Automated save/loads. Continue your video from where you stopped, even after comfy restart
Laufzeitprofil
Quellenbeschreibung
Automated save/loads. Continue your video from where you stopped, even after comfy restart
Nearly limitless video length. Easily add new sections to continue your video further, all in single continuous workflow
Change base models for each section. Find which ones work best for your idea
GGUF support for low VRAM systems. Use your GGUF clip and diffusion models like usual models at unified fields
Separable upscale/interpolation. You can stitch a full video purely from saved data, preserving RAM and VRAM, or just generate from the beginning to upscaled video in one go
Even more refined and thoughtful design. Fewer nodes, more capabilities
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
This workflow is for creating segmented videos with Wan Video 2.2 I2V-A14B and SVI 2.0 Pro. It can extend a video with new sections and stitch them into a full video using prompts, segment lengths, seeds, base models, LoRa, and reference images; outputs can include saved video, a
You can save and load video data to continue from where you stopped, including after a ComfyUI restart.
You can add new sections in one continuous workflow and stitch a full video from saved data; upscaling and interpolation can be handled separately at the end.
Each video segment can use its own prompt, length, seed, and reference image.
Different reference images can introduce assets or characters not visible in the starting image, without a LoRa.
The workflow can produce saved video data, a stitched full video, an upscaled video, or an interpolated video.
Version 3.0 requires the custom node pack ComfyUI-HeresyNodes, and the Options subgraph is the starting point for the guide.
Listed model files include clip_l.safetensors; RealESRGAN_x2plus.pth; rife49.pth; umt5_xxl_fp8_e4m3fn_scaled.safetensors; wan_2.1_vae.safetensors; wan_latent.safetensors; and Wan2.1_14B_VACE-Q6_K.gguf.
Other listed model files include wan22_DasiwaI2V14BLightspeed_synthseduction_HIGH_v9.safetensors; wan22_DasiwaI2V14BLightspeed_synthseduction_LOW_v9.safetensors; wan22_smoothMix_V20_HIGH.safetensors; wan22_smoothMix_V20_LOW.safetensors; wan22_SVI_v2_PRO_Wan2.2-I2V-A14B_HIGH_lora
Listed node packs include basic_data_handling; comfy-mtb; ComfyUI_Comfyroll_CustomNodes; comfyui_layerstyle; comfyui_lora_tag_loader; ComfyUI-Crystools; comfyui-dream-project; comfyui-easy-use; comfyui-frame-interpolation; comfyui-gguf; comfyui-impact-pack; comfyui-kjnodes; comfy
Choose a different base model and LoRa for each video section.
The workflow supports GGUF clip and diffusion models for low-VRAM systems.
Before installing, verify the exact file and source for wan_2.1_vae.safetensors, RealESRGAN_x2plus.pth, and rife49.pth.
Vorschlag · nicht geprüft
Before installing, verify the exact pack and source for comfyui_lora_tag_loader and comfyui-gguf.
Vorschlag · nicht geprüft
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
3 AuszügeSource context: 3870 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
6,74 GB über 3 von 13 Modell-Dateien. Gesamtmodell-Dateien + 25% Ladeaufwand + 2 GB Ausführungs-Puffer, aufgerundet.
Anforderungen
29 AnforderungenText encoder · 235 MB · SAFETENSORS · Hugging Face · diamkan/comfyui_oldmodel
Upscaler · Hugging Face · ishaansutaria35/RealESRGAN_x2plus
Checkpoint · Hugging Face · VMTamashii/rife49
Text encoder · 6.27 GB · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · 242 MB · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
wan_latent.safetensors
Nicht aufgelöstCheckpoint · Unknown
Wan2.1_14B_VACE-Q6_K.gguf
Nicht aufgelöstCheckpoint · Unknown
wan22_DasiwaI2V14BLightspeed_synthseduction_HIGH_v9.safetensors
Nicht aufgelöstCheckpoint · Unknown
wan22_DasiwaI2V14BLightspeed_synthseduction_LOW_v9.safetensors
Nicht aufgelöstCheckpoint · Unknown
wan22_smoothMix_V20_HIGH.safetensors
Nicht aufgelöstCheckpoint · Unknown
wan22_smoothMix_V20_LOW.safetensors
Nicht aufgelöstCheckpoint · Unknown
wan22_SVI_v2_PRO_Wan2.2-I2V-A14B_HIGH_lora_rank_128_fp16.safetensors
Nicht aufgelöstLoRA · Unknown
wan22_SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16.safetensors
Nicht aufgelöstLoRA · Unknown
basic_data_handling
Nicht aufgelöstKnotenpaket · Registry
Knotenpaket · Registry
Source context: 3284 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Source context: 3277 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Knotenpaket · Registry
Knotenpaket · Registry
comfyui_lora_tag_loader
MöglichKnotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
comfyui-gguf
MöglichKnotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry