My TG Channel - https://t.me/StefanFalkokAI
My TG Chat - https://t.me/+y4R5JybDZcFjMjFi
My NSFW Channel - https://t.me/stefanfalkokmoth
My ComfyUI Build - https://huggingface.co/datasets/StefanFalkok/ComfyUI_portable_torch_2.10.0_cu130_cp313_sageattention_triton/tree/main
Hi! I introduce my model WAN 2.2 I2V 10 steps for NSFW Generation
if you want generate SFW content - go to my models https://civarchive.com/models/2086218/wan-22-10-steps-t2v-and-i2v-fp8-gguf-q80-q4km-models
Everything u need - just load model without light lora, set 8 steps (4/4), set 2cfg on High Noise and cfg1 on low noise, set 81 frame (16 framerate), set resolution from 576p to 720p
To get my i2v NSFW workflow, just install from https://huggingface.co/StefanFalkok/Wan_2.2_10steps/blob/main/wan%202.2%20i2v%2010%20steps%20correct.json
I merged original WAN 2.2 Models from ComfyUI repository with LightX T2V Rank 256 bf 16 (https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Lightx2v/lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank256_bf16.safetensors), also merged nsfw loras - https://civarchive.com/models/1307155?modelVersionId=2073605, https://civarchive.com/models/1954774/cunnilingus-pussy-licking-lora-i2v-wan22-k3nk
https://civarchive.com/models/1811313?modelVersionId=2176505
fp8 results on rtx 5080
1024x576 - around 3 minutes
720p - around 5 minutes
I also recomend trigger words to control your generation, also recomend write better prompts. Enjoy!
Description
Wan 2.2 I2V 10 Steps NSFW High Noise
FAQ
Comments (13)
I am brand new at generating Ai videos. I have a workflow but I want to use this model, Does it go into a checkpoint folder or Diffusion_Models?
place into difussion_models. But I recomend use my NSFW workflow with 10steps model with control of many loras https://civitai.com/models/2105650/wan-22-nsfw-workflow-with-10-steps-i2v-model-nsfw-loras-fp8-gguf-upscale-with-interpolation-mmaudio
Hi ! Is it possible to use it with a 5060ti 16GB Vram and 32go ram ?
Hi, of course it possible
GGUF please
Wait... the files i downloaded are GGUF?
fp8
@Stefan_Falkok don't mind me, i'm still learning comfyui and figured it out after hours of learning... it's still a bit confusing though... sigh
I used your fp8 model and workflow, 10 step, on a 5060ti with 16GB VRAM and 32GB RAM. At a resolution of 1024*576, it takes about 13 minutes. Is this normal? I used the official WAN 2.2 accelerated LoRA.Just got into ComfyUI, thanks for the reply
hi, 13 minutes is very good result fot 5060 ti 16
@Stefan_Falkok Thanks a lot for your answer