Klein 9B image edit workflow for Comfyui with Loras support. CTRL + B to activate Lora Node.
Runtime profile
Source excerpt
Klein 9B image edit workflow for Comfyui with Loras support. CTRL + B to activate Lora Node.
Estimated VRAM requirement
Estimate unavailable
9.36 GB across 2 of 9 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
25 requirementsAI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Klein 9B Edit with Loras is a Comfyui image-edit workflow with LoRA support. It takes an image and a reference latent, then provides preview and saved-image outputs.
The workflow contains 22 nodes for image loading, VAE encoding and decoding, custom sampling, previewing, and saving.
Image handling includes GetImageSize and ImageScaleToTotalPixels, alongside LoadImage, ReferenceLatent, PreviewImage, and SaveImage.
Sinatra published the workflow, which uses Flux.2 Klein 9B as its base model.
Download it from https://civitai.com/models/2590007.
The workflow names these model files: flux-2-klein-9b-fp8.safetensors, flux2-vae.safetensors, klein_9B_Turbo_r128.safetensors, qwen_3_8b_fp8mixed.safetensors, and real-dream-klein9b-1-fp8.safetensors.
Named nodes include CFGGuider, CLIPLoader, CLIPTextEncode, ConditioningZeroOut, EmptyFlux2LatentImage, Flux2Scheduler, GetImageSize, ImageScaleToTotalPixels, KSamplerSelect, and LoadImage.
They also include LoraLoaderModelOnly, PreviewImage, RandomNoise, ReferenceLatent, SamplerCustomAdvanced, SaveImage, UNETLoader, VAEDecode, VAEEncode, and VAELoader.
Press Ctrl+B to activate the LoRA node.
Verify that flux2-vae.safetensors is the file you intend to use before running the workflow.
Suggestion · not verified
Before use, check that your Comfyui setup includes CFGGuider, LoadImage, PreviewImage, and SaveImage.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
2 excerptsSource context: 795 downloads · Type Workflows · Base model Flux.2 Klein 9B
CLIPLoader
Not resolvedText encoder · Unknown
flux-2-klein-9b-fp8.safetensors
File unverifiedCheckpoint · Hugging Face · black-forest-labs/FLUX.2-klein-9b-fp8 · FLUX.2 Klein 9b FP8
VAE · Hugging Face · Comfy-Org/flux2-dev
LoRA · 1.29 GB · SAFETENSOR · Unknown
Text encoder · 8.07 GB · SAFETENSORS · fp16 · Hugging Face · Comfy-Org/flux2-klein-9B
real-dream-klein9b-1-fp8.safetensors
Not resolvedCheckpoint · Unknown
VAEDecode
Not resolvedVAE · Unknown
VAEEncode
Not resolvedVAE · Unknown
VAELoader
Not resolvedVAE · Unknown
CFGGuider
Not resolvedNode pack · Unknown
CLIPTextEncode
Not resolvedNode pack · Unknown
ConditioningZeroOut
Not resolvedNode pack · Unknown
EmptyFlux2LatentImage
Not resolvedNode pack · Unknown
Flux2Scheduler
Not resolvedNode pack · Unknown
GetImageSize
Not resolvedNode pack · Unknown
ImageScaleToTotalPixels
Not resolvedNode pack · Unknown
KSamplerSelect
Not resolvedNode pack · Unknown
LoadImage
Not resolvedNode pack · Unknown
LoraLoaderModelOnly
Not resolvedNode pack · Unknown
PreviewImage
Not resolvedNode pack · Unknown
RandomNoise
Not resolvedNode pack · Unknown
ReferenceLatent
Not resolvedNode pack · Unknown
SamplerCustomAdvanced
Not resolvedNode pack · Unknown
SaveImage
Not resolvedNode pack · Unknown
UNETLoader
Not resolvedNode pack · Unknown
Source context: 749 downloads · Type Workflows · Base model Flux.2 Klein 9B