert.

Requirements:

Proven experience with AI tools for image generation

Excellent understanding of visual advertising on Facebook

Ability to create high-quality static creatives with commercial appeal

Expert at writing prompts that generate targeted, aesthetic results

Attention to detail and high visual standards

Strong communication skills

Bonus: Experience with e-commerce and direct response advertising

What you’ll do:

Design AI-generated static creatives for Facebook campaigns

Refine prompts to match brand/product angles

Iterate quickly based on feedback

Deliver clean, ready-to-use files for ad placement

Skills: Graphic Design

🎨 Buscamos Diseñador Gráfico para Agencia de Marketing Digital (Nicho: Restaurantes)


¿Te apasiona el diseño gráfico y tienes experiencia creando anuncios irresistibles para el mundo gastronómico? En nuestra agencia de marketing digital especializada en restaurantes locales y negocios gastronómicos, estamos buscando un diseñador o diseñadora con talento y visión para sumarse a nuestro equipo.


🔧 ¿Qué necesitamos de ti (a nivel técnico)?

- Experiencia comprobable en diseños para anuncios publicitarios para restaurantes.
- Dominio de herramientas como Photoshop, Adobe Illustrator y Canva.
- Conocimiento y uso de herramientas de inteligencia artificial para transformar imágenes de productos de comida en anuncios visualmente impactantes.
- Plus si sabes darle vida al contenido con motion graphics o pequeños efectos (no excluyente).


🧠 ¿Qué buscamos en ti como persona?

- Que seas responsable y cumplas con los tiempos de entrega.
- Que seas comunicativo, te guste recibir feedback y mantenernos al tanto del avance de los proyectos.
- Que tengas una actitud proactiva y creativa, siempre con ideas frescas y soluciones.
- Que te apasione el detalle y tengas buen ojo estético, sobre todo en el rubro gastronómico.


💼 ¿Qué ofrecemos?

- Pago mensual de $150 USD.
- Carga de trabajo baja a moderada.
- No hay horarios fijos: trabajas a tu ritmo, siempre y cuando cumplas con los plazos acordados.
- Posibilidad de crecer dentro del equipo a medida que lo hacen nuestros clientes.


📩 ¿Te interesa? Esto es lo que necesitamos de ti:

- Tu portafolio con diseños relacionados con el sector gastronómico (restaurantes, cafés, food trucks, etc.).
- Una breve descripción de tu experiencia con las herramientas requeridas.

Skills: Advertising Design, AI Image Generation, Flyer Design, Food & Beverage, Adobe Illustrator, Canva, Graphic Design, Ad Creative, Adobe Photoshop

I have 2 Photoshop task one more simple task and one complex task, task one is a picture of me that is now very static, I want other background and more natural flow (I can send reference how I want it that was created by ai but my face looks totally different) and task 2 will be more complex, I have loose pictures of me and my bike. I want you (Maybe with ai) to generate a picture of me in live action cycling on that bike. I have access to sora so if you need that I can help you out.


Price= 10$

Skills: Adobe Photoshop, Photo Editing, Image Editing, AI Image Generation

We're looking for an expert in artificial intelligence, digital character creation, and branding to help us develop a virtual female influencer powered by AI.

The character already has a defined personality, aesthetic, tone of voice, and monetization goals (e.g. OnlyFans, social media, etc.). Our goal is to build a consistent visual and narrative identity, using the right tools to generate believable, high-quality content at scale.

