Machine DelusionsandClaude Opus 4.6
0bdacabcbd
Vision-language model nodes for ComfyUI using Tencent's Penguin-VL. Includes image query, video query, batch image query, and model loader nodes. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
35 lines
1.3 KiB
Python
35 lines
1.3 KiB
Python
"""
|
|
FL PenguinVL - Vision-Language Model Nodes for ComfyUI
|
|
|
|
Query images and videos with natural language using Tencent's Penguin-VL.
|
|
Supports 2B and 8B model variants with OCR, document analysis,
|
|
visual QA, dense captioning, and more.
|
|
|
|
Model: https://huggingface.co/tencent/Penguin-VL-2B
|
|
Paper: https://github.com/tencent-ailab/Penguin-VL
|
|
"""
|
|
|
|
from .fl_nodes.model_loader import FL_PenguinVL_LoadModel
|
|
from .fl_nodes.image_query import FL_PenguinVL_ImageQuery
|
|
from .fl_nodes.video_query import FL_PenguinVL_VideoQuery
|
|
from .fl_nodes.batch_image_query import FL_PenguinVL_BatchImageQuery
|
|
|
|
NODE_CLASS_MAPPINGS = {
|
|
"FL_PenguinVL_LoadModel": FL_PenguinVL_LoadModel,
|
|
"FL_PenguinVL_ImageQuery": FL_PenguinVL_ImageQuery,
|
|
"FL_PenguinVL_VideoQuery": FL_PenguinVL_VideoQuery,
|
|
"FL_PenguinVL_BatchImageQuery": FL_PenguinVL_BatchImageQuery,
|
|
}
|
|
|
|
NODE_DISPLAY_NAME_MAPPINGS = {
|
|
"FL_PenguinVL_LoadModel": "FL PenguinVL Load Model",
|
|
"FL_PenguinVL_ImageQuery": "FL PenguinVL Image Query",
|
|
"FL_PenguinVL_VideoQuery": "FL PenguinVL Video Query",
|
|
"FL_PenguinVL_BatchImageQuery": "FL PenguinVL Batch Image Query",
|
|
}
|
|
|
|
__version__ = "1.0.0"
|
|
__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]
|
|
|
|
print(f"\n[FL PenguinVL] v{__version__} - Vision-Language Model nodes loaded\n")
|