This repository does not expose a bounded model card.
TalmajM
Edit source images with a validated ComfyUI workflow family. Estimated setup is about 20 minutes, with no local installation. From $0.25/hour.
Validated runtime
Architecture and task checked
Immutable revision
312bb02464
Dedicated workload
Isolated model endpoint
You control runtime
Runs until you stop it
The outcome
LongCat-Image-Edit_ComfyUI_repackaged is a validated image editing model.
GPU Vault admits only generated-registry repositories whose exact component paths and hashes match a pinned official ComfyUI core-node workflow.
The model launches in a persistent authenticated ComfyUI workspace. Download outputs before stopping the workload because workspace files are deleted during teardown.
Example workflows
Build and refine media with an editable node graph.
Adjust the bundled starter workflow for your project.
Queue prompts through the authenticated ComfyUI API.
Results depend on the model, prompt, sampling settings, and publisher guidance.
Recommended hardware
We run this on
1× GPU · 24 GB VRAM
This is the smallest supported topology with enough memory for the model weights, runtime overhead, and the validated context window. GPU Vault also reserves 47 GB for the immutable model files and engine data.
The compatibility classifier uses safetensors metadata, engine overhead, context memory, and tensor-parallel divisibility. It rejects unsupported architectures and models that need more than eight GPUs.
Transparent usage
Current public starting rate
$0.25/hour
The dashboard shows your exact role-based rate and live offer before approval.
There is no fixed serving duration. Billing follows active compute time from instance creation through teardown.
Review the exact GPU, base compute rate, setup estimate, and initial wallet hold. No credits are reserved from this public page.
Choose your workflow
Start from the GPU Vault core-node workflow and keep full graph control.
Available after the model passes its readiness check.
Use the short-lived direct ComfyUI API credential from the workload page.
Rotate or revoke the workload key at any time.
Exact profile
Keep exploring
From TalmajM
This repository does not expose a bounded model card.
Common questions
Outputs stay on the GPU instance. Download anything you need before Stop or teardown; GPU Vault does not copy catalog workspace files into Supabase storage.
No. GPU Vault uses a fixed server-owned runtime configuration and the model’s immutable revision. Select a live GPU offer, explicitly approve the launch, and wait for the readiness check.
The workspace runs until you stop it, with the approved rate protected by your initial and rolling wallet holds. If the runtime image cannot download before ComfyUI becomes ready, GPU Vault records zero customer usage and returns the complete hold after confirmed teardown.
Approval revalidates the exact model profile, GPU offer, rate, wallet, and operational gates. If a customer-visible model or offer changes before launch, GPU Vault requires a fresh review.
GPU Vault records only endpoint, status, latency, and byte-count metrics for inference requests. Prompt content, documents, embeddings, and generated output are not persisted by the inference proxy.
Ready when you are
Choose an exact live offer, review the rate and wallet hold, then approve the launch from your dashboard.