What we need:
- Strategic advice on how to structure the workflow: what tools to use (DALL·E, Midjourney, Stable Diffusion, ChatGPT, etc.), how to integrate them, and how to scale content creation
- Technical input on generating photorealistic images (selfies, lifestyle pics, etc.) and possibly short animations.
- Guidance on how to keep the character’s visual and narrative identity consistent (style, tone, storytelling)
- Optional: insights into monetization strategies, and how to position this type of persona on social media

Ideal profile:
- Experience creating AI-generated characters, virtual influencers, or avatars
- Strong knowledge of generative AI (image, text, voice, video)
- Creative mindset and strategic thinking for experimental projects
- Bonus: background in digital marketing, influencer branding, or the creator economy

Additional Info:
- This is an hourly-rate consulting project
- An NDA will be required before any sensitive details are shared

Skills: AI Image Generation, AI Consulting, Generative AI, Generative AI Prompt

We are creating an Advent calendar puzzle game product, for which we need beautiful and festive Christmas-themed pictures. The pictures need to be composed in a very particular way to work well for this product, and then created with a high level of detail.

In total, we need 8 pictures, but this job is priced for a single one. If we're happy with it, we may ask you to do more.

The project of generating these pictures can be split into two parts. Below is a brief overview of each part. More detailed instructions will be provided after hiring.

We'd prefer to hire people who can take on both parts, but we'll consider those who can only do one of them really well.
___________

1: The first part is the creative planning stage. We want artists to generate creative ideas in the form of concepts/sketches/layouts for the pictures that will be generated.

Each image will be a square, physical size 22.5x22.5 cm. This image will be subdivided into 9 smaller squares by a 3x3 grid. Each of these smaller squares (7.5x7.5 cm) will itself be a puzzle in the game.

So, the main complexity is that the picture needs a precise layout such that when it is split into the 9 small squares, each of the small squares itself is an interesting and detailed picture. We want to craft these pictures in a way that really optimizes for the small squares, while still allowing them to be reassembled into a bigger picture that is interesting and makes sense.

For content and style, we're looking for festive, cozy, and holiday-themed. The image could show some type of scene: Christmas villages, festive celebrations, Santa's workshop, Santa's sleigh in the sky, Christmas Tree and fireplace, etc.

The scene should feature christmas and holiday symbols: santa, elves, reindeer, sleigh, snow, garlands, carolers, christmas tree, holly, snowman, fireplace, stockings, vintage train, wreaths, decorations, etc. The picture should evoke holiday warmth, festive cheer, and visual storytelling.

It needs to lend itself to a realistic style (digital painting, illustrative realism, photo realism, etc.), because the smaller squares should have a high level of detail.

Please see attached "sleigh_3x3.png" to better understand what we're looking for.

In this image, you can see a picture of a sleigh with the 3x3 grid overlaid. Regarding content, this picture fits the theme well. But stylistically, this picture is not vibrant or detailed enough. And on the level of individual small squares, only a few of them work well. Let's grade each square and explain.

1) 8/10. This works because the woman's head is the focus, with a winter hat on her. There are Christmas decorations in the background. However, ideally the woman's head would be larger and more centered inside the square.
2) 5/10. The man is nicely centered and takes up most of the square. However, he is very drab in appearance. There is nothing festive, and it's not interesting at all by itself.
3) 8/10. Two interesting subjects - the horse and the snow shoveler. Shoveling snow is on theme. Would be improved if the horse's head fit entirely into this square.
4) 9/10. The wreath is a classic Christmas symbol, and here it is centered and without distractions. So even though it is not too interesting, it's great.
5) 2/10. Taken by itself, it's unclear what is even going on here, it's a mess. This won't work. It could maybe be improved by adding some intricate decorations on the side of the sleigh.
6) 5/10. The bottom half of the horse is not that interesting, nor is it Christmas themed. Could be improved by placing an object in the foreground, like a street lamp.
7) 5/10. Not too interesting, but also not cluttered and there is something artistic about it. The tracks in the snow have a nice texture. Surprisingly, this could work.
8) 0/10. Too similar to square 7. We can have one of them, but not both.
9) 0/10. No good at all.
___________

2: The second part is actually generating realistic and detailed illustrations based on the sketches from the first stage. It will probably be best to do this with the help of generative AI like MidJourney, Stable Diffusion, etc. The images we are generating will be quite complex with many objects in a precise layout. So if working with AI, it will probably be a complex task requiring remixing or else manually stitching several images together.

