The purpose of this workflow is to mix flux2klein excellent prompt tracking and high image quality with illustrious- SDXL's vast AGC character resources.
Runtime profile
Source description
flux2_klein-SDXL_Upscale_workflow
(text to image upscale)
The purpose of this workflow is to mix flux2_klein excellent prompt tracking and high image quality with illustrious- SDXL's vast AGC character resources.
In other words, characters that flux2_klein has not yet learned can be expressed using illustrious-SDXL's learned resources without using Lora.
It combines flux2_klein and SDXL for extremely fast generation speeds .
This is how I use it, but it's up to you to use it in your own way.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This ComfyUI workflow uses a text prompt to generate images with flux2_klein and Illustrious-SDXL character resources, with an optional image-upscaling path.
It can use Illustrious-SDXL’s learned character resources for characters flux2_klein has not learned, without a LoRA.
It can scale and upscale images, arrange them in rows, and save animated WEBP files.
The listed requirement is ComfyUI version 0.9.1 or higher.
The setup list names flux-2-klein-4b-fp8.safetensors or flux-2-klein-4b.safetensors, qwen_3_4b.safetensors, and flux2-vae.safetensors.
The instructions also name an Illustrious checkpoint and recommend DMD2 Speed LoRA options dmd2_sdxl_4step_lora_fp16 or dmd2_sdxl_4step_lora_fp32, plus the lollypop.pth upscaler.
The listed node packs are ComfyUI-Custom-Scripts, ComfyUI-Easy-Use, comfyui-mute-bypass-by-ID, and images-grid-comfy-plugin.
Turn off Upscale-Switch to render only flux2_klein; in this mode, the workflow does not upscale.
The listed upscale ratio is 1.5 to 2.0, with 1.5 recommended.
Luc_meqemeqe-SR.safetensors is named without a download link; check whether your copy of the workflow uses it.
Suggestion
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 413 downloads · Type Workflows · Base model Flux.2 D
Turn Off Upscale-Switch, only flux2_klein will be rendered.
Can be used as a regular flux2_klein workflow
Doesn't upscale anything
Upscale ratio 1.5 to 2.0 (1.5 recommended)
Requirements
ComfyUI ver. 0.9.1 or higher
flux2_klein
Models
flux-2-klein-4b-fp8.safetensors
or
flux-2-klein-4b.safetensors
text_encoders
VAE
Illustrious Model
Civitai | Share your models Illustrious Checkpoint
also recommend my merge model
DMD2 Speed LoRA
dmd2_sdxl_4step_lora_fp16 or dmd2_sdxl_4step_lora_fp32
Recommend upscaler lollypop
Use Custom Node
Remaining hardware or download-size estimates are not available yet.
Requirements
dmd2_sdxl_4step_lora_fp16.safetensors
Not resolvedLoRA · Civitai · 1820946
Checkpoint · 3.79 GB · Hugging Face · black-forest-labs/FLUX.2-klein-4b-fp8
Source context: 412 downloads · Type Workflows · Base model Flux.2 D
Source context: 354 downloads · Type Workflows · Base model Flux.2 D
VAE · 321 MB · Hugging Face · Comfy-Org/flux2-dev
Upscaler · 63.9 MB · Hugging Face · uwg/upscaler
Luc_meqemeqe-SR.safetensors
Not resolvedCheckpoint · Unknown
Text encoder · 7.49 GB · Hugging Face · Comfy-Org/flux2-klein
comfyui-custom-scripts
FoundNode pack · Registry
comfyui-easy-use
FoundNode pack · Registry
comfyui-mute-bypass-by-id
FoundNode pack · Registry
Node pack · Registry