Image model · Available as managed deployment
Qwen-Image — generation with strong legible in-image text, plus instruction editing via Qwen-Image-Edit — validated on AxForge hardware and available as a managed deployment on a dedicated European system for your traffic only. Generation and editing from one model family, on one machine you rent.
Why AxForge
| Generation and editing, one family | Strong legible in-image text and high-quality generation, plus instruction editing via Qwen-Image-Edit — OpenAI-compatible /v1/images/generations and /v1/images/edits on your machine. |
|---|---|
| Validated in production | This is the model that served the serverless API's generation until AxForge's seed-matched bake-off replaced it with ERNIE Image Turbo — validated on AxForge nodes through 2026-08, Apache 2.0 open weights. |
| Your model, your traffic, our hardware | On a dedicated system in Málaga, Spain (eu-es-1), prompts and images are processed in memory — not written to disk, not logged, not retained, never used to train. |
Specifications
| Model | Qwen-Image — generation + instruction editing (Qwen-Image-Edit), strong in-image text |
|---|---|
| License | Apache 2.0 (open weights) |
| Endpoint | OpenAI-compatible /v1/images/generations and /v1/images/edits on your machine |
| Hardware | Your own NVIDIA DGX Spark (GB10, 128 GB unified memory) |
| Rental term | Hour, week, month or year |
| Hardware pricing | €0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT |
| Managed service | Quoted per deployment |
| Region | Málaga, Spain (eu-es-1) |
Full details, benchmarks and FAQ on the Qwen-Image page. Prices exclude VAT.
How it works
| 1 | Request deployment — describe your generation and editing volume and rental term. |
|---|---|
| 2 | You receive the configuration, hardware rental and managed-service price in writing before anything is billed. |
| 3 | AxForge deploys Qwen-Image on a dedicated DGX Spark reserved for you. |
| 4 | Point your OpenAI SDK at your own /v1/images/generations and /v1/images/edits. |
| 5 | Adjust the term — hour, week, month or year — as your workload settles. |
Request deployment or sign in to start.
FAQ
Not on the serverless API — there, generation runs on ERNIE Image Turbo and editing on FLUX.2 Klein 4B, both picked in seed-matched bake-offs on AxForge hardware. Qwen-Image is available as a managed deployment on a dedicated system for your traffic only.
Strong legible in-image text and high-quality generation, plus instruction editing via Qwen-Image-Edit. A dedicated deployment gives you both on your own machine.
A DGX Spark (GB10, 128 GB unified memory) in an EU region running Qwen-Image for only your traffic, rented by the hour, week, month or year, with an OpenAI-compatible endpoint. The managed service is quoted per deployment.
Two parts: the DGX Spark hardware rental — by the hour, week, month or year, with longer terms earning the lower rate — and the managed service, quoted per deployment. Both are confirmed in writing before anything is billed.
No. Prompts and images are processed in memory in the EU, never persisted or used for training. Only request metadata is kept for billing and operations.