Added support for fantasyspeaking model

added Phantom model support

added missing file diffusion forcing file

removed test leftover

added missing file diffusion forcing file

Added Preview mode and support Sky Reels v2 Diffusion Forcing

fix flash attention

addded missing recammaster files

Added Recammaster support

Added Low VRAM support for RTX 10XX and RTX 20XX GPUs

Added Vace Sliding Window

Added Vace Inpainting Support and Create a Mask inside WanGP

Code cleaning

Optimized Vace RAM usage

Simplified Vace, added auto open pose and depth extrators

New model selection logic / removed tabs

Added Vac Contronet support

Added Rife Temporal upsampling and Lanczos spatial upsampling

Queue adaptations

Added Fun InP models support

Fixe Star zero bug

Fixe Sage test

Added CFG Zero *

Fixed Sage detection support

RAM optimizations and faster launch

New Multitabs, Save Settings, End Frame

fixed bug with Sage2 sm86 architecture

This UI color is the good one + slightly reduced VRAM when using Sage2 attention

Lora festival part 2, new macros, new user interface

Lora fest + Skip Layer Guidance

Refactored Loras

Add skip layer guidance

Added 10% boost, improved Loras and Teacache

Fixed pytorch compilation

Fixed Flash attention

Added support for multiple input images

Implemented VAE tiling

Added TeaCache support

Fix pb with Sage1

RIFLEx support

RIFLEx support

Added RIFLEx support

beta version

Update text2video.py to reduce GPU memory by emptying cache (#44)

init upload