Wan 2.2 Notes - This model works very well with Wan 2.2.

These are the settings that have worked well for me and produce amazing results in Wan 2.2 at high resolutions.

High noise LoRAs

• BustySigrid: 0.9 - 1.10

• Breast Squeeze and Lactation: 0.50

• either one of these

  • Wan21_CausVid_14B_T2V_lora_rank32_v2: 1.00

  • lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank32_bf16: 3.00

Low noise LoRAs

• BustySigrid: 0.90 - 1.10

• Breast Squeeze and Lactation: 0.50

• BoobPhysics, latest version: 1.50

• BouncyWalk: 0.50

• Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32: 1.00

CFG at 1.0, render for 6 steps. 3 steps each for high and low noise.

The "Breast Squeeze" lora is great for scenes where she is handling her own breasts. If you don't specify milk and lactation, you won't get any of that, it just improves the motion of the squeezing. The Breast Physics and BouncyWalk LoRAs are most useful in the Low Noise render. In my experience, they don't have much effect on the High Noise render. For lightning render speed, the High Noise render can use either the latest CausVid (versoin 2) or the latest release of lightx2v (version 2). They produce equally good but different results in my testing. Try out both at low resolutions and see what you prefer. The Low Noise render seems to do best with the older lightx2v (version 1). I like the "rank32" version better than "rank??" in my videos, but you may have a different opinion.

Sigrid is a busty blonde woman who started as a Flux character model (https://civitai.com/models/1337046) and now she is ready for her debut as a video character with Wan. Note: The BustySigrid Flux model has been updated using the same training images as this Wan model. So if you want to generate images with Flux and do image-to-video, you can get consistent results either way.

Important: This model is 100% fictitious and is not based on images of any real person. She originated with images generated from still image checkpoints and has evolved from there using only AI rendering. No images (neither actual nor AI-generated) of any real person was ever involved in the making of this model.

This is a Text-to-Video LoRA, so I can't promise quality results if you try to use it with Image-to-Video instead.

Sigrid appears to mix well with other Wan LoRAs and can be rendered at different resolutions (tested at 320x320, 320x480, 480x720, ??0x??0, 720x720, and ??0x960). Wan videos can be a little stiff, so I recommend pairing this LoRA with other motion enhancers like Bouncy Walk (https://civitai.com/models/1361346). Some of her training images were ???????, so she looks good with her shirt off, too.

For prompt tips, see the sample videos. I added the full prompt text to each video and the ComfyUI workspace is embedded in each video as well.

The Wan settings I used for the sample videos are:

• LoRA strength: 0.75 to 1.0

• Frames: 81

• Steps: 25-30 (at 20 steps, the quality was noticeably worse)

• cfg: 3.0 - 6.0

• Sampler: uni_pc_bh2

• Scheduler: simple

I used frame interpolation to add intermediate frames just to smooth out the video. No upscaling was used for the sample videos.

I hope you enjoy making movies with Sigrid. If you make videos you like, please either post them to this page or mark this LoRA as a resource when you post your clip. I always like seeing what other people make with my models.