The final images should be in a realistic style (digital painting, illustrative realism, photo realism, etc.) with a high level of detail, vibrant colors, and high contrast.

The image will be printed and trimmed to a physical size of 225x225 mm. We need to add 3.175 mm bleed on all sides. The image should be 300 DPI.

So, the size of the image has to be at least 2732x2732 px. Working with AI, images can be generated at 2048x2048 and upscaled if needed.
___________

To apply, please show examples of relevant past work, and describe why you'll be good at this project.

Skills: Midjourney AI, AI-Generated Art, AI Image Generation, Digital Art, Realistic, Traditional Style, Graphic Design, Adobe Photoshop, Illustration

We’re assembling a supplemental creative team to help bring a new product website to life — and we’re looking for a Graphic Designer with expert-level skill in AI image generation prompting.

This role is perfect for someone who thrives at the cutting edge of design and tech, using tools like Midjourney, DALL·E, Stable Diffusion, and more to create high-quality visual assets that align with brand and narrative goals.

You’ll help us:
Generate unique, high-quality visuals for the website’s hero sections, UI background art, and storytelling blocks
Craft precise prompts that yield stunning and intentional AI-generated imagery
Refine, retouch, and finalize assets in line with brand guidelines
Collaborate with our core design/dev team for seamless asset handoff

You are:
A strong visual designer with a killer aesthetic and a portfolio to match
Experienced in AI image tools and strategic prompting
Agile and fast-moving in feedback-driven creative sprints
Familiar with website creative workflows, especially product marketing pages

Bonus if you:
Have worked with startups or new product launches
Understand web UX principles and how to design for layout, scale, and responsiveness

To Apply:

Please send:
Examples of your AI-generated design work
A quick note on your prompting approach
Your availability and hourly/project rate

Skills: ChatGPT, Midjourney AI, Runway, Logo Design, Infographic, Illustration, Adobe Photoshop

We’re building Warmly.AI – an AI-powered platform that creates holiday-themed family portraits from individual photo uploads.

We're looking for an experienced AI developer or ML engineer to help us build and fine-tune a Winter Wonderland theme generator using Stable Diffusion with ControlNet and IP-Adapter. The goal is to dynamically compose individual user-uploaded faces into a photorealistic, festive, winter-themed group portrait.

What We Need:
Setup and integration of Stable Diffusion (v1.5 or SDXL) into our backend (can use RunPod, Replicate, or self-hosted)

Integration of:

ControlNet (pose or composition control)

IP-Adapter (face identity/reference guidance)

Ability to combine 3–6 individual photos into one cohesive group portrait with:

Natural expressions and positioning

Winter clothing (inpainted or prompted)

A snowy, pine-forest or cozy outdoor festive backdrop

Warm golden-hour lighting and subtle snowfall effect

Support for dynamic prompt building and post-processing if needed

Output must be high-resolution (at least 2048px wide) and visually seamless

Example Use Case:
Users upload 3–6 individual headshots.

System extracts face crops and optionally a group layout (or default pose template).

Your generation pipeline takes the data and outputs a photorealistic group image in a Winter Wonderland scene.

Final output is stored and made available to the user for download or print (handled separately).

Nice-to-Have Experience:
Prior work with portrait composition or facial blending using diffusion models

Experience optimizing prompt structure and negative prompts

Familiarity with Printify API (optional, but useful for understanding our pipeline)

Knowledge of image inpainting, upscaling (Real-ESRGAN, etc.), and post-processing pipelines

Deliverables:
Working image generation pipeline (dockerized or callable via API)

Sample outputs using test images (we'll provide test faces)

Documentation for API or callable function

Assistance integrating it into our existing web stack (optional but appreciated)

Skills: Stable Diffusion, Web Design, Artificial Intelligence

OVERVIEW
We’re building a library of sleek, on‑brand skyline images for dozens of U.S. cities. Each graphic will be used in social posts and marketing assets. You’ll follow a streamlined workflow—Google Image search, ChatGPT‑4 image generation, and a Figma template—to produce, polish, and export the final JPEGs.

