Mf alone is carrying the whole Wan Loras production on his back! Thank you for what you're doing, bro!

Are you sure your loras work for i2v? the titty drop lora for example got a new i2v lora trained and that works but when I used their old lora trained on t2v it wouldn't work so well in i2v scenarios

from your video example it seems the added genitials are placed a bit too high, it's subtle but that's the impression I have when looking at these

Can I suggest a rename: Flaccid Penis Gigantic Half-Mast Elephant Dick

T2V I2V NOT WORK

most videos start with a grey flash, what's up with that?

IMPORTANT: INFORM ALL WAN USERS! I DISCOVERED HOW TO USE LORAS 'NSFW/SFW' IN WAN 2.2 T2V, GETTING THE FULL POTENTIAL OF "HIGH NOISE" AND "LOW NOISE." THE RESULTS WERE IMPRESSIVE!! I ran it on an RTX 3060 6GB, 32GB RAM, 480x480, length: 41, generation time: 5 minutes to generate each video. The quality is fantastic! For those of you with more powerful computers, the results will be even more incredible. I used the models: WAN 2.2 - Q4_1.gguf FOLLOW THE STEPS BELOW: 1: Don't use acceleration/enhancement LoRas (such as Lightx2v or other) on "high noise"; use only on "low noise" with strength 1. (I'm using this version of Lightx2v LoRa): lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16 2: Use 'NSFW/SFW' LoRas on both "high noise" and "low noise" models. On "high noise," use strength 2, and on "low noise," use half the strength, with strength 1. You can vary the strengths as you like, but always keep the "low noise" strength at half the strength of the "high noise." 3: Use these settings in KSamplers: "high noise": steps: 9 / cfg: 3.5 / euler/simple / start_at_step: 0 / end_at_step: 4 "low noise": steps: 9 / cfg: 1.0 / euler/simple / start_at_step: 4 / end_at_step: 10000 Note: To improve speed, I set the Windows system to "best performance," disable unnecessary background programs and applications, and lower the desktop resolution. This significantly speeds up video generation. I hope this helps.

Does anyone know if theres similar for wan2.2?

I always get extremely huge no matter what! normal means like 25cm and short like 20cm.

Thank you for this fabulous Lora! I was glad to see your garden party reference workflow use Wan 2.2 but i see that you use your Lora at 0.4 strength on low instead of the 0.8 you recommend. What are the implications of the 0.4 to 0.8 range? (I notice that setting it near 1.0 that the skin texture becomes grainy)