WAN 2.2 5B Model
Do not expect this to work with most LoRAs.
Recommended settings:
CFG 3.5
FPS 24
GGUF Quant of base model of Wan2.2 TI2V 5B
Capable of T2V and I2V
Original Model: https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B
YOU are responsible for outputs as always! If you make ToS violating content and I get aware I WILL report this.
Description
FAQ
Comments (4)
Rtx3060 12Gb gguf version VAE decoding takes forever with new VAE 2.2 and don't know why (without Loras). When add Loras I got hundred of errors. Also most people say 5b model has worse quality then old 1.3b...
I'm having trouble getting this to work. What Text Encoder and VAE do I use for the Q6 version (and the Q8)? Thanks.
Hello decoding is fast ?
hi. how it work ? any workflow?i can not find any workflow that show how GGUF setup in it.
Details
Files
wan22TI2V5BGGUF_q8.gguf
Mirrors
Wan2.2-TI2V-5B-Q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
wan2.2-ti2v-5b-q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
wan2.2-ti2v-5b-q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
Wan2.2-TI2V-5B-Q8_0.gguf
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.