Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
What’s the point of this workflow? Well, if you’re like me and sick of constantly switching between klein workflows, this one’s for you. It’s just some simple tweaks to keep things lean and efficient.
Runtime profile
Source description
What’s the point of this workflow? Well, if you’re like me and sick of constantly switching between klein workflows, this one’s for you. It’s just some simple tweaks to keep things lean and efficient.
1.It packs both T2I and Edit workflows into one, so you can swap between them on the fly.
2.Added Lora nodes.
3.Added inpaint nodes.
3.Bumped the reference image inputs from 2 up to 3, and you can toggle the amount whenever you want.
And if you need another reason, honestly, I’m just uploading this because I wanted to have a backup of this workflow on Civitai.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This workflow is for T2I image generation and image editing. It combines both modes, accepts up to three selectable reference-image inputs, and includes SaveImage for image output.
It combines T2I and Edit workflows in one setup, with added LoRA nodes and inpaint nodes.
The T2I and Edit workflows can be switched between on the fly.
The inputs are text for T2I work and images for editing, with up to three selectable reference-image inputs; SaveImage is listed for the image output.
It is listed as a Workflows item, uses Flux.2 Klein 9B as its base model, and is published by SamLiu.
Listed model files include dmd2_sdxl_4step_lora.safetensors, elsa_klein_9b-13.safetensors, elsa_klein_9b-38.safetensors, and flux-2-klein-9b-fp8.safetensors.
Other listed model files are flux-2-klein-base-9b-fp8.safetensors, flux2-vae.safetensors, and qwen_3_8b_fp8mixed.safetensors.
Listed node packs are comfyui_resolution-and-ratio, comfyui-easy-use, and was-ns.
Switch between the T2I and Edit workflows as needed; the modes can be changed on the fly.
Suggestion · not verified
Select up to three reference images; the amount can be toggled.
Suggestion · not verified
Before using the workflow, verify that these model files are available under their exact filenames: dmd2_sdxl_4step_lora.safetensors, elsa_klein_9b-13.safetensors, elsa_klein_9b-38.safetensors, flux-2-klein-9b-fp8.safetensors, flux-2-klein-base-9b-fp8.safetensors, flux2-vae.safet
Suggestion · not verified
Also verify that comfyui_resolution-and-ratio, comfyui-easy-use, and was-ns are available.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 757 downloads · Type Workflows · Base model Flux.2 Klein 9B
Estimated VRAM requirement
Estimate unavailable
16.9 GB across 2 of 7 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
10 requirementsdmd2_sdxl_4step_lora.safetensors
Not resolvedLoRA · Unknown
elsa_klein_9b-13.safetensors
Not resolvedLoRA · Unknown
elsa_klein_9b-38.safetensors
Not resolvedLoRA · Unknown
Checkpoint · 8.79 GB · SAFETENSORS · Unknown
flux-2-klein-base-9b-fp8.safetensors
Not resolvedCheckpoint · Hugging Face · black-forest-labs/FLUX.2-klein-base-9b-fp8
VAE · Hugging Face · Comfy-Org/flux2-dev
Text encoder · 8.07 GB · SAFETENSORS · fp16 · Hugging Face · Comfy-Org/flux2-klein-9B
Node pack · Registry
Node pack · Registry
was-ns
Node pack · Registry
