Fast interactive video character replacement: upload, mark two points, pick a reference.
ComfyUITemplates.com
Discover free ready-made ComfyUI templates for AI workflows.
Artifact-free native 4K+ image generation with FLUX via direct UNet patching through DyPE.
Wan 2.2 text-to-image with fast render and cinematic color science for vivid film-like output.
WAN 2.2 image-to-video with ultra-smooth motion, smart prompt extension, cinematic color.
Swap any character in a video with a reference image and two points; Reactor refines the face.
Pose-transfer a video onto an image or swap a character in, with DWPose, Sam2, and Reactor.
Cinematic HD text-to-video with WAN 2.2 V2: prompt extension, color grading, fast render.
Wan 2.2 + Light2X turns one image into a 32fps video in 4 steps with a multi-LoRA loader.
RealESRGAN 2x video upscaler; monitor logs and anticipate long processing times.
Ultra-fast 2x and 4x video upscaling that preserves motion and detail.
One-step diffusion video upscale to high resolution with adaptive window attention.
Turn photos into Miyazaki-style anime art with a tuned LoRA on SD1.5; bright shots work best.