WorkflowPublicadoExterno

FLUX.1-Fill-dev. [Inpaint->Regional Inpaint->Outpaint]. 3 in 1. [Flux-Tool]

ComfyUI workflow designed to use with FLUX.1-Fill-dev model(s).

TareaMúltipleCapacidadesEdición de imagen · Imagen a imagen · AmpliaciónFamiliaFLUXVRAM estimadaNot yet characterizedBcalidad

Perfil de ejecución

Acceso: Flujo externo
Estado: Publicado
Fuente: Civitai
Actualizado: 25 oct 2026

Descripción de la fuente

ComfyUI workflow designed to use with FLUX.1-Fill-dev model(s).

Supports switching between diffusion models and it's GGuf variants, as well as different inpainting modes (basic and regional)+outpainting. Also supports optional mask editing, switching between manual and florence2 prompt, exif viewer...

Note: Regional inpaint (a.k.a. - crop and stitch nodes) works better if you need to edit small parts of a large image, also allows you to preserve base resolution of input image. In other cases standart inpainting and regional inpainting will act similarly.

Intrsructions provided in workflow.

What you need

Model files: 9.1 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requisitos

Modelos

clip_l.safetensors
Posible
Text encoder · Unknown
DualCLIPLoader
Posible
Text encoder · Unknown
flux1-fill-dev.safetensors
Posible
Checkpoint · Unknown
t5xxl_fp16.safetensors
Encontrado
Text encoder · 9.12 GB · SAFETENSORS · Unknown
thwri/CogFlorence-2.2-Large
Archivo sin verificar
Vision model · Hugging Face · thwri/CogFlorence-2.2-Large
VAEDecode
Posible
VAE · Unknown
VAELoader
Posible
VAE · Unknown

Paquetes de nodos

Anything Everywhere3
Encontrado
Paquete de nodos · Unknown
CLIPTextEncode
Posible
Paquete de nodos · Unknown
CLIPTextEncodeFlux
No resuelto
Paquete de nodos · Unknown
ConditioningZeroOut
Posible
Paquete de nodos · Unknown
CR Text Input Switch
Encontrado
Paquete de nodos · Unknown
DifferentialDiffusion
No resuelto
Paquete de nodos · Unknown
DownloadAndLoadFlorence2Model
Posible
Paquete de nodos · Unknown
easy imageSize
Encontrado
Paquete de nodos · Unknown
Fast Groups Bypasser (rgthree)
No resuelto
Paquete de nodos · Unknown
Fast Groups Muter (rgthree)
No resuelto
Paquete de nodos · Unknown
Florence2Run
Posible
Paquete de nodos · Unknown
GoogleTranslateTextNode
No resuelto
Paquete de nodos · Unknown
GrowMaskWithBlur
Encontrado
Paquete de nodos · Unknown
Image Comparer (rgthree)
No resuelto
Paquete de nodos · Unknown
Image Inset Crop (rgthree)
No resuelto
Paquete de nodos · Unknown
ImageAndMaskPreview
Posible
Paquete de nodos · Unknown
ImageMaskSwitch
Encontrado
Paquete de nodos · Unknown
ImagePadForOutpaint
Posible
Paquete de nodos · Unknown
ImageResizeKJ
Posible
Paquete de nodos · Unknown
ImageScaleToTotalPixels
Posible
Paquete de nodos · Unknown
InpaintCrop
No resuelto
Paquete de nodos · Unknown
InpaintModelConditioning
Posible
Paquete de nodos · Unknown
InpaintStitch
No resuelto
Paquete de nodos · Unknown
KSampler
Posible
Paquete de nodos · Unknown
Load image with metadata [Crystools]
No resuelto
Paquete de nodos · Unknown
LoadImage
Posible
Paquete de nodos · Unknown
OverrideCLIPDevice
Encontrado
Paquete de nodos · Unknown
Power Lora Loader (rgthree)
No resuelto
Paquete de nodos · Unknown
Preview from metadata [Crystools]
No resuelto
Paquete de nodos · Unknown
PreviewImage
Posible
Paquete de nodos · Unknown
SaveImage
Posible
Paquete de nodos · Unknown
Seed Everywhere
Encontrado
Paquete de nodos · Unknown
ShowText|pysssss
Encontrado
Paquete de nodos · Unknown
UNETLoader
Posible
Paquete de nodos · Unknown

Comentario generado por IA

Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.

Propósito

Use this ComfyUI workflow with FLUX.1-Fill-dev models to edit or expand an input image through basic inpainting, regional inpainting, or outpainting; it accepts optional mask editing and a manual or Florence2 prompt, and produces an edited or expanded image.

Flujo

The workflow includes PreviewImage and SaveImage nodes for image preview and saving.

Entradas y salidas

Start with an input image; optional mask editing is available, and the intended output is an edited or expanded image.
Choose between a manual prompt and a Florence2 prompt, then use basic inpainting, regional inpainting, or outpainting.

Configuración inicial

Review the instructions provided in the workflow before use.
Sugerencia · sin verificar

Dependencias

The named model files and model are clip_l.safetensors, flux1-fill-dev.safetensors, t5xxl_fp16.safetensors, and thwri/CogFlorence-2.2-Large.
The workflow names these nodes: Anything Everywhere3; CLIPTextEncode; CLIPTextEncodeFlux; ConditioningZeroOut; CR Text Input Switch; DifferentialDiffusion; DownloadAndLoadFlorence2Model; DualCLIPLoader; easy imageSize; Fast Groups Bypasser (rgthree); Fast Groups Muter (rgthree);⁠
It also names these nodes: Florence2Run; GoogleTranslateTextNode; GrowMaskWithBlur; Image Comparer (rgthree); Image Inset Crop (rgthree); ImageAndMaskPreview; ImageMaskSwitch; ImagePadForOutpaint; ImageResizeKJ; ImageScaleToTotalPixels; InpaintCrop; InpaintModelConditioning; In/;

Configuración

You can switch between diffusion models and their GGuf variants.
Optional controls include mask editing, a manual or Florence2 prompt, and an EXIF viewer.

Precauciones

For a small edit on a large image, consider regional inpainting, also called crop and stitch, because the description says it works better for this use and can preserve the input image’s base resolution; otherwise, it says standard and regional inpainting act similarly.
Sugerencia · sin verificar
License information is not provided for this workflow.

¿Es necesario editarlo?

Inicia sesión para solicitar una edición.

Fuentes

1 fuente

CivitaiPrincipal

civitai.com/models/1030853

Verificado 20 jul

Extractos de fuentes

1 extracto

Note20 julcivitai.com/models/1030853

Source context: 1432 downloads · Type Workflows · Base model Flux.1 D