VNCCS Utils 0.5.3 Adds UniCanvas Infinite Canvas in ComfyUI
VNCCS Utils 0.5.3 brings UniCanvas, an infinite-canvas image generation and editing workspace, to ComfyUI with SAM masking and layer-based editing.
TextMakerPro Adds Layer-Based Text Design to ComfyUI
A new open-source ComfyUI custom node called TextMakerPro brings a layer-based text and layout editor into Stable Diffusion workflows, letting creators design stylized text compositions without leaving ComfyUI.
Control Diffusion Models Without Text Using DINO Reps
A new technique from Linköping University trains diffusion models on DINO self-supervised representations instead of text prompts. The model discovers semantic variation directions in image data without any labels.
MooshieUI Brings ComfyUI to Beginners with Anima Support
MooshieUI is a new ComfyUI frontend that replaces the node graph with a clean three-panel interface. It includes one-click install, 13 model family presets including Anima and Illustrious, and built-in tiled upscaling.
PoseStudio 0.4.19: Mixamo FBX Import and SAM3D Detection
VNCCS PoseStudio 0.4.19 for ComfyUI adds Mixamo FBX animation import, SAM3D body detection from real photos, and an online pose library from Hugging Face. Here is what changed and what it enables.
FLUX.2-klein-9B in ComfyUI: Sub-Second Image Gen
Black Forest Labs' FLUX.2-klein-9B now integrates with ComfyUI via NKD Klein Tools v1.7.0, enabling sub-second image generation with just 4 inference steps on an RTX 4090.
NVIDIA GPU Prices Are Rising: What Creators Must Know
Jensen Huang says older NVIDIA GPUs are appreciating like fine wine as supply tightens. H100, H200, and A100 rental rates are rising. Here is what AI creators need to do now.
PyTorch 2.12: What AI Creators Need to Know
PyTorch 2.12 lands with 5-26% ROCm speedups for AMD GPU creators, CUDA Graph torch.cond support, and MX quantization export. Here is what changes for Stable Diffusion and ComfyUI users.