Ir para o conteúdo
WorkflowListadosExterno
Fonte aberta

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...

Fontecivitai.com/models/1278122
TarefaMúltiploCapacidadesImagem para imagem · Aumento de resoluçãoFamíliaStable DiffusionEstimado VRAMNot yet characterizedBnota

Perfil de execução

Acesso
Fluxo de trabalho externo
Status
Listados
Fonte
Civitai
Atualizado
19 de ago. de 2026

Descrição da fonte

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

    Não resolvido

    Checkpoint · Unknown

  • dmd2_sdxl_4step_lora_fp16.safetensors

    Não resolvido

    LoRA · Unknown

  • ImageUpscaleWithModel

    Possível

    Upscaler · Unknown

  • UpscaleModelLoader

    Possível

    Upscaler · Unknown

  • VAEDecode

    Possível

    VAE · Unknown

  • VAEEncode

    Possível

    VAE · Unknown

Pacotes de nós

8

  • CheckpointLoaderSimple

    Possível

    Pacote de nós · Unknown

  • CLIPTextEncode

    Possível

    Pacote de nós · Unknown

  • ImageCASharpening+

    Encontrado

    Pacote de nós · Unknown

  • ImageScaleBy

    Possível

    Pacote de nós · Unknown

  • KSamplerAdvanced

    Possível

    Pacote de nós · Unknown

  • LoadImage

    Possível

    Pacote de nós · Unknown

  • LoraLoader

    Possível

    Pacote de nós · Unknown

  • PreviewImage

    Possível

    Pacote de nós · Unknown

Comentário gerado por IA

Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são 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.

Fluxo

  • ImageCASharpening+ is included from the ComfyUI_essentials node pack.

Entradas e saídas

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

Dependências

  • 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.

Configuração

  • 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.

    Sugestão · não verificado

  • 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.

    Sugestão · não verificado

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

    Sugestão · não verificado

Precauções

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

  • No license information is listed.

Isso precisa ser editado?

Faça login para enviar uma solicitação de edição.

Fontes

1 fonte
CivitaiPrimário
civitai.com/models/1278122

Verificado 20 de jul.

Trechos de fonte

1 trecho
Note20 de jul.civitai.com/models/1278122

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