OpenArt
OpenArt
Workflows

    My stuff

  • My Workflows

  • Liked Workflows

  • Following Workflows

Go to OpenArt main site
Upload workflow

SD3 - composition repair

5.0

0 reviews
2
1.8K
403
1
Description

SD3 can generate interesting images, but it has a huge problem with the human body. However, I noticed that simply reducing the image size to 60% can, in most cases, eliminate issues with image composition as well as extra hands or legs. This workflow does not solve the problem of having six fingers, etc. :)

Base model:   https://tensor.art/models/751330255836302856/Aderek-SD3-v1  or https://civitai.com/models/600179/aderek-sd3

Look at the image below. You might say: "Hey, nothing's wrong here." Well, that's because you're already seeing the generation based on the reduced size. Below, you have the original image.

Use composition on to use this trick&tips.

Have fun!

Support Paweł Tomczuk on Ko-fi! ❤️. ko-fi.com/aderek514 - Ko-fi ❤️ Where creators get support from fans through donations, memberships, shop sales and more! The original 'Buy Me a Coffee' Page.


Visit my DeviantArt page: Aderek - Hobbyist, Digital Artist | DeviantArt


Discussion

(No comments yet)

Loading...

Author

Aderek

Aderek

62
65.7K
398
337.3K
    sd3-full-workflow-with-composition-repair.json (105.6 kB)

No reviews yet

  • - latest (a year ago)

Primitive Nodes (23)

Anything Everywhere (2)

CLIPTextEncodeSD3 (3)

ControlNetApplySD3 (1)

EmptySD3LatentImage (1)

Fast Groups Bypasser (rgthree) (1)

Image Comparer (rgthree) (2)

ModelSamplingSD3 (1)

Note (6)

PrimitiveNode (1)

ReActorFaceBoost (1)

Reroute (3)

SD3NegativeConditioning+ (1)

Custom Nodes (66)

Chaosaiart-Nodes

  • - chaosaiart_TextCLIPEncode (1)

Comfyroll Studio

  • - CR Overlay Text (1)

  • - CR Upscale Image (2)

  • - CR Latent Input Switch (1)

ComfyUI

  • - LoadImage (5)

  • - ConditioningZeroOut (1)

  • - ConditioningSetTimestepRange (2)

  • - PreviewImage (8)

  • - SaveImage (1)

  • - ConditioningConcat (1)

  • - CLIPTextEncode (2)

  • - VAEEncodeTiled (1)

  • - VAEDecode (3)

  • - KSampler (3)

  • - VAEEncode (2)

  • - ControlNetLoader (1)

  • - ConditioningCombine (2)

  • - CheckpointLoaderSimple (1)

  • - LoraLoader (1)

  • - LatentUpscaleBy (1)

ComfyUI Essentials

  • - RemBGSession+ (1)

  • - ImageRemoveBackground+ (1)

JPS Custom Nodes for ComfyUI

  • - SDXL Resolutions (JPS) (1)

pythongosssss/ComfyUI-Custom-Scripts

  • - ShowText|pysssss (1)

ReActor Node for ComfyUI

  • - ReActorFaceSwap (2)

  • - ReActorRestoreFace (1)

SD Prompt Reader

  • - SDPromptSaver (3)

WAS Node Suite

  • - Text Multiline (2)

  • - Mask Dominant Region (1)

  • - Mask Crop Region (1)

  • - Image Crop Location (1)

  • - Image Paste Crop (1)

  • - Image Lucy Sharpen (1)

  • - Image Filter Adjustments (1)

  • - CLIPSeg Masking (1)

  • - Image Paste Crop by Location (1)

  • - Image Remove Background (Alpha) (1)

  • - Image Blend (2)

  • - Image Resize (1)

  • - BLIP Analyze Image (1)

  • - BLIP Model Loader (1)

Checkpoints (1)

AderekSD3.safetensors

LoRAs (1)

sd3_easy_illustrator.safetensors