DEV Community

AI-KSK profile picture

AI-KSK

AI creator focused on ComfyUI, AI video generation, workflows and practical AIGC tutorials. Sharing reproducible workflows, model tests and YouTube guides.

Joined Joined on 
Six ComfyUI UI Workflows: Pose, Costume and Matrix on Qwen2.1 vs FLUX3 Klein

Six ComfyUI UI Workflows: Pose, Costume and Matrix on Qwen2.1 vs FLUX3 Klein

Comments
2 min read
H3 Viggle Remake: Character Swap Without Masks, Original Camera Intact

H3 Viggle Remake: Character Swap Without Masks, Original Camera Intact

Comments
2 min read
MiniMax H3 Digital Human + SeedVR2: One Photo, One Audio Clip, a 2K Talking Head

MiniMax H3 Digital Human + SeedVR2: One Photo, One Audio Clip, a 2K Talking Head

Comments
2 min read
MiniMax H3-Image: Native 4K at 16.8MP in Six Steps - Three ComfyUI Workflows Compared

MiniMax H3-Image: Native 4K at 16.8MP in Six Steps - Three ComfyUI Workflows Compared

Comments
3 min read
MiniMax H3 Image: Two Pose Directors (Manual VNCCS + SAM3D Photo Reverse) - ComfyUI Workflow Guide

MiniMax H3 Image: Two Pose Directors (Manual VNCCS + SAM3D Photo Reverse) - ComfyUI Workflow Guide

Comments
3 min read
FLUX: MOSS StepLab CharRef — 6 Workflows, Read From the Graphs

FLUX: MOSS StepLab CharRef — 6 Workflows, Read From the Graphs

Comments
3 min read
MOSS Image Cleaning: 50 Steps vs 8-Step DMD vs 4-Step Turbo (ComfyUI)

MOSS Image Cleaning: 50 Steps vs 8-Step DMD vs 4-Step Turbo (ComfyUI)

Comments
2 min read
FLUX: MOSS Image DMD Turbo — 5 Workflows, Read From the Graphs

FLUX: MOSS Image DMD Turbo — 5 Workflows, Read From the Graphs

Comments
3 min read
Qwen Image: Character Swap SAM VDN8 — 1 Workflows, Read From the Graphs

Qwen Image: Character Swap SAM VDN8 — 1 Workflows, Read From the Graphs

Comments
2 min read
FLUX3 Klein 4K Repair: Single Image, ZIP Batch, or Local Folder (ComfyUI)

FLUX3 Klein 4K Repair: Single Image, ZIP Batch, or Local Folder (ComfyUI)

Comments
2 min read
FLUX: image_flux3_klein_image_edit — 7 Workflows, Read From the Graphs

FLUX: image_flux3_klein_image_edit — 7 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: MiniMax — 1 Workflows, Read From the Graphs

Qwen Image: MiniMax — 1 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: MiniMax ControlNet Union — 5 Workflows, Read From the Graphs

Qwen Image: MiniMax ControlNet Union — 5 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: VDN NFE Hero Shot — 2 Workflows, Read From the Graphs

Qwen Image: VDN NFE Hero Shot — 2 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: Mini Max Face Refine — 3 Workflows, Read From the Graphs

Qwen Image: Mini Max Face Refine — 3 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: MiniMax OpenVDN DMD8 VDA — 2 Workflows, Read From the Graphs

Qwen Image: MiniMax OpenVDN DMD8 VDA — 2 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: QwenImage2.1 — 1 Workflows, Read From the Graphs

Qwen Image: QwenImage2.1 — 1 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: Character Pose Director — 1 Workflows, Read From the Graphs

Qwen Image: Character Pose Director — 1 Workflows, Read From the Graphs

Comments
3 min read
Qwen Image: Eros Beta5 FL2VA Ref2VA — 2 Workflows, Read From the Graphs

Qwen Image: Eros Beta5 FL2VA Ref2VA — 2 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: MiniMax TaoMate lora — 2 Workflows, Read From the Graphs

