📄️ Backend V1
BETA
📄️ Face inpainting
Entire picture
📄️ Face Swap
Without face-swap
📄️ FaceID
BETA
📄️ Latent Consistency Models
DPM SDE Karras 30 steps 15 seconds for 8 images
📄️ LoRAs
This feature is mainly relevant for SD15 models. SDXL subject fine-tuning use LoRA, and tend to collide with other style LoRAs
📄️ Multi-Controlnet
Available only for Backend V1
📄️ Multi-Pass inference
BETA
📄️ Multi-Person
BETA
📄️ Prompt Masking
Prompt masking uses a short text to create a mask from the input image. The mask can then be used to inpaint parts of the image. Use the below parameters as part of the prompts to use auto-masking
📄️ Tiled upscale
BETA