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...
Laufzeitprofil
- Zugriff
- Externer Arbeitsablauf
- Status
- Aufgelistet
- Quelle
- Civitai
- Aktualisiert
- 19. Aug. 2026
Quellenbeschreibung
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.
Anforderungen
Modelle
7- Gefunden
Upscaler · 63.9 MB · PTH · Unknown
bigLove_xl1.safetensors
Nicht aufgelöstCheckpoint · Unknown
dmd2_sdxl_4step_lora_fp16.safetensors
Nicht aufgelöstLoRA · Unknown
ImageUpscaleWithModel
MöglichUpscaler · Unknown
UpscaleModelLoader
MöglichUpscaler · Unknown
VAEDecode
MöglichVAE · Unknown
VAEEncode
MöglichVAE · Unknown
Knotenpakete
8CheckpointLoaderSimple
MöglichKnotenpaket · Unknown
CLIPTextEncode
MöglichKnotenpaket · Unknown
- Gefunden
Knotenpaket · Unknown
ImageScaleBy
MöglichKnotenpaket · Unknown
KSamplerAdvanced
MöglichKnotenpaket · Unknown
LoadImage
MöglichKnotenpaket · Unknown
LoraLoader
MöglichKnotenpaket · Unknown
PreviewImage
MöglichKnotenpaket · Unknown
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Zweck
This DMD2 LoRA workflow takes an image through an upscale and refine pass, aiming to produce an enlarged image with subtle fixes.
Fluss
ImageCASharpening+ is included from the ComfyUI_essentials node pack.
Eingaben und Ausgaben
The creator describes using it at the end of image generation; LoadImage and PreviewImage are listed among its nodes.
Abhängigkeiten
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.
Konfiguration
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.
Vorschlag · nicht geprüft
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.
Vorschlag · nicht geprüft
For stronger sharpness, resize the image, pass it through the 1xReFocus upscaler, then run KSampler.
Vorschlag · nicht geprüft
Vorsichtsmaßnahmen
The creator recommends 768–1280 input images and warns that larger images can produce mutations such as double knees.
No license information is listed.
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 Quelle
Quellen
1 QuelleQuellenauszüge
1 Auszug
Quellenauszüge
1 AuszugSource context: 1101 downloads · Type Workflows · Base model Other
