Up to 4K resolution
Generate images up to 4096×4096 with photorealistic detail.
Consistent identity
Maintain character, scene, and product identity across multiple generations.
Style control
Reference images, style transfer, color palette, and lighting control.
Standard API
OpenAI-compatible /v1/images/generations endpoint.
Edit & refine
Inpainting, outpainting, and instruction-based editing.
Fast at scale
1.4s P50 for 1024×1024. Burst capacity for product launches.
Pricing
Token-efficient, with volume discounts and burn incentives.
P50 1.4s
P50 4.2s
P50 12s
Preserves original regions
Pricing is illustrative. Final rates are governed by on-chain parameters and may vary based on network state.
Staking requirements
Tier-based access. Higher stakes unlock better economics and more capacity.
| Tier | Required stake | Access |
|---|---|---|
| Builder | 50M QUBIC | Image generation enabled |
| Startup | 150M QUBIC | Priority queue, fine-tuning |
| Business | 500M QUBIC | Custom models, brand-safety |
| Enterprise | Custom | On-prem, dedicated capacity |
Example
Drop-in compatible with the OpenAI SDK.
from aigarth import Aigarth
client = Aigarth(api_key="sk-aigarth-...")
response = client.images.generate(
model="aigarth-image-1",
prompt="A botanist in a glass greenhouse, soft morning light, 35mm photograph",
size="1024x1024",
n=4,
)
for i, image in enumerate(response.data):
image.save(f"greenhouse-{i}.png")Enterprise benefits
Everything in the standard tier, plus the things enterprises need.
- Brand-safety filters and content moderation
- Custom model fine-tuning for brand identity
- Watermarking and provenance tracking
- On-prem deployment for IP-sensitive content
- Bulk generation with consistent characters
- Compliance with content policies
- Migration from DALL·E, Midjourney, Stable Diffusion
- Dedicated CSM and quarterly reviews