Media lab

Choose the layer before choosing the model.

A model is the learned generator. A UI is how you operate it. A runtime is what loads it. A host is where the computer lives. Keeping those layers separate makes experimentation much less confusing.

Starting point for your PC: prior context records an RTX 4060 with 8 GB VRAM. Begin with one local 1024px image in Fooocus/SDXL, then lower resolution or simplify the workflow if memory is tight. Re-check this hardware assumption before buying or renting around it.

Paths by ambition

PathGood first choiceStrengthTradeoff
Easy local imageFooocus + SDXLOffline, simple prompt-focused workflow, modest setup.Fooocus is now limited long-term support with bug fixes; its model family is SDXL, not every new image model.
Controlled local pipelineComfyUINodes expose model, conditioning, control, upscaling, video, audio, and other stages.More power means more concepts, workflow files, custom nodes, and maintenance.
Hosted image/video/audioProvider API or managed workspaceLittle local setup, access to large models, easy burst capacity.Ongoing cost, provider terms, data transfer, rate limits, and less control.
Cloud GPU workstationRented GPU Pod or dedicated GPU serverMore VRAM and batch throughput without buying hardware.Storage, security, idle billing, model downloads, and shutdown discipline matter.

Model families worth understanding

Family / exampleMediaPractical readLicense note
SDXL 1.0ImageMature base model and a natural match for Fooocus. The model card describes base and optional refiner stages.CreativeML Open RAIL++-M; read the actual model card and restrictions before redistribution or a commercial service.
FLUX.2 KleinImage and editingNewer open-weight direction; the official overview lists a 4B version under Apache 2.0 and a 9B version under a non-commercial license.“Open weights” does not mean every size or use has the same license. Verify the exact checkpoint.
FLUX [dev]ImageStrong image-generation direction with self-hosting options.Terms can require commercial licensing, filtering, or review. Do not choose it for publishing until the exact terms are checked.
Video, audio, and 3D ecosystemsVideo, speech/music, 3DFast-moving families are often easiest to operate through ComfyUI workflows or hosted endpoints.Model cards, datasets, voices, likenesses, and outputs can have separate restrictions. Review each component.
Checkpoint

A saved model state

Usually a large file containing learned weights. Think of it as the trained “brain” a runtime loads. Different checkpoints can change style, anatomy, speed, memory needs, and license.

LoRA

A small adaptation

A lightweight add-on that nudges a base model toward a style, subject, or behavior. It is not automatically compatible with every checkpoint, and its own license matters too.

SDXL

A model architecture

Stable Diffusion XL is a diffusion-based image model family. Fooocus is an application built around SDXL; SDXL is not the same thing as Fooocus.

VRAM

Graphics memory

The working space for model weights and intermediate images. Quantization, offloading, lower resolution, fewer stages, and smaller models can reduce pressure, but each changes speed or quality.

Copyright and safety checklist

Recommended exploration order

1) one SDXL image locally, 2) one project-referenced image set, 3) a repeatable ComfyUI workflow, 4) compare one rented GPU session, 5) only then evaluate video/audio/3D or public serving. This order keeps the learning curve and spend visible.