Go to OpenArt main site
Upload workflow

An attempt at Full-Character Consistancy. (Using SDXL model with Lightning 8-step lora)

5.0

1 reviews
127
25.2K
5.3K
8
Description

My attempt at Full Character Consistancy...

Although 100% consistency may be almost impossible to achieve with SD (yet).

A work in progress ;)


I generated 4 portrait faces with another basic workflow.

These are then all fed into IPAdapter FaceID plus v2 SDXL.

(See resource download links on the right of this page)

To Keep the same Character in different poses consistant,

you need to keep the seed and prompt fixed when you have found a good prompt with good results.

Then you can change the character's pose with an image and the OpenPose controlnet... (I will add this soon)...

#NeuraLunk

Discussion

(No comments yet)

Loading...

Author

399
308.3K
4.3K
1.1M
    ComfyUI_00698_.png (1.3 MB)
    ComfyUI_00742_.png (1.1 MB)
    ComfyUI_00738_.png (1.1 MB)
    ComfyUI_00714_.png (1.2 MB)

No reviews yet

  • - latest (10 months ago)

  • - v20240225-122427

Primitive Nodes (10)

IPAdapterApplyFaceID (1)

InsightFaceLoader (1)

Note (1)

PrimitiveNode (1)

Reroute (2)

Seed (rgthree) (1)

Text box (3)

Custom Nodes (32)

Comfyroll Studio

  • - CR Image Output (1)

  • - CR SDXL Aspect Ratio (1)

ComfyUI

  • - CLIPSetLastLayer (1)

  • - CLIPTextEncodeSDXL (2)

  • - PreviewImage (5)

  • - ImageBatch (3)

  • - KSampler (1)

  • - VAEDecode (1)

  • - FreeU_V2 (1)

  • - CheckpointLoaderSimple (1)

  • - LoadImage (4)

  • - LoraLoader (1)

  • - CLIPVisionLoader (1)

  • - IPAdapterModelLoader (1)

  • - Bus Node (3)

  • - Image Crop Face (4)

Checkpoints (1)

realcartoonXL_v6.safetensors

LoRAs (1)

sdxl_lightning_8step_lora.safetensors