WAN 2.2
This one is pretty damn good if I do say so myself. Swapped out some of the other LoRAs for WAN 2.2 in my tests and this v2 blows them all away. Your results may vary, so look at the showcase prompts for help. This can create videos or images of male from a prompt, in realistic detail. It can also preserve the if they are in your start frame for image to video workflows. Detailed prompting helps, see showcase for v1 and v2 for example prompts, or use local LLM Qwen VL or Grok for help with terms.
And it knows this time. No other LoRAs were used for showcase videos except for Lightx2v. For the , describe how much and exact details of where it goes. Beware saying 'massive ' or you'll get a firehose like velocity and volume shooting out (see showcase).
You need both the high and low models in your workflows for video creation. The high noise model has its own version tab instead of the Required Components panel I orginally used. That would prohibit it from being used to generate videos with high+low loras on this site. The high noise part gets the motion, and low noise gets the details.
You can use the low noise with WAN 2.1 or its variants such as the SCAIL-2 or one of my favorites, Bindweave. You can create very high resolution images also the t2v model or with Magic WAN that are quite good (see showcase).
See showcase for prompts and workflows should be embedded in most mp4 files. I try to put the technique in them, t2v, or i2v. Some use RIFE or FILM interpolation for the frame rate and TensorRT or Nvidia RTX image scaling as well to get beyond 480p/720p. If there are some you like and the workflow is not available, let me know.
Check out where you can see my latest work and follow me for free.
v2
Built on v1, adding 60 videos and the latest image dataset with the goal to fix the backwards or upside-down . It still can produce backwards , but before it would do it 90% of the time when viewing the underside of the , and now completely opposite, failing about 10% of my tests. Prompts can help if you get that. use 'detailed defined '. I guess it's hard to get rid of all the backwards heads in this world. Trained to a total of 15k steps, 20 hours of additional GPU time for version 2, stopping and adjusting along the way. Loads of work
v1
Trained on the same dataset as versions 1 of my Z-Image Turbo and LTX-2 LoRA, but for WAN 2.2 trained with the T2V model, which can be used to generate from your detailed prompt, or keep them in your scene if using i2v workflow.
Description
WAN 2.2
This one is pretty damn good if I do say so myself. Swapped out some of the other LoRAs for WAN 2.2 in my tests and this v2 blows them all away. Your results may vary, so look at the showcase prompts for help. This can create videos or images of male from a prompt, in realistic detail. It can also preserve the if they are in your start frame for image to video workflows. Detailed prompting helps, see showcase for v1 and v2 for example prompts, or use local LLM Qwen VL or Grok for help with terms.
And it knows this time. No other LoRAs were used for showcase videos except for Lightx2v. For the , describe how much and exact details of where it goes. Beware saying 'massive ' or you'll get a firehose like velocity and volume shooting out (see showcase).
You need both the high and low models in your workflows for video creation. The high noise model has its own version tab instead of the Required Components panel I orginally used. That would prohibit it from being used to generate videos with high+low loras on this site. The high noise part gets the motion, and low noise gets the details.
You can use the low noise with WAN 2.1 or its variants such as the SCAIL-2 or one of my favorites, Bindweave. You can create very high resolution images also the t2v model or with Magic WAN that are quite good (see showcase).
See showcase for prompts and workflows should be embedded in most mp4 files. I try to put the technique in them, t2v, or i2v. Some use RIFE or FILM interpolation for the frame rate and TensorRT or Nvidia RTX image scaling as well to get beyond 480p/720p. If there are some you like and the workflow is not available, let me know.
Check out where you can see my latest work and follow me for free.
v2
Built on v1, adding 60 videos and the latest image dataset with the goal to fix the backwards or upside-down . It still can produce backwards , but before it would do it 90% of the time when viewing the underside of the , and now completely opposite, failing about 10% of my tests. Prompts can help if you get that. use 'detailed defined '. I guess it's hard to get rid of all the backwards heads in this world. Trained to a total of 15k steps, 20 hours of additional GPU time for version 2, stopping and adjusting along the way. Loads of work
v1
Trained on the same dataset as versions 1 of my Z-Image Turbo and LTX-2 LoRA, but for WAN 2.2 trained with the T2V model, which can be used to generate from your detailed prompt, or keep them in your scene if using i2v workflow.