ComfyUI-FramePackWrapper_Plus

DownloadAndLoadFramePackModel

No hay una descripción breve disponible para este nodo.

FramePackWrapper · 1 entrada · 4 parámetros · 1 salida

FramePackFindNearestBucket

Finds the closes resolution bucket as defined in the orignal code

FramePackWrapper · 1 entrada · 1 parámetro · 2 salidas

FramePackLoraSelect

Select a LoRA model from ComfyUI/models/loras

FramePackWrapper · 1 entrada · 3 parámetros · 1 salida

FramePackSampler

No hay una descripción breve disponible para este nodo.

FramePackWrapper · 8 entradas · 14 parámetros · 1 salida

FramePackSampler_F1

The main generation node using the F1 sampling technique. Inputs: - model: The loaded FramePack model - positivetimeddata: Timestamped positive prompts - negative: Negative prompt conditioning - startlatent: Initial latent for generation - startimageembeds: CLIP Vision embeddings for start image - endlatent: (Optional) End latent for transitions - endimageembeds: (Optional) CLIP Vision embeddings for end image - initialsamples: (Optional) For video-to-video generation - Various sampling parameters (steps, CFG, guidance scale, etc.)

FramePackWrapper · 8 entradas · 12 parámetros · 1 salida

FramePackTimestampedTextEncode

Encodes text prompts with timestamps for timed conditioning. Inputs: - clip: CLIP text model - text: Text prompt with timestamps - negativetext: Negative prompt - totalsecondlength: Video duration in seconds - latentwindowsize: Processing window size - promptblendsections: Number of sections to blend prompts

FramePackWrapper/Experimental · 1 entrada · 5 parámetros · 2 salidas

FramePackTorchCompileSettings

torch.compile settings, when connected to the model loader, torch.compile of the selected layers is attempted. Requires Triton and torch 2.5.0 is recommended

HunyuanVideoWrapper · 0 entradas · 7 parámetros · 1 salida

LoadFramePackModel

No hay una descripción breve disponible para este nodo.

FramePackWrapper · 2 entradas · 5 parámetros · 1 salida