This workflow retrieves the last 15 frames of a video to create a logical sequence, then merges the sequence with your original video.
📂Files :
Recommendation :
>24 gb Vram: base or Q8_0
16 gb Vram: Q5_K_S
<12 gb Vram: Q4_K_S
For base version
VACE Model: wan2.1_vace_14B_fp8_e4m3fn.safetensors or wan2.1_vace_1.3B_fp16.safetensors
In models/diffusion_models
CLIP: umt5_xxl_fp8_e4m3fn_scaled.safetensors
in models/clip
For GGUF version
VACE Quant Model: Wan2.1-VACE-14B-QX_0.gguf
In models/diffusion_models
Quant CLIP: umt5-xxl-encoder-QX.gguf
in models/clip
VAE: wan_2.1_vae.safetensors
in models/vae
ANY upscale model (depreciated):
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in models/upscale_models
📦Custom Nodes :
Description
What's new? :
ComfyUi 0.3.29 positive node fix,
LoRA fix with torch compile.
FAQ
Comments (6)
2.1 all the manual fields have changed to inputs? Example: the Positive Text Node is now a TEXT connection point instead of a text field. Am I missing a update or something else?
Update comfyUI. For portable, go to update folder and then update_comfyui.bat
This kind of problem can occur if your ComfyUI frontend is not up to date. The latest updates break my old workflows, but when I update them, they no longer work for older versions.
Is this any different compared to manually extending from last frame in the normal workflow?
how do u do that ,or u mean download the vid,ss the last frame and introduce it again
is it possible to make a variant with the new vace technology?