Redistribution is prohibited.
If you like my work, consider giving me more support, likes, buzz, feedback and reactions.
Commissions are available. DM me for details.
ABOUT THE MODEL
Remielle Dan From Zenless Zone Zero
20260726v3
Trained on Anima Base v1
I adjusted the dataset to see if it would improve the clothing details, but it still hasn't met my expectations. Training with Anima costs about twice as much as SDXL, so it ended up costing me quite a bit.
Update
3+ outfits.
Improved clothing learning, making each outfit easier to generate with details that more closely match the original. +1
Carefully separated caption tags that are likely to conflict with one another. +1
Issues
The costume details lack accuracy.
This model is designed for a specific art style, so the @ symbol is intentionally bound to its corresponding trigger word. If you'd like to blend it with other artist styles or experiment with different stylistic combinations, consider using a LoRA or tools such as Anima-Artist-Mixer to achieve the desired result.
If the style is not stable enough, consider increasing the weight of the tag "@remielledan"
Consider adding tag "realistic" to help preserve natural body proportions.
When the face becomes blurry, consider using ADetailer to fix it.
When the output becomes blurry, consider using MultiDiffusion to fix it.
TRIGGER WORDS
Black
(@remielledan:1.1),realistic,
pink hair,bob hair,side-swept bangs,black hair bows,silver hairpin,a silver four-pointed-star-hairclip on hair,pink eyes,black lace face mask,black gothic cyber dress with silver star ornaments,sheer black sleeves,black long flared gloves,(black wings:1.1),black lace thighhighs,black pointed-heels with a studded strap,White
(@remielledan:1.1),realistic,
pink hair,bob hair,side-swept bangs,large-violet-fabric-hairbow,2 silver four-pointed star-hairclips on hair,white headband,pink eyes,silver hair ribbon,white and silver corset minidress with swallowtail,the bodice features front-lacing adorned with two small purple and blue tassels,white wings,white detached flared sleeves,white stockings with bow,silver slingback-heels,Swimming Suit
(@remielledan:1.1),realistic,
pink hair,bob hair,side-swept bangs,large white-fabric-hairbow,silver-blue hairband with shell ornament,pink eyes,white and light blue fantasy-style halter leotard,thin bracelets and small metallic accessories on the arms,one upper arm has a pale lavender ribbon decoration,thin belt-like decoration with pearl-like beads crosses the waist,sheer lavender-white wrap skirt with translucent swallowtail,white ankle strap heel with open toes and small blue bow decorationsYou could find the example prompts from my showcase.
My prompts are basically composed in the order of [character traits] + [clothing] + [camera]+ [customize content] + [background], and you can delete or modify them as needed.
Requirements
Checkpoints: Anima
Recommended Tools: ForgeNeo, ComfyUI
Recommended Step: 20~30
Recommended weight: 0.6~1
Recommended size: 768*1344, 832*1216, 896*1156, 1024*1024, 1344*768, 1216*8
32, 1156*896
I’ve set the gallery moderation of this post to “R”, so explicit content may not appear on this page.
ARCHIVES
20260716v2.5
Trained on Anima Base v1
Update
2+ outfits.
Improved clothing learning, making each outfit easier to generate with details that more closely match the original.
Carefully separated caption tags that are likely to conflict with one another.
Trigger Words
Black
(@remielledan:1.1),realisic,
pink hair,bob hair,side-swept bangs,black hair bows,silver hairpin,a silver star-hairclip on hair,pink eyes,black lace face mask,black gothic cyber dress with silver star ornaments,sheer black sleeves,black long flared gloves,black wings,black lace thighhighs,black pointed heels with a studded strap,White
(@remielledan:1.1),realisic,
pink hair,bob hair,side-swept bangs,large-violet-fabric-hairbow,two silver four-pointed star-hairclips on hair,no hairpin,white headband,pink eyes,white and silver corset minidress with swallowtail,the bodice features front-lacing adorned with two small purple and blue tassels,white wings,white detached flared sleeves,white stockings with a bow,silver slingback-heels,20260709v2
Trained on Anima Base v1
Finally managed to tune this style. It's now closer to the official artwork.
Zenless Zone Zero has an outstanding art style. However, its official artwork is heavily covered with film grain and various kinds of noise. Although these illustrations appear to be simple cel-shaded images to the human eye, for a model the size of Anima, those seemingly insignificant artifacts actually corrupt the underlying visual structure.
If the official artwork is used directly as training data, it results in severe information loss and distortion—film grain, JPEG artifacts, and other compression noise prevent the model from faithfully learning and reproducing the style.
In the end, I carefully curated the dataset and even created some of my own training images, making the style much more learnable for Anima while minimizing information loss during training.
Perhaps once a larger and more capable base model becomes available, this kind of complicated preprocessing won't be necessary anymore.
Trigger Words
Black
@remielledan,
pink hair, bob hair, side-swept bangs, black hair bows, silver-hairpins, a silver star-hairclip on hair, pink eyes, pointy ears, black gothic cyber dress with silver star ornaments, white high collar, sheer black sleeves, black long flared gloves, black wings, black lace thighhighs, black pointed heels with bows,White
@remielledan,
pink hair,bob hair,side-swept bangs,large-violet-fabric-hairbow,two silver star-hairclips on hair,white headband,pink eyes, pointy ears,form-fitting white and silver strapless bodice,white wings,white detached flared sleeves,white stockings with a bow,silver-high-heels with a small decorative bow,20260704v1
Trained on Anima Base v1
Features
1+ outfits.
Issues
Style is not stable enough, consider increasing the weight of the tag "a masterpiece image of 7em1e11e" or adding the tag "anime screenshot"
The costume details lack accuracy.
When the face becomes blurry, consider using ADetailer to fix it.
When the output becomes blurry, consider using MultiDiffusion to fix it.