jinx/ComfyUI
1
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-08-03 07:26:31 +08:00
Code Issues Activity

Nodes to properly use the SDV img2vid checkpoint.

Browse Source 
The img2vid model is conditioned on clip vision output only which means
there's no CLIP model which is why I added a ImageOnlyCheckpointLoader to
load it. Note that the unClipCheckpointLoader can also load it because it
also has a CLIP_VISION output.

SDV_img2vid_Conditioning is the node used to pass the right conditioning
to the img2vid model.

VideoLinearCFGGuidance applies a linearly decreasing CFG scale to each
video frame from the cfg set in the sampler node to min_cfg.

SDV_img2vid_Conditioning can be found in conditioning->video_models
ImageOnlyCheckpointLoader can be found in loaders->video_models
VideoLinearCFGGuidance can be found in sampling->video_models
This commit is contained in:
comfyanonymous
2023-11-23 19:43:09 -05:00
parent 871cc20e13
commit 42dfae6331
2 changed files with 90 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
nodes.py
View File

@@ -1850,6 +1850,7 @@ def init_custom_nodes():
"nodes_model_advanced.py",
"nodes_model_downscale.py",
"nodes_images.py",
"nodes_video_model.py",
]
for node_file in extras_files: