Stars
ComfyUI DyPE, enabling artifact-free 4K+ image generation for Qwen, Flux + Nunchacku
ComfyUI nodes for Kandinsky 5 DiT. T2V model generates high-quality video with advanced text conditioning.
ComfyUI node for modular, human‑like Kani TTS. Generate natural, high‑quality speech from text
ComfyUI node for highly expressive speech and realistic zero-shot voice cloning
ComfyUI node that generates animated dotted waveform visualizations from audio input with multiple animation styles including teardrop-shaped bars.
ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio
[IEEE TPAMI] A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends
Pre-compiled Python whl for Flash-attention, SageAttention, NATTEN, xFormer etc
ComfyUI node for Fast Video Generation with Magnitude-Aware Cache
ComfyUI Chatterbox TTS & Voice Conversion Node