ComfyUI/AI Tech - Icekiub AI

We will be using skool from now on while I'm building my own platform > most free and sub workflows are already up on there - appreciate the support <3 https://www.skool.com/ai-tech-and-comfyui-workflows-2226

if you were a sub on here contact me on skool so i can put you as a sub for 2 weeks to cover lost time or just sub back up if you prefer doing that, skool doesn't have coupon codes unfortunately but I'll find a way

if you asked for a refund while i was fixing stuff, thanks for your support up to that point I guess😂 see yall there

This whop has been banned just like the patreon, join the discord if you want to get updates on my next steps https://discord.gg/EJvsmQbSSC

Instagram carousel photosets with the new Klein 9B KV

This workflow will let create consistent photosets for social media content or really whatever type of content you want. This version made specifically for people but changing the prompt, it could be used for product photography for example!

Klein KV: https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv-fp8/blob/main/flux-2-klein-9b-kv-fp8.safetensors

Klein No KV: https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-fp8/blob/main/flux-2-klein-9b-fp8.safetensors

if no access: https://modelscope.cn/models/black-forest-labs/FLUX.2-klein-9b-fp8/file/view/master/flux-2-klein-9b-fp8.safetensors?status=2

text_encoders: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/text_encoders/qwen_3_8b_fp8mixed.safetensors

vae: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/vae/flux2-vae.safetensors

LTX 2.3 Motion Control workflow

New version of the LTX motion control using LTX 2.3, in general I'd say its 10-15% better but hard to quantify.

Harder to run locally cause it's bigger. Make sure your Comfyui and NVIDIA drivers are updated to use the latest optimizations for Klein and LTX.

Mostly removed the nodes that were causing issues for alot of people

Try it out and let me know.

LTX goes in checkpoint:https://huggingface.co/Lightricks/LTX-2.3-fp8/blob/main/ltx-2.3-22b-distilled-fp8.safetensors
Text encoder: https://huggingface.co/Comfy-Org/ltx-2/blob/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors
Control lora: https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control/blob/main/ltx-2.3-22b-ic-lora-union-control-ref0.5.safetensors

Klein KV: https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-kv-fp8/blob/main/flux-2-klein-9b-kv-fp8.safetensors

Klein No KV: https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-fp8/blob/main/flux-2-klein-9b-fp8.safetensors

if no access: https://modelscope.cn/models/black-forest-labs/FLUX.2-klein-9b-fp8/file/view/master/flux-2-klein-9b-fp8.safetensors?status=2

text_encoders: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/text_encoders/qwen_3_8b_fp8mixed.safetensors

vae: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/vae/flux2-vae.safetensors

Motion Control workflow with WAN SCAIL + FLUX KLEIN

This workflow uses WAN SCAIL for movement and Flux Klein for the first frame generation. While this is more efficient than the previous version, I still recommend a 5090 and good amount of RAM to run it efficiently.

WAN Models
diffusion models:https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/resolve/main/SCAIL/Wan21-14B-SCAIL-preview_fp8_e4m3fn_scaled_KJ.safetensors

vae: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors

text encoder: https://huggingface.co/Kijai/WanVideo_comfy/blob/main/umt5-xxl-enc-fp8_e4m3fn.safetensors

clip_vision_h.safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors

speed lora: https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/resolve/main/loras/Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors

Detection models (put in models/detection):
vitpose_h_wholebody: https://huggingface.co/Kijai/vitpose_comfy/tree/main/onnx

yolov10m:https://huggingface.co/Wan-AI/Wan2.2-Animate-14B/blob/main/process_checkpoint/det/yolov10m.onnx

Klein (ask for access)

Diffusion_models: https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-fp8/blob/main/flux-2-klein-9b-fp8.safetensors

if no access: https://modelscope.cn/models/black-forest-labs/FLUX.2-klein-9b-fp8/file/view/master/flux-2-klein-9b-fp8.safetensors?status=2

text_encoders: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/text_encoders/qwen_3_8b_fp8mixed.safetensors

vae: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/vae/flux2-vae.safetensors

ZIB + ZIT workflow

This pipeline uses Z-image Base for initial generation and turbo for the final refinement. Also going over ZIB training in the vid.

Links:

All for ZIB: https://huggingface.co/Comfy-Org/z_image/tree/main/split_files

All for ZIT: https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files

*8 steps ZIB (ComfyUI one): https://huggingface.co/alibaba-pai/Z-Image-Fun-Lora-Distill/tree/main

Uncensored Image to image edits with Flux Klein

This workflow will let you recreate ANY image (nsf too) you want with your character as the main star. This can be used with a single image or with a lora. Obviously using a LoRa trained on Flux Klein will yield better results.

Make sure you sub to get these workflows weeks in advance!!!!!!

The best part is that you can change the image's feature only with prompting, no complex inpainting needed.

I can't show the nsf results of this workflow on here but the results have been showcased in the discord for those who want to see.

Enjoy!

Model: https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-fp8/blob/main/flux-2-klein-9b-fp8.safetensors

Non gated Klein: https://modelscope.cn/models/black-forest-labs/FLUX.2-klein-9b-fp8/files

Text encoder: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/text_encoders/qwen_3_8b_fp8mixed.safetensors

vae: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/vae/flux2-vae.safetensors

Captioning workflow for datasets

Just set the path to your dataset folder and your trigger word and Queue up the workflow. Super easy!

Set image load cap to 0 to process everything

High quality Lora Based Faceswap

Join the discord: https://discord.gg/hnZC2d5G5T

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

ICY ANIMATE WORKFLOW
Full body and Head Only version

Load your image and video, and run the Klein Swap. Might take a couple tries to get the good first frame, nothing I can do about that (model skill issue)

If you do not want to use Klein swap, connect the load image directly to the Set_Referenceimage

When you're happy with your first frame, lock the seed and activate the preprocessing group and run the workflow

The higher the resolution, the higher the processing time. You will need to do some basic math to determine how many frames you do per sampler, this amount you can do per sampler will depend on your available amount of VRAM. The more you have the more frames you can do at once. For example, using a RTX PRO 6000 you can do as many frames as you want at once.

I recommend starting medium res (3) with 81 frames chunks (5seconds) per sampler and go up or down from there depending on your hardware and chosen resolution.

you will need access to sam3 and klein for all to work guide in blue node isnt fully updated

Klein (ask for access)

Diffusion_models: https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-fp8/blob/main/flux-2-klein-9b-fp8.safetensors

text_encoders: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/text_encoders/qwen_3_8b_fp8mixed.safetensors

vae: https://huggingface.co/Comfy-Org/flux2-klein-9B/resolve/main/split_files/vae/flux2-vae.safetensors

Wan Animate

Diffusion_models: https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/resolve/main/Wan22Animate/Wan2_2-Animate-14B_fp8_scaled_e4m3fn_KJ_v2.safetensors

vae https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors

text_encoders: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors

clip_vision/ https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors

WanAnimate_relight_lora_fp16.safetensors https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/LoRAs/Wan22_relight/WanAnimate_relight_lora_fp16.safetensors

speed lora https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/resolve/main/loras/Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors