Ethanfel/ComfyUI-SelVA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add fps input to PrismAudioFeatureExtractor

Browse Source 
Exposes the video frame rate as an optional input (default 30).
Correct FPS ensures accurate temporal frame sampling in VideoPrism
and Synchformer feature extraction.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Ethanfel
2026-03-27 20:08:10 +01:00
parent c416045ace
commit f32456a142
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nodes/feature_extractor.py
+3 -2
View File
@@ -120,6 +120,7 @@ class PrismAudioFeatureExtractor:
"caption_cot": ("STRING", {"default": "", "multiline": True, "tooltip": "Chain-of-thought description"}), "caption_cot": ("STRING", {"default": "", "multiline": True, "tooltip": "Chain-of-thought description"}),
}, },
"optional": { "optional": {
"fps": ("FLOAT", {"default": 30.0, "min": 1.0, "max": 120.0, "step": 0.001, "tooltip": "Frame rate of the input video. Match this to your source (e.g. 24, 25, 30, 60). Affects temporal sampling in feature extraction."}),
"python_env": ("STRING", {"default": "python", "tooltip": "Path to python binary with JAX/TF. Leave as 'python' to auto-install a managed venv on first use."}), "python_env": ("STRING", {"default": "python", "tooltip": "Path to python binary with JAX/TF. Leave as 'python' to auto-install a managed venv on first use."}),
"cache_dir": ("STRING", {"default": "", "tooltip": "Directory to cache extracted features. Empty = temp dir"}), "cache_dir": ("STRING", {"default": "", "tooltip": "Directory to cache extracted features. Empty = temp dir"}),
"synchformer_ckpt": ("STRING", {"default": "", "tooltip": "Path to synchformer checkpoint (auto-resolved if empty)"}), "synchformer_ckpt": ("STRING", {"default": "", "tooltip": "Path to synchformer checkpoint (auto-resolved if empty)"}),
@@ -131,7 +132,7 @@ class PrismAudioFeatureExtractor:
FUNCTION = "extract_features" FUNCTION = "extract_features"
CATEGORY = PRISMAUDIO_CATEGORY CATEGORY = PRISMAUDIO_CATEGORY
def extract_features(self, video, caption_cot, python_env="python", cache_dir="", synchformer_ckpt=""): def extract_features(self, video, caption_cot, fps=30.0, python_env="python", cache_dir="", synchformer_ckpt=""):
# Resolve python binary — auto-install managed venv if using default # Resolve python binary — auto-install managed venv if using default
if python_env == "python": if python_env == "python":
python_env = _ensure_extract_env() python_env = _ensure_extract_env()
@@ -152,7 +153,7 @@ class PrismAudioFeatureExtractor:
# Save video to temp file # Save video to temp file
with tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) as tmp: with tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) as tmp:
tmp_video = tmp.name tmp_video = tmp.name
_save_video_tensor_to_mp4(video, tmp_video) _save_video_tensor_to_mp4(video, tmp_video, fps=fps)
# Build subprocess command # Build subprocess command
script_path = os.path.join( script_path = os.path.join(
workflows/video_to_audio.json
+1 -1
View File
@@ -50,7 +50,7 @@
{"name": "features", "type": "PRISMAUDIO_FEATURES", "links": [4], "slot_index": 0} {"name": "features", "type": "PRISMAUDIO_FEATURES", "links": [4], "slot_index": 0}
], ],
"properties": {"Node name for S&R": "PrismAudioFeatureExtractor"}, "properties": {"Node name for S&R": "PrismAudioFeatureExtractor"},
"widgets_values": ["describe the video in detail", "python", "", ""] "widgets_values": ["describe the video in detail", 30.0, "python", "", ""]
}, },
{ {
"id": 4, "id": 4,