We are looking for someone who is proficient at using Comfy UI, Automatic 1111, ControlNet, LoRA model training, text-to-image and image-to-image generation techniques, plus experience with models such as Stable Diffusion, DALL-E, or MidJourney. Proficiency in Python and popular AI/ML libraries would be an added bonus. The chosen intern should have a keen eye for design and preferably a passion for fashion. Strong communication and problem-solving skills are essential.
Proficiency with Open-Source Generative AI Tools, including but not limited to:
• Automatic1111 (Stable Diffusion UI)
• LoRA (Low-Rank Adaptation) model training
• Text-to-image and image-to-image generation techniques
Understanding of Generative AI Architectures
• Experience with models such as Stable Diffusion, DALL-E, or MidJourney
Strongly considered/ Preferred Qualifications:
• Ability to prepare datasets for model training (data cleaning, labelling, augmentation)
• Experience with handling large-scale image datasets
Programming and Development Skills:
• Proficiency in Python and popular AI/ML libraries (PyTorch, TensorFlow)
• Familiarity with API integrations for generative tools and workflows
• Familiarity with GANs, VAEs, or diffusion-based models
• Knowledge of tools like Adobe Photoshop for post-processing outputs
• Experience with tools for creating 3D visuals is a plus (e.g., Blender, CLO 3D)
• Experience of working on AI projects specifically tailored to the fashion or creative industries
• Familiarity with ethical considerations and copyright laws related to AI-generated outputs
• Strong problem-solving abilities and a detail-oriented mindset
• Excellent communication skills, especially when discussing technical concepts with non-technical clients/audience
• Ability to work both independently and as part of a team
• Passion for AI and its application in creative industries, particularly fashion
We are an equal opportunities employer and positively encourage applications from suitably qualified and eligible candidates regardless of sex, race, disability, age, sexual orientation, gender reassignment, religion or belief, marital status, or pregnancy and maternity.
All candidates would be required to share a portfolio showcasing generative AI outputs or projects and workflows.