Disclaimer
Financial support is very much appreciated, but please do so by donating to my Ko-Fi instead of sending me Buzz, as I currently have no uses for CivitAI Buzz!
Description
An SDXL 1.0 LoRa made by AI_Characters for producing images with an artstyle similar to the artworks of Jean Giraud, also known as Moebius - specifically the artstyle related to one of his last works titled Voyage d'Hermès.
Recommended generation parameters
Weight: 1.0 (adjust down as needed when used in conjunction with other LoRa's)
Model: SDXL 1.0 with 0.9 vae
Steps/Sampler/CFG/Resolution: 25 steps | DPM++ 2M Karras | CFG 7 | 1536x1536
'Kohya Deep Shrink' settings: 4 blocks | 2 downscale | 0 start | 0.35 end | skip = true
Positive prompt: high-definition 8k
Negative prompt: text, blur, low-resolution, low-quality, grainy, glossy, poorly drawn, amateur, poorly shot, compression artifacts
'CLIPTextEncodeSDXL' ComfyUI node resolution: 4096x4096
Trigger words (must be included in the prompt for the LoRa to take effect!)
'flat-color cartoon artwork in jmst artstyle'
Further usage notes
/
Usage permissions
You may not sell this model, merges containing it, or images generated with it.
Credit me when using this model in a merge or hosting it on a generation service.
TL:DR Training Workflow
Train full finetune with a dataset of 20-100 images using this config on a Vast.AI rented A100 80gb GPU
Extract LoRa at 512/512 dimensions using these settings
Resize LoRa to 16 ranks using these settings
Changelog
v1.2 [FINAL]
complete rework; higher epoch count, trained with EMA, reworked captions, reworked dataset preparation - overall much better likeness and quality at the cost of some slight bias and overtraining increase - final version for now
v1.1
retrained with new captions: much better style likeness, slightly better flexibility, less bias towards the subject matter of the training data; added "flat color cartoon" to the trigger word
v1.0
Initial release