SD.Next vs Artcraft vs InvokeAI

Side by side, as alternatives to Adobe Firefly. Rows that differ are highlighted; the strongest value in a row is marked. Unknown means no source yet.

SD.Nextvladmandic/sdnext

Artcraftstorytold/artcraft

InvokeAIinvoke-ai/InvokeAI

Adobe Fireflypaid product

Cost and coverage

Price

$0 software; you run it

Free daily generations; paid plans from US$9.99/month (2,000 generative credits) source ↗

Text-to-image

Partly

Yes

Image editing (generative fill and expand)

Partly

Yes

Style and image reference

Partly

Yes

Jobs covered

3 of 3 jobs

2 of 3 jobs

All 3

Popularity and activity (from GitHub)

Stars

7,357

34,551Top

28,793

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

273

896Top

—

Latest release

Unknown

artcraft-v0.41.0 · 2026-09-26

v6.14.2 · 2026-09-27Top

—

Commits / 12 wk

895

1,890

—

People committing / 12 mo

21+

77+

—

Issues opened / closed, 30 days

21 / 17

361 / 56

146 / 207

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, local server and web UI; Docker recipes

Yes, desktop app for Windows and macOS; the listed image and video models are hosted provider services

Yes, local web server and UI

Hosted by the vendor

Code licence

Apache-2.0

—

Model weights licenceDiffers

No single default; picks from a reference model list, licence varies

Model/provider-specific. No blanket weights licence verified for the hosted catalogue; the application licence is separate.

No single default model; licence depends on the model you install

—

Commercial useDiffers

Apache-2.0 code; weights vary (e.g. FLUX.1-dev is non-commercial)

Yes, code is MIT or Apache-2.0 at your option

Apache-2.0 code; weights vary (SD3.5 community licence, FLUX.1-dev non-commercial)

—

Paid services needed?Differs

None required

Not checked yet

None required; some models are API-only (GPT Image, Nano Banana, Wan)

Subscription

HardwareDiffers

CPU-only supported; SDNQ cuts VRAM up to 4x; no minimums stated

Windows 10 (64-bit) or macOS 12.0 or newer; 8 GB RAM recommended; 2 GB free storage

SD1.5 4GB VRAM/8GB RAM; SDXL 8GB/16GB; FLUX.1 10GB/32GB

—

Operating systemsDiffers

Windows, Linux, macOS (Apple M1/M2 via MPS)

Windows and macOS installers; Linux by building from source

Windows 10+, macOS 14+ (Apple Silicon), Linux

—

Setup effortDiffers

Medium; needs git and Python, then run webui script

Easy; download the Windows or macOS installer

Easy, official Invoke Launcher

—

Stars over time

Switch to Growth % to compare projects of different sizes fairly.

SD.Next
Artcraft
InvokeAI

Focus a point, use arrow keys, or tap for its value.

Tracked daily since 15 Oct 2026. Dashed history: estimated from public records of when people starred the repo. Lines connect observations only; gaps contain no measured points.

Growth % starts at each project's first observed point in the shown range. Zero-star starts are unavailable.

Notes for a video or post

A plain summary with today's date and a link to the sources. Check each project page before you publish.

SD.Next vs Artcraft vs InvokeAI (as alternatives to Adobe Firefly)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=sdnext,artcraft,invokeai&product=adobe-firefly

Adobe Firefly: Free daily generations; paid plans from US$9.99/month (2,000 generative credits)
SD.Next: free software; does 3 of 3 Adobe Firefly jobs
Artcraft: free software; does 2 of 3 Adobe Firefly jobs
InvokeAI: free software; does 2 of 3 Adobe Firefly jobs

- SD.Next: 7,357 GitHub stars, 895 commits in 12 weeks, licence Apache-2.0
- Artcraft: 34,551 GitHub stars, 27 commits in 12 weeks, licence Apache-2.0
- InvokeAI: 28,793 GitHub stars, 1,890 commits in 12 weeks, licence Apache-2.0

Where they differ:
- Runs on my machine?: SD.Next Yes, local server and web UI; Docker recipes; Artcraft Yes, desktop app for Windows and macOS; the listed image and video models are hosted provider services; InvokeAI Yes, local web server and UI
- Model weights licence: SD.Next No single default; picks from a reference model list, licence varies; Artcraft Model/provider-specific. No blanket weights licence verified for the hosted catalogue; the application licence is separate.; InvokeAI No single default model; licence depends on the model you install
- Commercial use: SD.Next Apache-2.0 code; weights vary (e.g. FLUX.1-dev is non-commercial); Artcraft Yes, code is MIT or Apache-2.0 at your option; InvokeAI Apache-2.0 code; weights vary (SD3.5 community licence, FLUX.1-dev non-commercial)
- Paid services needed?: SD.Next None required; Artcraft Not checked yet; InvokeAI None required; some models are API-only (GPT Image, Nano Banana, Wan)
- Hardware: SD.Next CPU-only supported; SDNQ cuts VRAM up to 4x; no minimums stated; Artcraft Windows 10 (64-bit) or macOS 12.0 or newer; 8 GB RAM recommended; 2 GB free storage; InvokeAI SD1.5 4GB VRAM/8GB RAM; SDXL 8GB/16GB; FLUX.1 10GB/32GB
- Operating systems: SD.Next Windows, Linux, macOS (Apple M1/M2 via MPS); Artcraft Windows and macOS installers; Linux by building from source; InvokeAI Windows 10+, macOS 14+ (Apple Silicon), Linux
- Setup effort: SD.Next Medium; needs git and Python, then run webui script; Artcraft Easy; download the Windows or macOS installer; InvokeAI Easy, official Invoke Launcher

Stars show popularity, not quality. Check each project page before publishing.

Want share images and a ready video description? Open a project's creator kit.

Numbers: GitHub, fetched nightly. Facts: read from each project's own documentation, with the source on its page. How we check. vladmandic/sdnext ↗storytold/artcraft ↗invoke-ai/InvokeAI ↗

SD.Next vs Artcraft vs InvokeAI

Stars over time

Notes for a video or post

Cookie preferences

Report a problem