ComfyUI
The nodal workflow engine for serious diffusion.
Open Source 6–16 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Krita AI Diffusion
Stable Diffusion baked into a real painting app.
Open Source 6–12 GB VRAMRuns locally
Actually FreeNo SignupOpen SourceWatermark-FreeHobbyist-FriendlyPlugin
Requires: ComfyUI
Visit Krita AI DiffusionUpdated 2026-05-10 · Direct link
Hardware requirements
Runs locally · Entry GPU (6–8 GB)
Min VRAM
6 GB
Rec. VRAM
12 GB
Min RAM
16 GB
Rec. RAM
32 GB
Disk
30 GB
GPU class
Entry GPU
Apple Silicon ✓GPU RequiredQuant: FP16, FP8
Inherits ComfyUI's requirements — backend does the heavy lifting.
Screenshot placeholder · Krita AI Diffusion
What is Krita AI Diffusion?
An open-source Krita plugin that turns the painting workflow inside out: paint a rough composition, mask a region, hit generate, refine, repeat. Uses ComfyUI as the local backend so you can swap in any checkpoint, LoRA, or ControlNet. The preferred toolchain for digital artists who want diffusion in their existing canvas — not a separate Gradio tab.
Pros & cons
Pros
- Inpainting / outpainting / refine inside a real painting tool
- Uses your existing ComfyUI install — no duplicate models
- Live generation as you paint with the auto-refresh option
Cons
- Requires Krita 5.2+ and a running ComfyUI backend
- Initial setup is fiddlier than a one-click installer
What's actually free?
GPL plugin; Krita itself is free and open.
✓ Actually FreeNo SignupOpen SourceWatermark-Free
Alternatives
InvokeAI
Production-leaning SD studio with canvas & batch.
Open Source 8–16 GB VRAM
- Min VRAM
- 8 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free