Hey guys 👋 I'm wondering if there is any chance to create SFW workflows for official cloud ComfyUi? The reason for me is simple : create casual and daily content, RunPod or Vast.ai are a pain in the ass... how many times I had to install 20-30 minutes the setup with jupyter on Vast.ai)

Hi everyone. I trained a LoRA with the help of Claude.ai in Kohya_SS. First I tried it with 74 photos, and then a second time with 161 photos. All the images were very high quality, generated through Grok. When I generated images using the LoRA, the face was always half blurry and out of focus. Does anyone here work with ComfyUI or SD.Next? Do you have any experience with this? I’d really like to exchange information, tips, and results with someone about generating images in open-source programs like ComfyUI or SD.Next. Thank you🙂

Hey @Icekiub Ai , I have a question about the WAN 2.2 Lora Based Faceswap workflow. How can I connect a node to upload my own videos that I already have from Instagram, instead of the plugin that downloads videos from TikTok? I see that there is a nod for it, but it's disconecded from the rest.

https://x.com/icekiubAI/status/2045116980206702691?s=20 A WAN 2.2 low noise character Lora is required for this to work but I think it's one of the better solutions out there right now and I quickly go over the whole process in the video This is mostly a faceswap pipeline, hair color, body and clothes will be from the original video, select your reference videos with that in mind. We use WAN 2.2 T2V not I2V make sure you get that right Workflow in the zip My character on the left in the samples The video for this will be coming today or tomorrow WAN 2.2 T2V: https://huggingface.co/icekiub/WAN-2.2-T2V-FP8-NON-SCALED/resolve/main/WAN2.2t2vLOWNOISEFP8.safetensors 4step: https://huggingface.co/lightx2v/Wan2.2-Lightning/resolve/main/Wan2.2-T2V-A14B-4steps-lora-250928/low_noise_model.safetensors text encoder: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors vae: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors

Covers the whole thing Prodigy with a learning rate of 1 can be used instead of AdamW8bit