toyxyz
Follow
Stars
Understand Human Behavior to Align True Needs
ControlNet++: All-in-one ControlNet for image generations and editing!
Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text".
[SIGGRAPH'24] CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization
Diffusers wrapper to run Kwai-Kolors model
Separate audio stems (vocals, bass, drums) from song, recombine, tempo match, slice/crop audio
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, LoRA
The official implement of research paper "MotionBooth: Motion-Aware Customized Text-to-Video Generation"
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
Allows to sample without generating any uncond with Stable Diffusion!
High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
Run Replicate models as nodes in ComfyUI
Tools needed for training B-LoRA method with sd-scripts.
Logic nodes to perform conditional renders based on an input or comparision
This custom node for ComfyUI allows you to create layers of an image based on input masks and save them into a PSD file.
Web interface for querying the LAION-5B dataset using CLIP embeddings.
Modifications to ComfyUI diffusers wrapper node X-Adapter to make it more ComfyUI-node-like
You can using StoryDiffusion in ComfyUI
Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication