Lightricks/LTX-2.3 · Distilled v1.1 - Improvements to Audio Quality and a Alightly Refined Visual Aesthetic
Example Workflows: https://github.com/Lightricks/ComfyUI-LTXVideo/tree/master/example_workflows/2.3 [https://github.com/Lightricks/ComfyUI-LTXVideo/tree/master/example_workflows/2.3]
Two Front Doors: Civitai.com, Civitai.red, and What's Next
xmarre/ComfyUI-Image-Conveyor: A Vue-node ComfyUI image queue that lets you drag in unlimited images, organize them visually, and process them sequentially across queued runs.
https://registry.comfy.org/publishers/masternc80/nodes/bboxnodes [https://registry.comfy.org/publishers/masternc80/nodes/bboxnodes]
masternc80/ComfyUI-BBoxNodes: BBoxes (BoundingBoxes) handling and visualization nodes
MajoorWaldi/ComfyUI-Majoor-AssetsManager: Majoor Assets Manager is an advanced asset browser for ComfyUI for managing, organizing, and viewing your generated assets.
The EASIEST Way to Make First Frame/Last Frame LTX 2.3 Videos, Using Custom ComfyUI Nodes!
OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
# Abstract > While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fragmented, and the few existing efforts toward unified video generation still struggle to seamlessly integrate diverse tasks within a single framework. To bridge this gap, we propose OmniWeaving, an omni-level video generation model featuring powerful multimodal composition and reasoning-informed capabilities. By leveraging a massive-scale pretraining dataset that encompasses diverse compositional and reasoning-augmented scenarios, OmniWeaving learns to temporally bind interleaved text, multi-image, and video inputs while acting as an intelligent agent to infer complex user intentions for sophisticated video creation. Furthermore, we introduce IntelligentVBench, the first comprehensive benchmark designed to rigorously assess next-level intelligent unified video generation. Extensive experiments demonstrate that OmniWeaving achieves SoTA performance among open-source unified models. The codes and model have already been publicly available. Project Page: this https URL [https://omniweaving.github.io/]. Paper: https://arxiv.org/abs/2603.24458 [https://arxiv.org/abs/2603.24458] Code: https://github.com/Tencent-Hunyuan/OmniWeaving [https://github.com/Tencent-Hunyuan/OmniWeaving] Models: https://huggingface.co/tencent/HY-OmniWeaving [https://huggingface.co/tencent/HY-OmniWeaving] Project Page: https://omniweaving.github.io/ [https://omniweaving.github.io/]
Even_Adder
Mystic Mushroom [Ze/Zir]
