WorkflowListedExternal

Mrpopo's Flux.2 Klein 9B anime workflow

TaskUpscalingFamilyFLUXEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Jul 18, 2026

Source description

unlock the capability of anime and unleash flux klein 9b true potential with my anime workflow. It features color adjustments and a simple upscale, perfect for anime. I've included notes in the workflow to help you out. I strongly suggest using my anime lora with this workflow. I appreciate anyone who tries my models! Cant wait to see what creative images you bring.

In the save image node, please change the hash to the new hash from this page. you can see it on the right side of this page. I've included notes to help you with that. Its to upload image to the correct workflow page. Use the AUTOV3 hash. I appreciate it!

Also, you can change the AUTOV3 hash of my version 1 anime lora to version 2 (i've updated the lora) in the image saver node.

This workflow is also good for non anime generations. just disable the anime lora, choose your sampler and produce photorealistic images. Sometimes simple workflow equals better. no complications. You could increase the resolution as well to 1664x2432. My Lora can handle that high of resolution.

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

Use this Flux.2 Klein 9B workflow to generate anime images with text encoding, an anime LoRA, sampler choice, and resolution settings; it can apply color adjustments and a simple upscale, and can also produce non-anime or photorealistic images when the anime LoRA is disabled.

Flow

Its 25-node graph includes text encoding, latent image creation, scheduling, sampling, VAE decoding, preview, color matching, autotone, upscaling, and image saving.

Inputs and outputs

The main controls are text encoding, anime LoRA selection, sampler choice, and resolution.
The described outputs include color-adjusted images, a simple upscale, and photorealistic images when the anime LoRA is disabled.

Setup

Before saving, update the Image Saver node with the AUTOV3 hash shown on the Civitai page. The description also says the version 1 anime LoRA hash can be changed to version 2.
Suggestion · not verified

Dependencies

The listed model files are DarkKlein9b_v2BFS_extracted_lora_r256.safetensors, qwen_3_8b_fp8mixed.safetensors, flux-2-klein-9b-nvfp4.safetensors, Flux.2 Klein 9B anime.safetensors, flux2-vae.safetensors, klein_snofs_v1_1.safetensors, and qwen_3_8b_fp4mixed.safetensors.
The listed node packs are comfyui-image-saver, comfyui-imageautotone, comfyui-kjnodes, RES4LYF, comfyui_essentials, and comfyui_nvidia_rtx_nodes.

Configuration

For anime output, enable the anime LoRA; for non-anime or photorealistic output, disable it and choose a sampler.
Suggestion · not verified
For a higher-resolution attempt, try 1664x2432; the description says its LoRA can handle that size.
Suggestion · not verified

Cautions

Before use, verify that klein_snofs_v1_1.safetensors, qwen_3_8b_fp4mixed.safetensors, flux-2-klein-9b-nvfp4.safetensors, and comfyui_nvidia_rtx_nodes are the intended files for this workflow.
Suggestion · not verified
Also verify that flux2-vae.safetensors and Flux.2 Klein 9B anime.safetensors are the intended files before use.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimaryVersion 2789395

civitai.com/models/2480987

Verified Jul 18

Source excerpts

1 excerpt

NoteJul 18civitai.com/models/2480987

Source context: 255 downloads · Type Workflows · Base model Flux.2 Klein 9B