Qwen Image: MiniMax TaoMate lora — 2 Workflows, Read From the Graphs

Comments
3 min read
Qwen Image: MiniMax OpenVDN DMD8 — 9 Workflows, Read From the Graphs

Qwen Image: MiniMax OpenVDN DMD8 — 9 Workflows, Read From the Graphs

Comments
3 min read
Qwen Image: MiniMax OpenVDN DMD8 — 6 Workflows, Read From the Graphs

Qwen Image: MiniMax OpenVDN DMD8 — 6 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: MiniMax Ref2VA Motion Lab — 2 Workflows, Read From the Graphs

Qwen Image: MiniMax Ref2VA Motion Lab — 2 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: MiniMax Ref2VA FL2VA — 3 Workflows, Read From the Graphs

Qwen Image: MiniMax Ref2VA FL2VA — 3 Workflows, Read From the Graphs

Comments
2 min read
Anima: Anima — 6 Workflows, Read From the Graphs

Anima: Anima — 6 Workflows, Read From the Graphs

Comments
3 min read
LTX: MiniMax Ref2VA FL2VA — 6 Workflows, Read From the Graphs

LTX: MiniMax Ref2VA FL2VA — 6 Workflows, Read From the Graphs

Comments
3 min read
Qwen Image: MiniMax H25 Hybrid — 1 Workflows, Read From the Graphs

Qwen Image: MiniMax H25 Hybrid — 1 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: MiniMax Larry Sageattention — 11 Workflows, Read From the Graphs

Qwen Image: MiniMax Larry Sageattention — 11 Workflows, Read From the Graphs

Comments
3 min read
Qwen Image: MiniMax — 2 Workflows, Read From the Graphs

Qwen Image: MiniMax — 2 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: MiniMax R2V — 10 Workflows, Read From the Graphs

Qwen Image: MiniMax R2V — 10 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: Krea krea2 — 3 Workflows, Read From the Graphs

Qwen Image: Krea krea2 — 3 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: Krea Identity Edit v1.2 — 3 Workflows, Read From the Graphs

Qwen Image: Krea Identity Edit v1.2 — 3 Workflows, Read From the Graphs

Comments
2 min read
Qwen Image: Krea — 3 Workflows, Read From the Graphs

Qwen Image: Krea — 3 Workflows, Read From the Graphs

Comments
2 min read
FLUX: Anima Aesthetic Testing — 10 Workflows, Read From the Graphs

FLUX: Anima Aesthetic Testing — 10 Workflows, Read From the Graphs

Comments
3 min read
LTX: ltx Image Controlnet — 4 Workflows, Read From the Graphs

LTX: ltx Image Controlnet — 4 Workflows, Read From the Graphs

Comments
3 min read
Qwen Image: Wan2.1 flf2v — 2 Workflows, Read From the Graphs

Qwen Image: Wan2.1 flf2v — 2 Workflows, Read From the Graphs

Comments
2 min read
LTX: LTX — 1 Workflows, Read From the Graphs

LTX: LTX — 1 Workflows, Read From the Graphs

Comments
2 min read
Anima: SCAIL单人三维姿态驱动 图像参考的长时序稳定生成 — 7 Workflows, Read From the Graphs

Anima: SCAIL单人三维姿态驱动 图像参考的长时序稳定生成 — 7 Workflows, Read From the Graphs

Comments
3 min read
Qwen Image: Wan2 2 3图首尾帧循环 — 2 Workflows, Read From the Graphs

Qwen Image: Wan2 2 3图首尾帧循环 — 2 Workflows, Read From the Graphs

Comments
3 min read
FLUX: 2512 vs z image vs flux2 — 6 Workflows, Read From the Graphs

FLUX: 2512 vs z image vs flux2 — 6 Workflows, Read From the Graphs

Comments
3 min read
Wan 2.2 SVI 2.0 Pro: Making a Video Loop Without a Visible Seam

