Ir para o conteúdo
WorkflowListadosExterno
Fonte aberta

HR Beautify ComfyUI workflow (SDXL): refine after upscale and go as high as 24K — v1.0

HR Beautify (‘HR’ stands for Hires, or High resolution) is an advanced ComfyUI workflow to refine raw upscaled images. It doesn’t include the usual upscale with AI model component, concentrating instead on the best...

Fontecivitai.com/models/1608027
TarefaImagem para imagemFamíliaStable DiffusionEstimado VRAMNot yet characterizedBnota

Perfil de execução

Acesso
Fluxo de trabalho externo
Status
Listados
Fonte
Civitai
Atualizado
2 de out. de 2026

Descrição da fonte

HR Beautify (‘HR’ stands for Hires, or High resolution) is an advanced ComfyUI workflow to refine raw upscaled images. It doesn’t include the usual upscale with AI model component, concentrating instead on the best refinement of upscaled hires images possible, optionally beautifying them with a style transfer.

The workflow includes two ControlNets, for the most powerful and flexible img2img guidance, and two IP Adapters, to enhance images with style transfer and composition or reference guidance. For extra refinement, the Power Lora Loader node is included, supporting a potentially unlimited number of detail or style LoRas. Also included in the workflow are three post processing components: enhancing image’s HDR range, advanced image sharpening and color-matching.

The tiling component that enables hires img2img refining is the widely used Tiled Diffusion (TD), together with Tiled VAE Encode & Decode. TD is compatible with all ControlNet models and can assist in processing images of up to 24K resolution, optionally adding creative detail in the output along the way.

The workflow includes a note with description of the user-controlled parameters. Full description of the HR Beautify workflow and custom nodes it uses can be found on the github wiki pages of the project. To view more examples of hires images refined with the HR Beautify workflow and download full-size png files embedding it, click here .

What you need

Hardware and download-size estimates are not available yet.

Requisitos

Modelos

8

  • CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors

    Não resolvido

    Vision model · Unknown

  • dreamshaperXL_lightningDPMSDE.safetensors

    Não resolvido

    Checkpoint · Unknown

  • ip-adapter_sdxl_vit-h-plus.safetensors

    Não resolvido

    Checkpoint · Unknown

  • ip-adapter-plus_sdxl_vit-h.safetensors

    Não resolvido

    Checkpoint · Unknown

  • Kataragi_inpaintXL-fp16.safetensors

    Não resolvido

    ControlNet · Unknown

  • VAEDecodeTiled

    Possível

    VAE · Unknown

  • VAEEncodeTiled

    Possível

    VAE · Unknown

  • xinsirtile-sdxl-1.0.safetensors

    Não resolvido

    ControlNet · Unknown

Pacotes de nós

37

  • ACN_AdvancedControlNetApply_v2

    Possível

    Pacote de nós · Unknown

  • ACN_ScaledSoftControlNetWeights

    Encontrado

    Pacote de nós · Unknown

  • CheckpointLoaderSimple

    Possível

    Pacote de nós · Unknown

  • CLIPTextEncode

    Possível

    Pacote de nós · Unknown

  • CLIPVisionLoader

    Possível

    Pacote de nós · Unknown

  • ControlNetApplyAdvanced

    Possível

    Pacote de nós · Unknown

  • ControlNetLoader

    Possível

    Pacote de nós · Unknown

  • CR Clamp Value

    Encontrado

    Pacote de nós · Unknown

  • Fast Bypasser (rgthree)

    Não resolvido

    Pacote de nós · Unknown

  • Fast Groups Bypasser (rgthree)

    Não resolvido

    Pacote de nós · Unknown

  • FromBasicPipe

    Encontrado

    Pacote de nós · Unknown

  • GetImageSize+

    Encontrado

    Pacote de nós · Unknown

  • Image Comparer (rgthree)

