Klein 9B img2img (denoise) with Loras
Runtime profile
Source excerpt
Klein 9B img2img (denoise) with Loras
Estimated VRAM requirement
Estimate unavailable
18.5 GB across 4 of 8 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
18 requirementsAI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Klein 9B img2img (denoise) with Loras — v1.0 is for denoising an input image and producing an image result with Loras, using Flux.2 Klein 9B as its base model.
The workflow includes three linked model components: flux-2-klein-9b-fp8.safetensors, klein_9B_Turbo_r128.safetensors, and qwen_3_8b_fp8mixed.safetensors.
Use an image as the main input and expect an image result; the listed image components include LoadImage and SaveImage.
Suggestion · not verified
It is published by Sinatra as v1.0 and classified as a Workflows item.
The listed source page is https://civitai.com/models/2590376?modelVersionId=2909957.
Named model files include flux-2-klein-9b-fp8.safetensors, klein_9B_Turbo_r128.safetensors, qwen_3_8b_fp8mixed.safetensors, and flux2-vae.safetensors.
Other named components include UNETLoader, VAELoader, VAEEncode, VAEDecode, KSampler, and LoraLoaderModelOnly.
The workflow also lists LoadImage, SaveImage, PreviewImage, ImageScaleToMaxDimension, CLIPLoader, CLIPTextEncode, ConditioningZeroOut, and MarkdownNote.
Configure it around the Flux.2 Klein 9B base model and the named denoising-with-Loras use case.
Suggestion · not verified
Before use, verify that flux2-vae.safetensors is the intended compatible VAE file and that PreviewImage is available; the file has a reported type mismatch, and no provider or filename is listed for PreviewImage.
Suggestion · not verified
No license is listed for this workflow, so check the source page's usage terms before reuse.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 602 downloads · Type Workflows · Base model Flux.2 Klein 9B
CLIPLoader
Not resolvedText encoder · Unknown
Checkpoint · 8.79 GB · SAFETENSORS · Hugging Face · black-forest-labs/FLUX.2-klein-9b-fp8
VAE · 321 MB · Hugging Face · Comfy-Org/flux2-dev
LoRA · 1.29 GB · SAFETENSOR · Hugging Face · saik0s/comfy_backup
Text encoder · 8.07 GB · SAFETENSORS · fp16 · Hugging Face · Comfy-Org/flux2-klein-9B
VAEDecode
Not resolvedVAE · Unknown
VAEEncode
Not resolvedVAE · Unknown
VAELoader
Not resolvedVAE · Unknown
CLIPTextEncode
Not resolvedNode pack · Unknown
ConditioningZeroOut
Not resolvedNode pack · Unknown
ImageScaleToMaxDimension
Not resolvedNode pack · Unknown
KSampler
Not resolvedNode pack · Unknown
LoadImage
Not resolvedNode pack · Unknown
LoraLoaderModelOnly
Not resolvedNode pack · Unknown
MarkdownNote
Not resolvedNode pack · Unknown
PreviewImage
Not resolvedNode pack · Unknown
SaveImage
Not resolvedNode pack · Unknown
UNETLoader
Not resolvedNode pack · Unknown
Source context: 549 downloads · Type Workflows · Base model Flux.2 Klein 9B
Source context: 521 downloads · Type Workflows · Base model Flux.2 Klein 9B