Wan 2.2 SVI 2.0 Pro: Making a Video Loop Without a Visible Seam

Comments
3 min read
LTX-2 Camera Control LoRAs: Seven Ways to Direct the Move, and What NVFP4 Actually Costs

LTX-2 Camera Control LoRAs: Seven Ways to Direct the Move, and What NVFP4 Actually Costs

Comments
4 min read
Four Image Models in One Graph: 2512 vs Flux 2 vs Z-Image vs Klein

Four Image Models in One Graph: 2512 vs Flux 2 vs Z-Image vs Klein

Comments
3 min read
AnyLight: Letting Blender's Physical Renderer Decide the Lighting

AnyLight: Letting Blender's Physical Renderer Decide the Lighting

Comments
3 min read
Qwen3-TTS in ComfyUI: Multi-Speaker Dialogue, 3-Second Voice Cloning, and One Sampler You Have Not Seen

Qwen3-TTS in ComfyUI: Multi-Speaker Dialogue, 3-Second Voice Cloning, and One Sampler You Have Not Seen

Comments
3 min read
Z-Image Base Inpainting, Upscaling, and an Encoder Type That Keeps Changing

Z-Image Base Inpainting, Upscaling, and an Encoder Type That Keeps Changing

Comments
3 min read
High-Noise Locks Structure, Low-Noise Explodes Style: The Split That Brings Back the Fun

High-Noise Locks Structure, Low-Noise Explodes Style: The Split That Brings Back the Fun

Comments
3 min read
Local Redraw at High Resolution: Crop, Regenerate, Paste Back Seamlessly

Local Redraw at High Resolution: Crop, Regenerate, Paste Back Seamlessly

Comments
3 min read
InfiniteTalk Native in ComfyUI: Looping a Talking Head to Unlimited Length

InfiniteTalk Native in ComfyUI: Looping a Talking Head to Unlimited Length

Comments
3 min read
LTX-2 Adapter LoRA: Consistency Gains, and a Fork You Should Know About

LTX-2 Adapter LoRA: Consistency Gains, and a Fork You Should Know About

Comments
3 min read
3D Pose and Lighting Control Without Leaving ComfyUI

3D Pose and Lighting Control Without Leaving ComfyUI

Comments
3 min read
Seedance 2.0 Post-Production: Three Fixes That Belong After Generation, Not Before

Seedance 2.0 Post-Production: Three Fixes That Belong After Generation, Not Before

Comments
3 min read
Anima 2B: A Small Anime Model Trained Without AI-Synthesised Data

Anima 2B: A Small Anime Model Trained Without AI-Synthesised Data

Comments
3 min read
Z-Image 8-Step vs 4-Step, and a Text Encoder That Cannot Agree On Its Own Type

Z-Image 8-Step vs 4-Step, and a Text Encoder That Cannot Agree On Its Own Type

Comments
3 min read
Training a LoRA From Six Images in Seconds: What i2L Actually Produces

Training a LoRA From Six Images in Seconds: What i2L Actually Produces

Comments
3 min read
Seamless Head Swap on Flux 2 Klein 9B: Rank 128 and the Upscale Trap

Seamless Head Swap on Flux 2 Klein 9B: Rank 128 and the Upscale Trap

Comments
3 min read
FireRed Image Edit 1.0 vs Qwen 2511: Anti-Drift Versus Free-Range Editing, and a Filename With a Space

FireRed Image Edit 1.0 vs Qwen 2511: Anti-Drift Versus Free-Range Editing, and a Filename With a Space

Comments
3 min read
SkyReels V3 R2V Merged With VACE: Skeleton-Guided Video on a Wan 14B Base

SkyReels V3 R2V Merged With VACE: Skeleton-Guided Video on a Wan 14B Base

Comments
3 min read
Face Swapping That Survives Upscaling: The Paste-Back Pattern

Face Swapping That Survives Upscaling: The Paste-Back Pattern

Comments
3 min read
A 20,000-Artist Style Reference Library, and a 2x Acceleration LoRA

A 20,000-Artist Style Reference Library, and a 2x Acceleration LoRA

Comments
3 min read
loading...