Downloads · 30 days
0
Shiyaku/XL_caulkinumAnimeLine
XL_caulkinumAnimeLine is a machine learning model from Shiyaku. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as openrail.
※このモデルにはいくつかのバリエーションがあることを見逃さないでください Note:Don't miss that there are several variations of this model! View Larger-拡大表示
Downloads · 30 days
0
Access
Public
Updated Jun 16, 2024
Repo size
48.6 GB
Likes
2
Public
Click a slice to open those files.
.safetensors48.6 GB · 100%
From the Hugging Face model README
※このモデルにはいくつかのバリエーションがあることを見逃さないでください
Note:Don't miss that there are several variations of this model!
View Larger-拡大表示

score_9, score_8_up, source_anime, extremely quality extremely detailed, illustration, cute anime face, 1girl, , teen , medium breast , multicolored eyes, , orange hair, medium hair , pixie cut, wavy hair , hair between eyes, , , , school uniform , white long pleated skirt, brown long sleeve hoodie , pantyhose, sneakers , shoulder_bag , happy, :), Firework Display, Crowds, bustle, congestion, bokeh, depth of field, Crowds, bustle, congestion, Forest Sunset, daytime, warm light, sunset, rays light sparkles lens flare, deep shadows, bokeh, depth of field, peerless, scenery, sentimental, golden hour
Negative prompt: text, error, signature, watermark, username, blurry, artist name, sound_effects, copyright, long body, comic, monochrome, crown, tiara, coral, dog, retriever, score_4, score_5, source_pony, source_furry, source_cartoon
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 6, Seed: 3931312973, Size: 1280x512, Model hash: 8fff32315a, Model: XL_caulkinumMgA, Clip skip: 2, kohya_hrfix_enabled: True, kohya_hrfix_block_number: 3, kohya_hrfix_downscale_factor: 2, kohya_hrfix_start_percent: 0, kohya_hrfix_end_percent: 0.35, kohya_hrfix_downscale_after_skip: True, kohya_hrfix_downscale_method: bicubic, kohya_hrfix_upscale_method: bicubic, Version: f0.0.10-latest-64-g257ac265
Sample Heaade = XL_caulkinumMgA
XL_caulkinum AnimeLine is an additional learning & merging model for drawing cute anime-like characters in SDXL. We have prepared several types of AnimeLine with different drawing styles. Please try them out. It is the same as the traditional checkpoints that elaborate prompts do not always produce good results. Quality tags can be added if you feel they are necessary, but they will generally produce good results even without them.
Currently, seven checkpoints are available. We recommend "ACA" and "MgA" for standard anime illustrations, and "FxA" for a style closer to modern game graphics. ADP" is also interesting for additional learning of the deformed game style.
The three models that have been additionally trained based on PONY V6 are "TQ," which is closer to 2.5D, "GeP," which has an anime style, and "GD," which has a deformed style. To reproduce a realistic look with TQ, please include prompts such as "photo realistic".
However, you may need to be prepared for the rare occasion that a good and heartbreaking disintegrating creature is spawned. It is a sign that mankind is carrying a karma deeper than the uncanny valley.
,
,
XL_caulkinum AnimeLineはSDXLで可愛らしいアニメ風のキャラクターを描くための追加学習&マージモデルです。画風違いでいくつかの種類を用意しました。ぜひ試してみてください。凝ったプロンプトが必ずしも良い結果を産むわけではないことは従来のチェックポイントと同じです。クオリティタグは必要と思ったら添えれば良いですが、無くても概ね良い結果をもたらしてくれるでしょう。
現在は七つのチェックポイントを用意しています。標準的なアニメイラストには「ACA」「MgA」を、現代的なゲームグラフィックに近い画風なら「FxA」がおススメです。 デフォルメゲームスタイルを追加学習した「ADP」も面白いです。
PONY V6を根幹とて追加学習を行っているのが 2.5D寄りの「TQ」、アニメ調の「GeP」、デフォルメ調の「GD」の 3モデルです。「TQ」で写実寄りを再現するには「photo realistic」等のプロンプトを含めてください。
ただし稀に良く心臓に悪い崩壊クリーチャーが産まれることもあるので覚悟は必要かもしれません。それは人類が不気味の谷よりも深い業を背負っている証です。
,
,
Negative prompt: text, error, signature, watermark, username, blurry, artist name, sound_effects, copyright, long body, comic, monochrome, crown, tiara, coral, dog, retriever
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 6, Seed: 1, Size: 640x1024, Model hash: 8fff32315a, Model: XL_caulkinumMgA, Clip skip: 2, kohya_hrfix_enabled: True, kohya_hrfix_block_number: 3, kohya_hrfix_downscale_factor: 2, kohya_hrfix_start_percent: 0, kohya_hrfix_end_percent: 0.35, kohya_hrfix_downscale_after_skip: True, kohya_hrfix_downscale_method: bicubic, kohya_hrfix_upscale_method: bicubic, Script: X/Y/Z plot, X Type: Seed, X Values: "1,1111,2024", Fixed X Values: "1, 1111, 2024", Y Type: Checkpoint name, Y Values: "XL_caulkinumMgA.safetensors [8fff32315a],XL_caulkinumACA.safetensors [da6fd904fe],XL_caulkinumGeP..safetensors [94758f694a],XL_caulkinumGD.safetensors [1f9294410e],XL_caulkinumTQ.safetensors [652fdba7a3],XL_caulkinumFxA.safetensors [69a5687954],XL_caulkinumADP.safetensors [e6e8ac1fd1]", Version: f0.0.10-latest-64-g257ac265

,
,
Coffee will increase work efficiency and motivation.
コーヒーは作業効率を高めモチベーションをアップさせるでしょう。
https://ko-fi.com/489489
Thank you for reading to the end.
We hope there is one person who will use it.
最後まで読んでくれてありがとうございます。
使用してくれる方が一人でもいることを願っています。