Features
No-code app builder from ComfyUI workflows
Serverless API deployment with autoscaling
Flexible GPU selection (T4, L4, A10G, L40S, A100, H100, H200, B200)
Custom environments (e.g., SageAttention, specific Transformers)
Memory Snapshot reduces cold starts by 3-5x
Access to latest models (Sora, Veo 3, GPT Image 1, Wan 2.2, Flux Pro)
Private model upload and sharing
Role-based access and shared workspaces
Full audit trails and zero data retention
On-premises / private deployment (Enterprise)
S3 integration for inputs/outputs (Enterprise)
White label for custom branding (Enterprise)
Built-in usage analytics and tracking
Supports any public or private ComfyUI node pack
GPU compute billed per active second
Sketch-to-image diffusion generation
Optional text prompt for style guidance
Client-side processing via Replicate API
Multiple output variations per sketch
No account or sign-up required
Open-source codebase on GitHub
Real-time preview of generated results
Unlimited free generations
512x512 output resolution
Privacy-focused – no server-side logs
Self-hosting option via GitHub
Lightweight web interface
