Supported now: SDXL for image generation — Upscale for upscale workflows. Not supported yet: SDΒ 1.5 and FLUX. Distilled SDXL variants (Turboβ―/β―Lightning) may work but need lower CFG and fewer steps.
AI detection: mask generated from Detection Prompt using SAM + GroundingDINO β no painting needed.
βΈ Advanced Mask Controls
Outpaint Padding (leave 0 for pure inpaint)
Estimate
Max VRAM
β
Gen Time
β
Price
β
No queue time included
Weekly allowanceβ / 2000 V
This job costsβ
Remaining afterβ
Resets inβ
Advanced Controlsexpand
Model Slots
Parameters
Video Settings
LoRA Strengths
Refiner
Import / Export Settings
Recent Jobs
No jobs yet
Browse Models
Models are filtered by Base Model when selecting in templates. SDXL 1.0 templates show only SDXL models; WAN Video templates show only WAN models. Models with no Base Model set are shown in all templates.
Register Model
First Version
LoRA Defaults
Bulk Register
Quickly register multiple versions. Model is auto-created from name.
My Models
Your registered models β manage versions, edit metadata, or delete.
Register Model
First Version
LoRA Defaults
Loadingβ¦
Workflow Templates
Reusable generation blueprints used by Style Packs. Each template defines the model slots, task type, and internal workflow.
Currently active: The live generation stack is SDXL-based. FLUX and SDΒ 1.5 are not supported by the current frontend workflows.
No Style Packs yet β create one below
Style Packs combine a workflow template, selected models, and default generation settings
Create Style Pack
Generation Parametersdefaults applied when this style pack is used
LoRA Strengths
Refiner
Save the style pack first, then add preview images.