clipproj4b-fl2va v2: split projection — vision rows through a vision-fitted map, faces hold

images: 4x face-crop A/B panels, clipproj v1 vs v2

images: 4x face-crop A/B panels, clipproj v1 vs v2

images: 4x face-crop A/B panels, clipproj v1 vs v2

images: 4x face-crop A/B panels, clipproj v1 vs v2

images: clipproj v1 vs v2 face A/B frames

images: clipproj v1 vs v2 face A/B frames

clipproj + fl2va in one 14.5 GB file: the 4B tower and the VAE encoder join the compact build; first-frame conditioning verified frame-for-frame

ClipProj 4B prompt encoder: 25.20 GB -> 14.13 GB, everything still q4tp

samples: ClipProj 4B variant, same prompt and seed as the q4tp/q2tp A-B

samples: ClipProj 4B variant, same prompt and seed as the q4tp/q2tp A-B

samples: ClipProj 4B variant, same prompt and seed as the q4tp/q2tp A-B

Upload mmh3-turbo-fl2va-q2tp.cmf with huggingface_hub

Upload samples/ab_q4tp.mp4 with huggingface_hub

Upload samples/ab_q2tp.mp4 with huggingface_hub

Upload samples/ab_q2tp.gif with huggingface_hub

Upload samples/ab_q4tp.gif with huggingface_hub

Upload mmh3-turbo-fl2va-q4tp.cmf with huggingface_hub

Upload samples/i2v_keyframe.ppm with huggingface_hub

Upload samples/i2v_corgi_flip.wav with huggingface_hub

Upload samples/i2v_corgi_flip.avi with huggingface_hub

Upload samples/i2v_corgi_flip.mp4 with huggingface_hub

Upload samples/i2v_corgi_flip.gif with huggingface_hub

Upload samples/corgi_512x288_4step.gif with huggingface_hub

Upload samples/corgi_512x288_4step.mp4 with huggingface_hub

Upload mmh3-turbo-q4tp.cmf with huggingface_hub

Upload samples/corgi_512x288_4step.wav with huggingface_hub

Upload samples/corgi_512x288_4step.avi with huggingface_hub

initial commit