Z Image Turbo
Generate high-quality images from text prompts
This is what I am working now
Generate high-quality images from text prompts
generate a video from a text prompt
Note wan2.2 T2V new
app_lora is base
Note wan2.2 I2V LORA
app.py is base
use app_fast.py for fast api works wel and app_t2v is 14B
Note 5B T I T V work very well t2v and i2v fastwan2.2 ==> FastWan2.2-TI2V-diffuser model 5B
generate a video from a text prompt
Note wan T2V
app_low is main
Note CPU prmot e nchancer
Note wan 25
Generate Hollywood Style Actors on your Local Machine
Note exp audio video
wan2_fast.py is wan22, app.py is wan2.1 with light lora
Note more exp with Quick Kiaji other model for wan2.1 T2V testing supports 4 K
generate a video from a text prompt app_aot for imp
Note 5B T I TV
Generate a video from an image with a prompt
Note I2V - Wan Fusion X
Wan2.2 Lora - app.py is base
Note Testing wan2.2 I2V LORA== on hold
Generate a video from two images and a prompt
Note Comfyui on hold for now
Generate a video by interpolating between two images with a prompt
Note with TorcjhAO - ON HOLD NW
Generate realistic audio from video and text
Note video to audio => on hold use when you need audio
use app.py for T2v 14b only
Note Current testing t2V main do not touch. == on hold
Video Analysis
Note video analysic => CPU upgrade run
Image to text
Note describe image to text => no GPU
generate a video from a text prompt
Note this is t2v and I2v test , use for other hack as well on hold GPU
Note L40s this is deepbeepmeep code
Generate videos from text or images
Note Testing original code from wan2.2 repo no GPU
app_t2v is working and app.py is original
Note on hold for now
Demo of Normalized Attention Guidance for 4 steps Wan2.1
Note T2V NAG FuszionX -- on hold for more zerogpu