IP Adapter Character Consistancy, part II
5.0
0 reviewsDescription
It's not easy to create several photos with the same character... This version works with SDXL models (recommended https://civitai.com/models/237678?modelVersionId=351046 ) on an RTX 3060ti GPU or better.
At the beginning, you upload a startup image (size about 1024x1024) and enter the path to a folder with six images, from which the system will load poses. The system will then create six images and proceed to try to apply identical outfits to the character. The better models you have access to detect items of clothing, the better the effect will be.
This set only creates images in the basic form, i.e. if you want to get better results, you need to add e.g. a face detailer. Have fun with this PE. Financial support welcome ;)
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...
Resources (8)
Reviews
No reviews yet
Versions (1)
- latest (10 months ago)
Node Details
Primitive Nodes (9)
AV_IPAdapter
Get image size
IPAdapterApply
Reroute
Custom Nodes (52)
ComfyUI
- CLIPTextEncode
- ControlNetLoader
- VAEDecode
- KSamplerAdvanced
- VAEEncodeForInpaint
- PreviewImage
- KSampler
- ConditioningConcat
- LoraLoader
- CLIPVisionLoader
- CheckpointLoaderSimple
- ControlNetApply
- ControlNetApplyAdvanced
- LoadImage
- SaveImage
- EmptyLatentImage
- SAMLoader
- LoadImagesFromDir //Inspire
- Zoe-DepthMapPreprocessor
- DWPreprocessor
- IPAdapterModelLoader
- PrepImageForClipVision
- Text _O
- ReActorFaceSwap
- ReActorLoadFaceModel
- SDXLPromptStyler
- GroundingDinoModelLoader (segment anything)
- GroundingDinoSAMSegment (segment anything)
- Seed
Model Details
Checkpoints (1)
Aderek DPO V2.safetensors
LoRAs (1)
sdxl_lora_dream.safetensors