If it runs locally, it runs on ViewComfy
ViewComfy gives you the same level of freedom as a local ComfyUI setup.
Full access to ComfyUI Manager
Install any public node pack and manage dependencies just like you would locally.
Bring any model
Download models from Hugging Face and CivitAI, or bring your own private models.
Custom environments for complex workflows
Install Python packages, performance optimizations like SageAttention, and private node packs.
A fully flexible and private Comfy cloud environment
ViewComfy runs your workflows in a private, fully featured ComfyUI environment. You don't need to adapt your workflow to the platform.
- Dedicated GPUs per workflow
- Connect your environment to your own s3 bucket
- Optional on-premises or private deployment
Built for teams
ViewComfy makes it easy to collaborate on workflows and share them with non-technical users.
Shared workspaces
Collaborate in shared environments with controlled access to workflows and models.
Roles and permissions
Decide who can edit workflows, manage models, or simply run generations.
Multiple teams with usage tracking
Organize users into teams and monitor usage and spending across projects.
Choose the hardware that fits your workflow
Run your workflows on the GPU that matches your needs, and switch instantly as your requirements change.
| Model | Memory (VRAM) |
|---|---|
| T4 | 16 GB |
| L4 | 24 GB |
| A10G | 24 GB |
| L40S | 48 GB |
| A100-40GB | 40 GB |
| A100-80GB | 80 GB |
| H100 | 80 GB |
| CPU | Physical cores (Up to 8 Cores) |
| Memory | GB (Up to 32GB) |