ComfyUIBuild reusable node workflows for local text-to-video and image-to-video generation.
Free GPL-3.0 app · Local Wan 2.1 · Own GPU required
AI tools
SwarmUI
Free optionOpen sourceLocal
Generate images from text prompts and refine variations using local diffusion models.
What you can use it for
Generate images from text prompts and refine variations using local diffusion models.
- Choose diffusion models and adjust prompt, seed and image size.
- Generate batches and download the resulting images.
Workflow coverage and comparison notes
Self-hosted text-to-image generation instead of buying additional hosted image-generation capacity. Krea and Leonardo also offer free quotas. This is a local image workflow using separately licensed models, not access to the named proprietary models or all editing/video/realtime features.
Before you switch
Technical installation and suitable GPU hardware required; rented GPU hosting costs money. Each model has its own licence and commercial-use restrictions. Covers prompt-to-image generation, not proprietary model access, identical output quality, hosted collaboration, Krea realtime drawing or video features.
Alternatives to these paid apps
Each comparison covers the workflow described above, rather than every paid feature.
More for the same workflow
See alternatives →ComfyUI
InvokeAIGenerate images and edit selected areas of artwork with Stable Diffusion workflows.
Free and open source (Apache-2.0 licence per GitHub).