Here's a Loom video walking through the task: https://www.loom.com/share/7619e18f77cc439fa4815a402411c650?sid=ee1475ef-6db5-4bf0-b02b-7e4b35de3c87

KEY RESPONSIBILITIES
- Source an attractive skyline reference (or skip if none exists) for each assigned city.
- Generate a stylized illustration in ChatGPT‑4 using our pre‑written prompt (attach reference photo when available).
- Insert and adjust the illustration in our Figma template:
• Replace the old image layer.
• Resize to fit the frame.
• Tweak exposure/contrast until seams disappear.
- Update headline text with the correct city (include state for smaller metros).
- Export each frame as a 1× JPEG named City‑State.jpg.
- Upload the files to the designated Google Drive folder.
- Repeat until all cities in the Airtable list are complete (initial batch ≈ 75 cities; ongoing work likely).

REQUIRED SKILLS
- Figma (layer management, basic image adjustments, exporting assets).
- Familiarity with ChatGPT or similar AI image‑generation tools.
- Solid eye for composition, contrast, and branding consistency.
- Reliable internet connection and the ability to manage dozens of small, repetitive tasks efficiently.

Skills: Figma, ChatGPT

We're looking for a creative graphic designer to produce high-converting static image ads for our fashion brand PARIJAN, which embodies the refined old money aesthetic.

Our ideal candidate not only has a strong design eye but also knows how to leverage AI tools like ChatGPT or Midjourney to generate high-quality fashion visuals when needed.

Your tasks will include:
- Designing static images for Facebook, Instagram, and TikTok
- Make Instagram stories
- Using AI image tools (e.g., ChatGPT’s image generation, Midjourney) to create or enhance visuals
- Following our brand old money aesthetic and direction to keep visuals elegant and on-brand

Nice to have:
- Experience with Shopify brands or performance marketing
- Passion for fashion, or “quiet luxury” visuals

To apply, please include your portfolio. Thank you!

Skills: Canva, Advertising Design, AI Image Generation, Fashion & Beauty, Graphic Design, Instagram

We're looking for an experienced ads image creator & editor.

We run continuous testing of ads and creative on Facebook.

We need to create 15 - 20 images a month.

We provide full descriptions of what is needed.

See examples below.

Using AI images generators is okay, as long as the images are 'photo realistic'.

Please indicate your pricing for the above work.

Thanks, Terry

========

EXAMPLES OF IMAGE DESCRIPTIONS

Image Description:

A three-panel progression showing James's car journey.

First panel shows James looking defeated at a dealership with "510 Credit Score" and "NOT APPROVED" stamp visible.

Middle panel shows James discovering our platform on his laptop, looking hopeful.

Final panel shows James confidently holding car keys beside a reliable vehicle with a warranty certificate visible.

Text Overlay:

"When Dealers Said 'Really Hard,' We Said 'Really Possible'"

Designer Instructions:

• Use a visual progress bar across the top showing the journey from "Rejection" to "Application" to "Approval" to "Driving"
• Include checkmarks next to our key differentiators (Quick online application, Pre-approved in minutes, Clear cost breakdown, Quality certified vehicles)
• Use a color scheme transitioning from blue/gray (rejection) to vibrant green (success)
• Add a subtle clock element showing the 48-hour timeline
• Include a stylized quote bubble with James's testimonial: "They showed me the real numbers, not just a payment designed to trap me"
• Create a visible "Apply Now" button with "Zero Credit Impact" text beneath it

Skills: AI Image Editing, AI Image Generation, Graphic Design, Facebook