    Não resolvido

    Pacote de nós · Unknown

  • ImageBlender

    Encontrado

    Pacote de nós · Unknown

  • ImageResize

    Possível

    Pacote de nós · Unknown

  • ImageScale

    Possível

    Pacote de nós · Unknown

  • ImageSmartSharpen+

    Encontrado

    Pacote de nós · Unknown

  • ImpactBoolean

    Encontrado

    Pacote de nós · Unknown

  • ImpactConditionalBranch

    Encontrado

    Pacote de nós · Unknown

  • IPAdapterAdvanced

    Possível

    Pacote de nós · Unknown

  • IPAdapterEmbeds

    Possível

    Pacote de nós · Unknown

  • IPAdapterEncoder

    Possível

    Pacote de nós · Unknown

  • IPAdapterModelLoader

    Possível

    Pacote de nós · Unknown

  • LayerFilter: HDREffects

    Encontrado

    Pacote de nós · Unknown

  • LoadImage

    Possível

    Pacote de nós · Unknown

  • Power Lora Loader (rgthree)

    Não resolvido

    Pacote de nós · Unknown

  • SaveImage

    Possível

    Pacote de nós · Unknown

  • SetUnionControlNetType

    Não resolvido

    Pacote de nós · Unknown

  • SimpleMath+

    Possível

    Pacote de nós · Unknown

  • TiledDiffusion

    Possível

    Pacote de nós · Unknown

  • ToBasicPipe

    Encontrado

    Pacote de nós · Unknown

  • workflow>Control image group

    Não resolvido

    Pacote de nós · Unknown

  • workflow>Control mask image

    Não resolvido

    Pacote de nós · Unknown

  • workflow>KSampler (Advanced) group node

    Não resolvido

    Pacote de nós · Unknown

  • workflow>Reference image

    Não resolvido

    Pacote de nós · Unknown

  • workflow>Resize back logic

    Não resolvido

    Pacote de nós · Unknown

  • workflow>Style image

    Não resolvido

    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

  • HR Beautify is a ComfyUI workflow for refining already-upscaled images with hires img2img processing. It takes an upscaled image, with optional control, reference, or style images, and produces a refined image; AI upscaling is not included.

Fluxo

  • The workflow combines Tiled Diffusion and tiled VAE encode/decode with two ControlNets and two IP Adapters for img2img guidance.

  • Tiled Diffusion can assist with images up to 24K resolution and can optionally add creative detail.

Entradas e saídas

  • The main input is a raw upscaled image; optional inputs include control images or masks, a reference image, and a style image.

  • The output is a refined image that can include style transfer, HDR enhancement, sharpening, color matching, or creative detail.

Configuração

  • The workflow uses SDXL 1.0 as its base model and is published by Minsky91.

Dependências

  • The listed model files include CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors, dreamshaperXL_lightningDPMSDE.safetensors, ip-adapter_sdxl_vit-h-plus.safetensors, and ip-adapter-plus_sdxl_vit-h.safetensors.

  • It also lists Kataragi_inpaintXL-fp16.safetensors and xinsirtile-sdxl-1.0.safetensors as ControlNet files.

  • Listed node components include TiledDiffusion, VAEEncodeTiled, VAEDecodeTiled, and Power Lora Loader (rgthree).

Configuração

  • You can use optional style transfer, composition or reference guidance, and detail or style LoRAs.

  • Tiled Diffusion is compatible with all ControlNet models, and the workflow includes a note describing user-controlled parameters.

Precauções

  • Because AI upscaling is not included, start with an already-upscaled image.

    Sugestão · não verificado

  • Before use, check that ComfyUI has TiledDiffusion, VAEEncodeTiled, VAEDecodeTiled, and Power Lora Loader (rgthree).

    Sugestão · não verificado

Isso precisa ser editado?

Faça login para enviar uma solicitação de edição.

Fontes

1 fonte
CivitaiPrimário
civitai.com/models/1608027

Verificado 19 de jul.

Trechos de fonte

1 trecho
Note19 de jul.civitai.com/models/1608027

Source context: 397 downloads · Type Workflows · Base model SDXL 1.0