compare
ComfyUI vs InvokeAI
The same facts for both, read from GitHub every night, and the relation a person reviewed.
| Fact | ComfyUI | InvokeAI |
|---|---|---|
| Language | Python | TypeScript |
| Licence | GPL-3.0 | Apache-2.0 |
| Stars | 136k | 28k |
| Latest | v0.39.0 | v6.14.2 |
| Last push | 2026-10-06 | 2026-10-06 |
| Release cadence | about 6 days between releases | about 16 days between releases |
| Active contributors | 49+ commit authors on the default branch in the last 90 days | 9+ commit authors on the default branch in the last 90 days |
| Flags | none | none |
How they relate
Both replace Midjourney. Alternatives to Midjourney →
PartialComfyUIRuns open diffusion models on your own GPU through a node graph; Midjourney's own models are not available.
PartialInvokeAIRuns open models such as Stable Diffusion and FLUX locally, with a canvas for inpainting and node workflows; Midjourney's own models are not available.
ComfyUI
- v0.39.02026-10-05Support LynnReal light Minimax-H3 vae
- v0.38.02026-09-29Improve qwen 2.1 KV cache location logic
- v0.37.02026-09-21Aimdo 0.5.5 + Auto-detect and enable --fast-disk when the disk is fast (CORE-440)
- v0.36.02026-09-15Add new model blueprints and reorganize subgraph categories
- v0.35.02026-09-09[Partner Nodes] chore(Google): drop retiring Veo 2 and Veo 3.0 models
InvokeAI
- v7.0.0-alpha.12026-10-04InvokeAI 7.0.0 (alpha 1)pre-release
- v6.14.22026-09-27Version 6.14.2
- v6.14.12026-09-06Version 6.14.1
- v6.14.02026-08-25InvokeAI 6.14.0
- v6.14.0-rc22026-08-16InvokeAI 6.14.0 (release candidate 2)pre-release
ComfyUI
unsigned The latest release, v0.39.0, carries no signature GitHub could verify.
Loading the security report
InvokeAI
unsigned The latest release, v6.14.2, carries no signature GitHub could verify.
Loading the security report