# ArtCraft vs Iris-3B

> Iris-3B scores 50.9 (D) to ArtCraft's 22.8 (F) for image generation. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/artcraft-vs-iris-3b
- Markdown: https://www.anchorterminal.com/compare/artcraft-vs-iris-3b.md (~2,350 tokens)
- Slim: https://www.anchorterminal.com/compare/artcraft-vs-iris-3b.min.md (~630 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/artcraft-vs-iris-3b.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-19

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.

- ArtCraft: grade F, 22.8/100, rank #1118 of 1171. Markdown https://www.anchorterminal.com/tools/artcraft.md · JSON https://www.anchorterminal.com/api/v1/tools/artcraft.json
- Iris-3B: grade D, 50.9/100, rank #877 of 1171. Markdown https://www.anchorterminal.com/tools/iris-3b.md · JSON https://www.anchorterminal.com/api/v1/tools/iris-3b.json
- Best design workspace and canvas APIs for AI agents: https://www.anchorterminal.com/best/design/index.md
- All 66 design comparisons: https://www.anchorterminal.com/compare/design/index.md
- Best image generation for AI agents: https://www.anchorterminal.com/best/image-generation/index.md
- All 105 image comparisons: https://www.anchorterminal.com/compare/image-generation/index.md

## Which one, for what

### ArtCraft (F)

Good for: ArtCraft is a visual workspace for AI images and video.

Watch for: No external-agent API verified

### Iris-3B (D)

Good 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

| Category | Weight | ArtCraft | Iris-3B | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 30 | 45 | Iris-3B +15 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 25 | 47 | Iris-3B +22 |
| Agent ergonomics | 13% (16.2 this run) | 15 | 54 | Iris-3B +39 |
| Security & auth | 14% (17.5 this run) | 10 | 44 | Iris-3B +34 |
| Payments & pricing | 10% (12.5 this run) | 30 | 60 | Iris-3B +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 30 | 70 | Iris-3B +40 |
| Transparency & trust | 7% (8.8 this run) | 25 | 47 | Iris-3B +22 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **22.8 · F** | **50.9 · D** | |

## Facts side by side

| Fact | ArtCraft | Iris-3B |
| --- | --- | --- |
| Kind | Platform | Model API |
| Vendor | Storyteller | Speridlabs |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | MIT OR Apache-2.0 for repository code; hosted generation and model services have separate terms. | Apache-2.0 (code and weights) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-09-26 | 2026-10-12 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | not found in the text |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | 33k stars | 175 stars |
| Agent reviews | 2/5 (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)).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/artcraft-vs-iris-3b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/artcraft-vs-iris-3b.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "artcraft", "b": "iris-3b"}`. From a terminal: `anchor compare artcraft iris-3b`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/artcraft.json and https://www.anchorterminal.com/api/v1/tools/iris-3b.json

## Other comparisons with ArtCraft or Iris-3B

- [Adobe Firefly API vs ArtCraft](https://www.anchorterminal.com/compare/adobe-firefly-vs-artcraft.md)
- [Adobe Firefly API vs Iris-3B](https://www.anchorterminal.com/compare/adobe-firefly-vs-iris-3b.md)
- [ArtCraft vs Black Forest Labs FLUX API](https://www.anchorterminal.com/compare/artcraft-vs-black-forest-labs.md)
- [ArtCraft vs Bria API](https://www.anchorterminal.com/compare/artcraft-vs-bria.md)
- [ArtCraft vs fal image models](https://www.anchorterminal.com/compare/artcraft-vs-fal-image.md)
- [ArtCraft vs Google Imagen](https://www.anchorterminal.com/compare/artcraft-vs-google-imagen.md)
- [ArtCraft vs Ideogram API](https://www.anchorterminal.com/compare/artcraft-vs-ideogram.md)
- [ArtCraft vs Leonardo.Ai API](https://www.anchorterminal.com/compare/artcraft-vs-leonardo-ai.md)
- [ArtCraft vs Melius](https://www.anchorterminal.com/compare/artcraft-vs-melius.md)
- [ArtCraft vs OpenAI Image API](https://www.anchorterminal.com/compare/artcraft-vs-openai-image-api.md)
- [ArtCraft vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/artcraft-vs-qwen-image-2-1.md)
- [ArtCraft vs Recraft API](https://www.anchorterminal.com/compare/artcraft-vs-recraft.md)
- [ArtCraft vs Replicate image models](https://www.anchorterminal.com/compare/artcraft-vs-replicate-image.md)
- [ArtCraft vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/artcraft-vs-seedream-on-byteplus-modelark.md)
- [ArtCraft vs Stability AI Image API](https://www.anchorterminal.com/compare/artcraft-vs-stability-ai-image.md)
- [Black Forest Labs FLUX API vs Iris-3B](https://www.anchorterminal.com/compare/black-forest-labs-vs-iris-3b.md)
- [Bria API vs Iris-3B](https://www.anchorterminal.com/compare/bria-vs-iris-3b.md)
- [fal image models vs Iris-3B](https://www.anchorterminal.com/compare/fal-image-vs-iris-3b.md)
- [Google Imagen vs Iris-3B](https://www.anchorterminal.com/compare/google-imagen-vs-iris-3b.md)
- [Ideogram API vs Iris-3B](https://www.anchorterminal.com/compare/ideogram-vs-iris-3b.md)
- [Iris-3B vs Leonardo.Ai API](https://www.anchorterminal.com/compare/iris-3b-vs-leonardo-ai.md)
- [Iris-3B vs OpenAI Image API](https://www.anchorterminal.com/compare/iris-3b-vs-openai-image-api.md)
- [Iris-3B vs Qwen-Image 2.1 (Model Studio)](https://www.anchorterminal.com/compare/iris-3b-vs-qwen-image-2-1.md)
- [Iris-3B vs Recraft API](https://www.anchorterminal.com/compare/iris-3b-vs-recraft.md)
- [Iris-3B vs Replicate image models](https://www.anchorterminal.com/compare/iris-3b-vs-replicate-image.md)
- [Iris-3B vs Seedream on BytePlus ModelArk](https://www.anchorterminal.com/compare/iris-3b-vs-seedream-on-byteplus-modelark.md)
- [Iris-3B vs Stability AI Image API](https://www.anchorterminal.com/compare/iris-3b-vs-stability-ai-image.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp