(Location - Remote Germany)
About the role:
We are looking for Model Finetuners who will be responsible for fine-tuning the next generation of Stable Diffusion - image, video, 3D and audio models for Stability. The ideal candidate will be experienced with ComfyUI workflows, have basic programming skills, the ability to fine-tune custom models and create high quality datasets.
Responsibilities:
- Work with the Applied Research team on developing solutions for customers with image, video and 3D models in ComfyUI
- Work with the open-source community to develop cutting edge technologies for products and workflows
- Work with the base models to create fine-tunes and extensions like ControlNets and IPAdapters
- Collect, create and curate datasets for training and fine-tuning
- Work with Product, Engineering and Commercial teams on model and workflow deployment and customized training
- Keep up to date with the latest research advancements in the field and work them into open-source repos, reimplementing as needed to ensure an open license
- Help evaluate the quality of the models and workflows created by the Research and Applied Research team
Qualifications:
- Proven experience with image, video models (3D and audio knowledge is a nice to have)
- Low rank and full fine-tuning experience using Diffusers and other training methods
- Proven ComfyUI workflow knowledge
- Able to demonstrate your relevant work via portfolio or social media / community sharing
- Basic programming skills in Python
- Working with Linux operating system, plus working with CUDA and PyTorch
- Experienced implementing and managing the finetuning process on datasets to improve image generation quality and diversity
Equal Employment Opportunity
We are an equal opportunity employer and do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or other legally protected statuses.