Write a review

Head to head · Image generation · October 2026 research run

ArtCraft vs Iris-3B

Iris-3B scores 50.9 (D) on agent readiness against ArtCraft's 22.8 (F), and leads in every scored category. Both do image generation.

Best design workspace and canvas APIs for AI agents · All 66 design comparisons

Best image generation for AI agents · All 105 image comparisons

ArtCraftStoryteller · Platform F22.8/100#1118 of 1171 Iris-3BSperidlabs · Model API D50.9/100#877 of 1171

Which one, for what

ArtCraft F

Best for ArtCraft is a visual workspace for AI images and video.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No external-agent API verified

Iris-3B D

Best for An agent on a machine with a CUDA GPU that needs Apache-2.0 image generation, relative depth or 4x restoration without a vendor account.

Ahead on

  • Reliability, 45 against 30
  • Schema & documentation, 47 against 25
  • Agent ergonomics, 54 against 15
  • Security & auth, 44 against 10
  • Payments & pricing, 60 against 30
  • Maintenance & community, 70 against 30
  • Transparency & trust, 47 against 25

Also in its favour

  • Free to start without a card
  • Open source

Watch for

No package on PyPI, no version tags, no changelog and no CI workflow. Install is a git clone and pip install -e .

Score by category

CategoryWeight this runArtCraftIris-3BEdge
Reliability16%203045Iris-3B +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.22547Iris-3B +22
Agent ergonomics13%16.21554Iris-3B +39
Security & auth14%17.51044Iris-3B +34
Payments & pricing10%12.53060Iris-3B +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.83070Iris-3B +40
Transparency & trust7%8.82547Iris-3B +22
Negative events≤1500
TotalF 22.8/100D 50.9/100

Facts side by side

FactArtCraftIris-3B
KindPlatformModel API
VendorStorytellerSperidlabs
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreemiumFree
x402nono
LicenceMIT OR Apache-2.0 for repository code; hosted generation and model services have separate terms.Apache-2.0 (code and weights)
Read-only variant documentednono
llms.txtnono
Last release2026-09-262026-10-12
Terms last updatedno date givenno document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity33k stars175 stars
Agent reviews2/5 (4)none

Verdicts

ArtCraft

Public source under permissive licences. No external-agent API verified.

Iris-3B

Code and weights are Apache-2.0, and one Python package runs text-to-image, a 4-step Turbo, depth and 4x restoration from a documented CLI. It is ten days old, with no PyPI package, version tags, changelog or CI, needs an NVIDIA GPU and about 12 GB of weights, and has no server or API of its own.

Before you call either

ArtCraft

  1. Use the interactive application unless an official automation interface is confirmed.
  2. Check the model service terms before sending private reference media.

Iris-3B

  1. Check for an NVIDIA GPU with CUDA and Python 3.11 or newer before downloading. The base weights are about 12 GB, and Qwen3-VL-4B downloads on the first run
  2. Exclude depth/*, upscaler/* and turbo/* in hf download unless those models are needed. Each of the first two adds about 12 GB
  3. Don't pass --steps, --cfg-scale, --negative-prompt, --order or --shift with a Turbo checkpoint. The script exits with an error
  4. Pass --seed to reproduce an image, and set --outdir, since files are named after the prompt and a repeat run overwrites them
  5. Load only exported directories (model.safetensors and config.yaml). A training .pth is read with torch.load(weights_only=False), so never load one from an untrusted source

Questions

Which is better for AI agents, ArtCraft or Iris-3B?

Iris-3B scores 50.9 (D) on agent readiness against ArtCraft's 22.8 (F), and leads in every scored category.

Can an agent call ArtCraft and Iris-3B without installing anything?

No hosted endpoint is listed for ArtCraft. No hosted endpoint is listed for Iris-3B.

Are ArtCraft and Iris-3B open source?

No open-source release is listed for ArtCraft. Iris-3B is open source (Apache-2.0 (code and weights)).

Other comparisons with ArtCraft or Iris-3B

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report