PerfectHD
5.0
0 reviewsDescription
Welcome to perfect HD
This workflow is capable of creating HD quality 8k images, 44mb+ i don't know how much more it can do, my 12gb card is limited there.
Previews are cropped from the 8k images, this place has a limit on sizes
You are not limited to 8k, anything lower works just as well.
With IP adaptor and now reactor, this can reliably copy a person likeness while following your prompts.. This can allow some very creepy things IMO with nudity. Be responsible and don't share photos of real people in situations you would not want to be put in.
Features
- XL or 1.5 base generation - LCM used can be removed.
- 2 base models - 2 extras for use with enhancers
- Full upscale with 1.5
- Full subject cutout and enhance
- Decent hand fixing with meshgraphormer
- Full face with hair cutout enhance
- inner face enhance
- face features enhance (eyes, nose, mouth)
- Aux detector to enhance something else (breasts, clothing, etc)
- All enhancement steps use cutouts to avoid full scale renders
- Any relevant areas have optional inpainting
- Any relevant areas have optional IP adaptor Refs
- All areas have separate prompts/Lora
V1.0
- fixed faces not working for multiple people
- fixed padding issues that came up rarely but caused improper blending
- fixed face detection drop size being too large, made drop size a main option due to its usefulness
- face parts enhance each option on its own now. Can do just 1 eye, or just mouth.
- added custom subject paste back to avoid bad paste orders on some photos.
- added 1 extra aux detailer because we all know why you need 2 :P
- added reactor face swap, it's not great on 8k but decent on others
- added model upscale option
- added Downscale for all previews, so my browser would stop freaking out. Turns out having 10 8k previews makes it freak out.
Discussion
(No comments yet)
Loading...
Resources (1)
Reviews
No reviews yet
Versions (1)
- latest (3 months ago)
Node Details
Primitive Nodes (422)
Display Int (rgthree) (36)
Fast Groups Bypasser (rgthree) (39)
Lora Loader Stack (rgthree) (7)
MaskFix+ (17)
Note (9)
Power Prompt - Simple (rgthree) (18)
PrimitiveNode (44)
Reroute (252)
Custom Nodes (426)
- CR Image Input Switch (10)
- CR Image Input Switch (4 way) (4)
- CR ControlNet Input Switch (1)
ComfyUI
- LoraLoaderModelOnly (4)
- RescaleCFG (4)
- FreeU_V2 (4)
- CLIPSetLastLayer (4)
- ImageScale (11)
- MaskToImage (17)
- VAEEncode (11)
- PreviewImage (43)
- ImageScaleBy (26)
- DifferentialDiffusion (5)
- VAEDecode (12)
- SetLatentNoiseMask (10)
- KSamplerAdvanced (12)
- EmptyLatentImage (1)
- CLIPVisionLoader (1)
- CheckpointLoaderSimple (4)
- UpscaleModelLoader (1)
- VAELoader (2)
- LoadImage (1)
- PatchModelAddDownscale (2)
- ImageUpscaleWithModel (1)
- GetImageSize+ (26)
- MaskPreview+ (11)
- ImageRemoveBackground+ (2)
- RemBGSession+ (1)
- SegsToCombinedMask (6)
- UltralyticsDetectorProvider (6)
- SAMLoader (2)
- ImpactSimpleDetectorSEGS (6)
- FacialPartColoringFromPoseKps (4)
- DWPreprocessor (1)
- PrepImageForClipVision (3)
- IPAdapterAdvanced (4)
- IPAdapterModelLoader (3)
- ScaledSoftControlNetWeights (10)
- ACN_AdvancedControlNetApply (10)
- DiffControlNetLoaderAdvanced (1)
- ControlNetLoaderAdvanced (2)
- ImageSelector (49)
- MeshGraphormer+ImpactDetector-DepthMapPreprocessor (1)
- CropFace (1)
- Cut By Mask (14)
- Image To Mask (10)
- Change Channel Count (9)
- Combine Masks (8)
- Separate Mask Components (6)
- Paste By Mask (30)
- Mask To Region (6)
- ReActorFaceSwap (2)
- Image Crop Face (1)
Model Details
Checkpoints (4)
aZovyaRPGArtistTools_v3.safetensors
crystalClearXL_ccxl.safetensors
kawaiiRealisticAsian_v04.safetensors
realisticVisionV40_v40VAE.safetensors
LoRAs (6)
LCM_LoRA_Weights_SDXL.safetensors
MS_Real_Cum_on_Tongue_Lite.safetensors
cum_b1.safetensors
lcm\SD1.5\pytorch_lora_weights.safetensors
lcm\SDXL\pytorch_lora_weights.safetensors