An experimental style LoRAs - CSA & CDE
[Disclaimer]
These LoRAs are not made for SD beginners because the CSA & CDE needs to be fine-tuned manually during the generation process
*PLEASE DONT NOT USE FOR COMMERCIAL ACTIVITIES*Background
CSA_Alpha (CSAA) was trained a month ago and it worked with other LoRA well, but CSAA will not open to public
Chanson Style Adder (CSA) aims to apply Kancolle Artist style and improve the generation of Kancolle Character in terms of art style
Chanson Style Adder - Mid-Life Update (CSA-MLU) is an extra resource pack
Chanson Detail Enhancer (CDE) aims to enrich the image's detail which slove the disavandtage of CSA, lack of detail but concept art
*In other word, CDE is the offspring of CSAAPurpose
[CSA]
-Applying kancolle artists style to your generation
-Reducing the amount of prompt without losing details
[CSA-MLU]
-Applying more kancolle artists style
[CDE]
-Assit CSA to become a compheresive style LoRA
-Output more details on [Drafting State], 512*512 res generationInfo
[CSA-v0.1]
-Training with 672 images, with 6800 steps
-512*512 training envirnoment
[CSA-v0.2]
-Training with 672 images, with 9200 steps
-768*768 training envirnoment
[CSA-MLU]
-Training with 318 images, with 10040 steps
-768*768 training envirnoment
[CSA-MLU2]
-Training with 445 images, with 9480 steps
-768*768 training envirnoment
[CSA-SpeicalPack]
-Training with 110 images, with 8800 steps
-768*768 training envirnoment
[CDE]
-Training with 617 images, with 10020 steps
-768*768 training envirnomentRecommended set up
These LoRAs weight: 0.5 for [general case], please go to [LoRA weighting] section for specific setupBasic prompts
[CSA]
-KonishiCSA
-KujouCSA
-ShibafuCSA
[CSA-MLU]
-HoshiakariCSA
-ShizumaCSA
[CSA-MLU]
-AkasakaCSA
-JijiCSA
-UgumeCSA
[CSA-sPack]
-KusadaCSA
[CDE]
-AlphaCDE
-BetaCDE
-GammaCDE
---BREAK LINE---
[CSA-v0.1]
-headgear, hair flaps !NEG!
[CSA-v0.2]
-machinery, weapon, rigging !NEG!
[CDE]
-nsfw !NEG!Testing environment
(masterpiece, best quality), [CSAs/CDEs],
BREAK, 1girl, solo,
BREAK, (Character LoRA prompts),
BREAK, oblique portrait, upper body shot, gradient background, white background,
BREAK, <lora:CSA/CDE:?>, <lora:Character:1>(worst quality, low quality)Samper: DPM++ 2M Karras
Sampling steps: 30 / [ 40 (hires-fix) ]
Res: 512*512
CFG Scale: 7
Clip Skip: 2
Hires-fix: 512*768
Hires-fix steps: 30
Hires-fix Denoising Strength: 0.65Advance Setting
-LoRA weighting
[CSA-v0.1]
[0.50 - 0.60] : recommendation
[CSA: Default]
[0.00 - 0.30] : Weak
[0.31 - 0.60] : Safe
[0.61 - 1.00] : Strong
[CSA: KonishiCSA]
[0.00 - 0.40] : Weak
[0.41 - 0.65] : Safe
[0.66 - 1.00] : Strong
[CSA: KujouCSA]
[0.00 - 0.25] : Weak
[0.26 - 0.69] : Safe
[0.70 - 1.00] : Strong
[CSA: ShibafuCSA]
[0.00 - 0.24] : Weak
[0.25 - 0.65] : Safe
[0.66 - 1.00] : Strong
[CSA-MLU: Default]
[0.00 - 0.30] : Weak
[0.31 - 0.70] : Safe
[0.71 - 1.00] : Strong
[CSA-MLU: ShizumaCSA]
[0.00 - 0.24] : Weak
[0.25 - 0.60] : Safe
[0.61 - 1.00] : Strong
[CSA-MLU: HoshiakariCSA]
[0.00 - 0.35] : Weak
[0.36 - 0.80] : Safe
[0.81 - 1.00] : Strong
[CSA-MLU2: Default]
[0.00 - 0.24] : Weak
[0.25 - 0.69] : Safe
[0.70 - 1.00] : Strong
[CSA-MLU2: AkasakaCSA]
[0.00 - 0.30] : Weak
[0.31 - 0.69] : Safe
[0.70 - 1.00] : Strong
[CSA-MLU2: JijiCSA]
[0.00 - 0.35] : Weak
[0.36 - 0.75] : Safe
[0.76 - 1.00] : Strong
[CSA-MLU2: UgumeCSA]
[0.00 - 0.30] : Weak
[0.31 - 0.74] : Safe
[0.75 - 1.00] : Strong
[CSA-sPack: KusadaCSA]
[0.00 - 0.25] : Weak
[0.26 - 0.84] : Safe
[0.85 - 1.00] : Strong
[CDE: Default]
[0.00 - 0.40] : Weak
[0.41 - 0.70] : Safe
[0.71 - 1.00] : Strong
[CDE: AlphaCDE]
[0.00 - 0.40] : Weak
[0.41 - 0.60] : Safe
[0.61 - 1.00] : Strong
[CDE: BetaCDE]
[0.00 - 0.15] : Weak
[0.16 - 0.69] : Safe
[0.70 - 1.00] : Strong
[CDE: GammaCDE]
[0.00 - 0.24] : Weak
[0.25 - 0.60] : Safe
[0.61 - 1.00] : Strong-LoRA Block Weight (Extension needs to be installed)
[CSA Series]
MIDD: PASS
OUTD: PASS
Other: Unable to determine
[CDE]
MIDD: PASS
OUTD: PASS
Others: Unable to determine-CFG Scale
7-Compatibility
CSA + CDE + ChansonMix + Chanson's LoRAs : Highest
CSA + CDE + CetusMix/Hassaku + Chanson's LoRAs : High
CSA + CDE + CetusMix/Hassaku + others's LoRAs : Close to High
CSA + CDE + other's checkpoint + other's LoRAs : Unable to determine (Need samples)-Multi-apply weight
[CSA/CDE]
Recommended to use | for Mixing art style
E.g. (KonishiCSA:0.7)|(KujouCSA:0.3) OR (AlphaCDE)_(GammaCDE)Anyway, have fun with CSA & CDE
Description
The basic version of CDE
FAQ
Comments (4)
-About CDE-
If you wonder what is AlphaCDE, BetaCDE, GammaCDE
Here's the overview:
-AlphaCDE: Normal anime style
-BetaCDE: NSFW anime style
-GammaCDE: NSFW anime style
In the short term, I used 4k or above-resolution image datasets in BetaCDE & GammaCDE. The reason for using NSFW images is they actually describe the body shape and face well.
And you can generate more precise NSFW image
thanks for the great style If possible, please add the style of Mr. Yorinori Shizuma, one of KanColle's leading painters.
@sinngai30 Thanks for the info. I would schedule this to my baking queue
-About CSAv0.2-
-Retrained with 768*768 resolution environment
-More training steps
If you already using CSA v0.1, you may want to try CSA v0.2 for better image generation in hires-fix & upscale
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.







