Downloads · 30 days
0
RAPID-AIO-FP16
TekeshiX/RAPID-AIO-FP16
RAPID-AIO-FP16 is a machine learning model from TekeshiX. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Access
Public
Updated Aug 7, 2025
Repo size
178 GB
Likes
27
Public
Repo makeup
Click a slice to open those files.
.safetensors178 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 6, 2025
- Updated
- Aug 7, 2025
- SHA
- 1fba199d
Model card
From the Hugging Face model README
ALL THE MODELS ARE IMAGE2VIDEO ONLY.
These models are merges between WAN 2.1 and WAN 2.2 -> both 720p 14B FP16:
- WAN2.2-RAPID_AIO_I2V_ACCELERATORS-LoRAs_FP16.safetensors -> this has the 2 accelerators LoRAs injected (lightx2v+pusa) so you can use as low as 4 steps.
- WAN2.2-RAPID_AIO_I2V_FP16.safetensors -> this doesn't contain any accelerators LoRAs, looks more like the original WANs.
These models are merges between Skyreels V2 and WAN 2.2 -> both 720p 14B FP16:
- WAN2.2-WITH_SKYREELS_RAPID_AIO_I2V_ACCELERATORS-LoRAs_FP16.safetensors -> this has the 2 accelerators LoRAs injected (lightx2v+pusa) so you can use as low as 4 steps.
- WAN2.2-WITH_SKYREELS_RAPID_AIO_I2V_FP16.safetensors -> this doesn't contain any accelerators LoRAs, looks more like the original WANs.
The merging workflow was provided by @Phr00t (https://huggingface.co/Phr00t). I told him to download these models and upload them to his official repo as I'm not looking to take any credits!
Good luck have fun!
- Created
- Aug 6, 2025
- Updated
- Aug 7, 2025