Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
Title: CogVideo Workflow for Image-to-Video Creation and Refinement
Profil d'exécution
Description de la source
Title: CogVideo Workflow for Image-to-Video Creation and Refinement
Description: This workflow is tailored for transforming static images into dynamic videos using the CogVideo model. It integrates advanced image conditioning, smooth latent space sampling, and robust video refinement features, enabling creators to generate high-quality video outputs from single or multiple image inputs. Key features include:
Image Input Flexibility : Supports single or start-to-end image sequences as conditioning inputs for video generation.
Dynamic Motion Control : Apply customizable motions like pans, tilts, or zooms to bring static images to life.
Latent Space Sampling : Generate smooth transitions with adjustable frame rates and resolutions using advanced sampling algorithms.
Sources
1 sourceExtraits de sources
1 extraitSource context: 692 downloads · Type Workflows · Base model CogVideoX
Post-Processing Refinements : Includes frame interpolation, color grading, and video stitching tools for a polished final output.
Modular Structure : Easily adaptable for various project needs, from artistic animations to cinematic effects.
This workflow is perfect for creators and designers who want to convert images into professional-quality videos with customizable motions and detailed refinements.
Requirements :
Pre-trained CogVideo model and VAE.
GPU with sufficient resources for high-resolution video generation.
Compatible with CogVideoX version 5b and above.
Transform your images into stunning videos and explore new creative possibilities with this image-to-video solution!
Remaining hardware or download-size estimates are not available yet.
Exigences
VAE · 822 MB · SAFETENSOR · Unknown
film_net_fp32.pt
Non résoluCheckpoint · Unknown
Checkpoint · Hugging Face · kijai/CogVideoX-5b-1.5-I2V
orbit_up_lora_weights.safetensors
Non résoluLoRA · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Unknown
