DMD2 essential upscaler/refiner workflow — v1.0

DMD2 essential upscaler/refiner workflow is for upscaling and refining an input image; it includes image-scaling and model-based upscaling steps and provides a PreviewImage node for viewing the image output. The description recommends 768–1280 input dimensions.

The graph includes LoadImage, ImageScaleBy, ImageUpscaleWithModel, KSamplerAdvanced, LoRA loading, VAE encoding and decoding, and PreviewImage.

The description suggests resizing an image, upscaling it, and then running KSampler; it also suggests an optional 1xReFocus pass for more aggressive sharpness.

Sugestão · não verificado

Provide an image through LoadImage; PreviewImage is included to view the image output.

The workflow is published by Luntrix on Civitai as model 1278122.

Before use, verify that the listed model files and workflow nodes are available in your setup.

Sugestão · não verificado

The workflow lists these model files: 4x_foolhardy_Remacri.pth, bigLove_xl1.safetensors, and dmd2_sdxl_4step_lora_fp16.safetensors.

Listed nodes include CheckpointLoaderSimple, CLIPTextEncode, ImageCASharpening+, ImageScaleBy, ImageUpscaleWithModel, KSamplerAdvanced, LoadImage, LoraLoader, PreviewImage, UpscaleModelLoader, VAEDecode, and VAEEncode.

Try start_at_step values from 60–68 at KSampler. Values closer to 70 are described as having less impact, while smaller values are described as making more fixes with more checkpoint intervention.

Sugestão · não verificado

For larger inputs, replace “upscale image by” with forced resize so the longest side is no more than 2048.

Sugestão · não verificado

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

Sugestão · não verificado

The description warns that images larger than 1280 can produce mutations such as double knees.

No license is specified for this workflow.