Loading
Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
Generate a short silent video from a scene and motion description using Kandinsky 5 Lite's fixed 5-second text-to-video model.
Bring this Pipe into Studio
Add to Studio uses this exact version. New releases do not replace a saved copy automatically.
Workflow details
Laufzeitprofil
Quellen
1 QuelleHover nodes for Pipe controls
Core
Primary Pipe surface
Positive prompt
CLIPTextEncode
Negative prompt
CLIPTextEncode
Video shape
Kandinsky5ImageToVideo
Extended
Additional surfaced controls
Playback
CreateVideo
Sampling
KSampler
Noise schedule
ModelSamplingSD3
Video encoding
SweetTeaPreviewVideo
Hardware and download-size estimates are not available yet.
Anforderungen
Text encoder · Hugging Face · comfyanonymous/flux_text_encoders · Flux Text Encoders
hunyuan_video_vae_bf16.safetensors
Datei ungeprüftVAE · Hugging Face · Kijai/HunyuanVideo_comfy · HunyuanVideo Comfy
kandinsky5lite_t2v_sft_5s.safetensors
Datei ungeprüftCheckpoint · Hugging Face · kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s
qwen_2.5_vl_7b_fp8_scaled.safetensors
Nicht aufgelöstText encoder · Hugging Face · Comfy-Org/HunyuanVideo_1.5_repackaged
Knotenpaket · GitHub · tea-time-labs/sweet-tea-nodes
