Text 2 Video using Wan 2.2
Updated to use Lightning LORA and few other enhancements.
Lightning does a good job of speeding up renders.
https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Wan22-Lightning
Aesthetic improvements with Wan 2.2
Wan2 AI: Next-Gen Image & Video Generation Tool - Wan 2.2 AI
For those experiencing slowness. Try downloading the Q2 GGUF.
Also, you might want to install "Crystools" monitor, this will show you your VRAM usage. You can find this in Comfy manager. Try to keep VRAM usage below 95% so things run smoothly. If you are running at 99%, things usually go bad.
High Noise (select the appropriate sized gguf for your vram)
https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main/HighNoise
Low Noise
https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main/LowNoise
Light2xV Lora
https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v
VAE
https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main/VAE
Description
First release, text to video using Wan 2.2
FAQ
Comments (3)
Wow i don't know what you did here but this produced the best wan 2.2 T2V clip i've produced by far from any workflow i've tested, thanks for sharing this.
Can you please recommend appropriate model size for 12gb vram?
Unfortunately this workflow does not work on 12GB VRAM cards. It takes forever...
[ComfyUI-Manager] All startup tasks have been completed.
got prompt
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Using scaled fp8: fp8 matrix mult: False, scale input: False
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load WanTEModel
loaded completely 9633.8 6419.477203369141 True
gguf qtypes: F16 (694), Q5_K (280), Q6_K (120), F32 (1)
model weight dtype torch.float16, manual cast: None
model_type FLOW
Requested to load WAN21
0 models unloaded.
loaded partially 128.0 127.998046875 0
Initializing block swap: 100%|█████████████████████████████████████████████████████████| 40/40 [00:04<00:00, 8.50it/s]
Attempting to release mmap (320)
Patching comfy attention to use sageattn
0%| | 0/4 [00:00<?, ?it/s]
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.