Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
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...
Profil d'exécution
Description de la source
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.
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
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.
Suggestion · non vérifié
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.
Suggestion · non vérifié
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.
Suggestion · non vérifié
For larger inputs, replace “upscale image by” with forced resize so the longest side is no more than 2048.
Suggestion · non vérifié
For more aggressive sharpness, resize the image, pass it through the 1xReFocus upscaler, then run KSampler.
Suggestion · non vérifié
The description warns that images larger than 1280 can produce mutations such as double knees.
No license is specified for this workflow.
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 1101 downloads · Type Workflows · Base model Other
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
Estimation des besoins VRAM
Estimation indisponible
440 MB sur 2 de 7 fichiers de modèle. Total des fichiers du modèle + 25 % de surcharge de chargement + 2 Go de tampon d'exécution, arrondi à l'unité supérieure.
Exigences
Exigences 15Upscaler · 63.9 MB · PTH · Unknown
bigLove_xl1.safetensors
Non résoluCheckpoint · Unknown
LoRA · 376 MB · SAFETENSOR · Unknown
ImageUpscaleWithModel
Non résoluUpscaler · Unknown
UpscaleModelLoader
Non résoluUpscaler · Unknown
VAEDecode
Non résoluVAE · Unknown
VAEEncode
Non résoluVAE · Unknown
CheckpointLoaderSimple
PossiblePack de nœud · Unknown
CLIPTextEncode
PossiblePack de nœud · Unknown
ImageCASharpening+
TrouvéPack de nœud · Unknown
Pack de nœud · Unknown
KSamplerAdvanced
PossiblePack de nœud · Unknown
LoadImage
PossiblePack de nœud · Unknown
LoraLoader
PossiblePack de nœud · Unknown
PreviewImage
PossiblePack de nœud · Unknown
