[VAE Suggested] [SD1.5 + SDXL]
Model trainer/creator: 4BEraser
Uploaded to MoescapeA by Laanver Phi
[Please view the full model detail on CivitAI]
DBv1 Source: https://civitai.com/models/212253?modelVersionId=239341
XLv1 Source: https://civitai.com/models/212253?modelVersionId=299095
XLv1-A3TE Source: https://civitai.com/models/212253?modelVersionId=363094
XLv2 Source: https://civitai.com/models/212253?modelVersionId=362412
XLv3-Δ Source: https://civitai.com/models/212253?modelVersionId=426588
Description
Original description: *THIS CHECKPOINT IS SDXL1.0
About this version:
Base model change to Kohaku Delta.
-----
How-to: Prompting logic is same to KohakuΔ: '1girl, , , '
Negative: 'lowres, error, worst quality, low quality, jpeg artifacts, watermark, signature, username'
Keep pr clean and tidy'. Suggest prompt length < 75 tokens.
Suggestion:
a. CFG: 4-7 (higher will have slightly better anatomy)
b. Sampler: Euler A @ 25steps
c. Resolution: 768 - 1792(ultrawide only), +32 each step.
d. Use DanTagGen.
- Set a low temperature (<1)
- Ban words: sketch, comic, flat color, .*official.*, .*boy.*, mecha, no humans, text, pixel art, speech bubble
- Total tag length: short
e. Use Hires.Fix
- Upscaler: DATx2
- Denoising: 0.4-0.5
f. Use ADetailer.
- face_yolov8n.pt
If you want generate typical color, put color scheme to at first.
Known issues:
- halo / heterochromia / .*focus.* seems to be overfitted in some circumstances. Can be helped by put them in negative tags.
- Background is not stable, keen to draw something unnecessary even if you type simple background, white background
What you should expected from this update:
- Better generalization
- Closer to Blue Archive style
- Beautiful glare
Much improved LoRA compatibility based on KohakuΔ.
- What you should NOT expected from this update:
- Better anatomy, always good hands and feet
- easy to use
- focus on given prompts (compare to previous version)
- multiple person / nsfw support (this is not gonna get any close to pony.)
- detailed background
bluearchive
blue_archive
xl
sdxl
style
trained
checkpoint
sd1.5
sdxl1.0
blue-archive
baxl
trainedcheckpoint
trained_checkpoint
trained-checkpoint
checkpoint_trained
checkpointtrained
checkpoint-trained
4beraser
baxl|bluearchiveflatcelluloidstylefine-tune
bluearchiveflatcelluloidstylefine-tune
blue_archive_flat_celluloid_style_fine-tune
celluloid
Details
Downloads
5,738
Platform
Moescape
Platform Status
Available
Created
11/6/2024
Updated
11/6/2024
Deleted
-
Available On (21 platforms)
SeaArt
BAXL | Blue Archive Flat Celluloid Style Fine-tune | 碧蓝档案赛璐璐平涂画风 [Kohaku Δ & Animagine XL v3] - DBv1SeaArt
BAXL | Blue Archive Flat Celluloid Style Fine-tune | 碧蓝档案赛璐璐平涂画风 [Kohaku Δ & Animagine XL v3] - XLv1-A3TESeaArt
BAXL | Blue Archive Flat Celluloid Style Fine-tune | 碧蓝档案赛璐璐平涂画风 [Kohaku Δ & Animagine XL v3] - XLv1SeaArt
BAXL | Blue Archive Flat Celluloid Style Fine-tune | 碧蓝档案赛璐璐平涂画风 [Kohaku Δ & Animagine XL v3] - XLv2SeaArt
BAXL | Blue Archive Flat Celluloid Style Fine-tune | 碧蓝档案赛璐璐平涂画风 [Kohaku Δ & Animagine XL v3] - XLv3-ΔSeaArt
BAXL Blue Archive Flat Celluloid Style Fine-tune - v1.0TensorArt
BArtstyleDB | XL | 碧蓝档案画风大模型 - XLv1TensorArt
BArtstyleDB | 碧蓝档案画风大模型 | ブルアカ画風モデル - DBv1TensorArt
BAXL (BArtstyleXL) | Blue Archive Flat Celluloid S - XLV2Moescape
BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv2Moescape
BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv3-ΔMoescape
BAXL | Blue Archive Flat Celluloid Style Fine-tune - DBv1Moescape
BAXL | Blue Archive Flat Celluloid Style Fine-tune - DisclaimerMoescape
BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv1-A3TEMoescape
BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv1Yodayo
BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv2Yodayo
BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv3-ΔYodayo
BAXL | Blue Archive Flat Celluloid Style Fine-tune - DBv1Yodayo
BAXL | Blue Archive Flat Celluloid Style Fine-tune - DisclaimerYodayo
BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv1-A3TEYodayo
BAXL | Blue Archive Flat Celluloid Style Fine-tune - XLv1






