Laufzeitprofil
Quellenbeschreibung
flux2_klein-i2i_T2i_workflow
(image edit and text to image)
A very simple workflow using
ComfyUI-PainterFluxImageEdit node.
Edit up to 3 images and switch between Text to Image.
Note: If you want to specify the image size using images, please use images 2 and 3 to specify the size for "T2i Latant".
Bypassing all images results in T2i and brown Latant is enabled.
When using image-edit, be sure to enable it from image1
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Use flux2_klein-i2i_T2i_simple_workflow for text-to-image generation or editing up to three images; it takes text and/or image inputs and produces an image.
Bypass all image inputs for text-to-image mode; enable image1 when editing images, with support for up to three images.
Image editing uses the ComfyUI-PainterFluxImageEdit node.
Use images 2 and 3 to set the image size for the "T2i Latant" setting.
Bypassing all images results in text-to-image mode.
Use ComfyUI version 0.9.2 or higher with the ComfyUI-PainterFluxImageEdit custom node.
Required model files are flux-2-klein-4b-fp8.safetensors, flux2-vae.safetensors, and qwen_3_4b.safetensors.
The workflow also requires the rgthree-comfy node pack.
The base model is Flux.2 Klein 4B.
The workflow allows other FLUX.2-klein models, excluding FLUX.2 [dev], in place of flux-2-klein-4b-fp8.safetensors.
The workflow includes a LoRA Loader.
Before use, verify the intended sources for flux2-vae.safetensors and qwen_3_4b.safetensors.
Vorschlag · nicht geprüft
License information is not specified.
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
1 AuszugSource context: 2786 downloads · Type Workflows · Base model Flux.2 Klein 4B
Lora Loader
Civitai | Share your models
Requirements
ComfyUI ver. 0.9.2 or higher
flux2_klein
Models
flux-2-klein-4b-fp8.safetensors
or other FLUX.2-klein models (Excluding FLUX.2 [dev])
FLUX.2 - a black-forest-labs Collection
text_encoders
VAE
Use Custom Node https://github.com/princepainter/Comfyui-PainterFluxImageEdit?tab=readme-ov-file#comfyui-painterfluximageedit
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
3,79 GB über 1 von 3 Modell-Dateien. Gesamtmodell-Dateien + 25% Ladeaufwand + 2 GB Ausführungs-Puffer, aufgerundet.
Anforderungen
4 Anforderungenflux-2-klein-4b-fp8.safetensors
GefundenCheckpoint · 3.79 GB · SAFETENSORS · fp8 · Hugging Face · black-forest-labs/FLUX.2-klein-4b-fp8
VAE · Hugging Face · Comfy-Org/flux2-dev
Text encoder · Hugging Face · Comfy-Org/z_image_turbo
Knotenpaket · Registry