Evidence tier Source Confirmed · 8 captures on record
What the publisher says
As described on Microsoft Marketplace.
Fooocus is a pre-configured AI image generation platform based on Stable Diffusion XL. It delivers a Midjourney-like experience — just type a prompt and get high-quality images. No complex workflows, no parameter tuning, no machine learning expertise required. This VM image comes with Fooocus, NVIDIA GPU drivers, Docker, and all dependencies pre-installed and ready to run.
Setting up AI image generation on cloud GPUs typically requires hours of manual configuration — installing NVIDIA drivers, CUDA, Python dependencies, and troubleshooting compatibility issues. Fooocus on Azure eliminates this entirely. Deploy the VM, open your browser, and start generating. No DevOps expertise needed.
Show the rest of the publisher’s description (17 more lines)
Unlike subscription-based services like Midjourney, you maintain full control of your environment and data. Pay only for the GPU hours you use, with no per-image fees or monthly generation limits.
Fooocus is ideal for designers and creatives who need AI-generated images without learning complex tools, marketing teams producing visual content at scale, developers building AI-powered products who need a ready-to-deploy backend, and agencies offering AI art services who want a private, self-hosted solution.
Key Features
- Text-to-image with built-in GPT-2 prompt enhancement for beautiful results from simple prompts
- Image upscaling (1.5x and 2x) with AI-powered detail enhancement
- Inpainting and outpainting using Fooocus's custom algorithm
- Image prompts for style and composition guidance
- Face swap via InsightFace integration
- Multiple style presets including Default, Anime, and Realistic modes
- Web UI accessible on port 7865 — no SSH required
Getting Started
- Deploy this image on a supported GPU VM (NC-series T4 recommended)
- Open your browser to http://<vm-public-ip>:7865
- Start generating images
Recommended VM Sizes
- Standard_NC4as_T4_v3 — 4 vCPUs, 28GB RAM, NVIDIA T4 16GB (best value)
- Standard_NC8as_T4_v3 — 8 vCPUs, 56GB RAM, NVIDIA T4 16GB
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Sources
Publisher resources
1 linkLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.