Description:
This workflow allows you to generate video from text.
You will find a step-by-step guide to using this workflow here: link
My other workflows for WAN: link
Resources you need:
📂Files :
For base version
T2V Model: fp16, fp8
In models/diffusion_models
For GGUF version
T2V Quant Model: Q8, Q5, Q3
In models/diffusion_models
Common files :
CLIP: umt5_xxl_fp8_e4m3fn_scaled.safetensors
in models/clip
VAE: wan_2.1_vae.safetensors
in models/vae
Speed LoRA: lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16.safetensors
in models/loras
ANY upscale model:
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in models/upscale_models
📦Custom Nodes :
Description
The main purpose of this update is to fix incompatibility issues with newer versions of ComfyUI.
I haven't added any new features, and if the older version works for you, there's no need to change it.
I also took the opportunity to simplify some functions and integrate the subgraph function to make editing easier.
FAQ
Comments (2)
In v1.0 and v1.1 there was a "Schedular" node with "Schedular" and "Denoise" parameters, but they were removed in the next versions - I need to specify denoise, but I can't do it in v3.0 - am I missing something? Also in v3.0 the preview is also removed, I wonder why - it's very useful.
I have a problem: the video I get doesn't change when I change the prompt after I run this one time, also, the new video has a lot of noise. I need to restart comfy-ui if I want to create a video with a new prompt.