Saltar al contenido
WorkflowPublicadoExterno
Abrir fuente

DMD2 essential upscaler/refiner workflow — v1.0

There's few DMD2 upscale/refine workflows on this site but all are overcomplicated. Here's the essential simplest workflow presenting how powerful it is. I'm using this stuff at end of all image generation because...

Fuentecivitai.com/models/1278122
TareaMúltipleCapacidadesImagen a imagen · AmpliaciónFamiliaStable DiffusionVRAM estimadaNot yet characterizedBcalidad

Perfil de ejecución

Acceso
Flujo externo
Estado
Publicado
Fuente
Civitai
Actualizado
19 ago 2026

Descripción de la fuente

There's few DMD2 upscale/refine workflows on this site but all are overcomplicated. Here's the essential simplest workflow presenting how powerful it is. I'm using this stuff at end of all image generation because its simply free 2-5sec, insane, not only upscale, but also subtle fix for every little thing.

DMD2 lora - https://huggingface.co/tianweiy/DMD2/blob/main/dmd2_sdxl_4step_lora_fp16.safetensors

At KSampler test with "start_at_step" in 60-68 range. Closer you get to 70 the less impact will it have on photo (less steps). Smaller number - more fixes (more steps) but also more intervention from the checkpoint that you potentially would not like. Input image should be in 768-1280 size. Bigger images can produce mutations like double knees.

To avoid that replace "upscale image by" node with forced resize where longest side is not bigger than 2048.

If you want be more aggressive with sharpness - resize image, pass it trough 1xReFocus upscaler and then do ksampler. https://openmodeldb.info/models/1x-ReFocus-V3

What you need

Model files
0.1 GiB known subtotal

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

Requisitos

Modelos

7

  • 4x_foolhardy_Remacri.pth

    Encontrado

    Upscaler · 63.9 MB · PTH · Unknown

  • bigLove_xl1.safetensors

    No resuelto

    Checkpoint · Unknown

  • dmd2_sdxl_4step_lora_fp16.safetensors

    No resuelto

    LoRA · Unknown

  • ImageUpscaleWithModel

    Posible

    Upscaler · Unknown

  • UpscaleModelLoader

    Posible

    Upscaler · Unknown

  • VAEDecode

    Posible

    VAE · Unknown

  • VAEEncode

    Posible

    VAE · Unknown

Paquetes de nodos

8

  • CheckpointLoaderSimple

    Posible

    Paquete de nodos · Unknown

  • CLIPTextEncode

    Posible

    Paquete de nodos · Unknown

  • ImageCASharpening+

    Encontrado

    Paquete de nodos · Unknown

  • ImageScaleBy

    Posible

    Paquete de nodos · Unknown

  • KSamplerAdvanced

    Posible

    Paquete de nodos · Unknown

  • LoadImage

    Posible

    Paquete de nodos · Unknown

  • LoraLoader

    Posible

    Paquete de nodos · Unknown

  • PreviewImage

    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

  • This DMD2 LoRA workflow takes an image through an upscale and refine pass, aiming to produce an enlarged image with subtle fixes.

Flujo

  • ImageCASharpening+ is included from the ComfyUI_essentials node pack.

Entradas y salidas

  • The creator describes using it at the end of image generation; LoadImage and PreviewImage are listed among its nodes.

Dependencias

  • Named model files: 4x_foolhardy_Remacri.pth, bigLove_xl1.safetensors, and dmd2_sdxl_4step_lora_fp16.safetensors.

  • Listed node names: CheckpointLoaderSimple, CLIPTextEncode, ImageCASharpening+, ImageScaleBy, ImageUpscaleWithModel, and KSamplerAdvanced.

  • Also listed: LoadImage, LoraLoader, PreviewImage, UpscaleModelLoader, VAEDecode, and VAEEncode.

Configuración

  • Try KSampler start_at_step values from 60 to 68; the creator says values nearer 70 have less effect, while lower values bring more fixes and more checkpoint influence.

    Sugerencia · sin verificar

  • To reduce the described risk of mutations, the creator suggests replacing “upscale image by” with a forced resize capped at 2048 on the longest side.

    Sugerencia · sin verificar

  • For stronger sharpness, resize the image, pass it through the 1xReFocus upscaler, then run KSampler.

    Sugerencia · sin verificar

Precauciones

  • The creator recommends 768–1280 input images and warns that larger images can produce mutations such as double knees.

  • No license information is listed.

¿Es necesario editarlo?

Inicia sesión para solicitar una edición.

Fuentes

1 fuente
CivitaiPrincipal
civitai.com/models/1278122

Verificado 20 jul

Extractos de fuentes

1 extracto
Note20 julcivitai.com/models/1278122

Source context: 1101 downloads · Type Workflows · Base model Other