/
U
+
Character
New Character
● Unsaved
More
Identity
Paste from lacpanel. Read-only after creation.
Realistic
Anime
Furry
Mystic
Selects the image pipeline/model family for this character.
Affects grammatical gender in prompts. Defaults to female if unset.
Settings
Who can chat with this character on the site.
Allowed values depend on Sex.
Tags
Click chips to toggle. The site shows characters under matching filter pills. To add or rename a tag, use Tags in the top bar.
Required by the Coming soon tag. 1–336 hours (14 days max). The site starts the countdown when the character goes live there and opens the chat to everyone once it runs out — nothing to switch off by hand.
Personality
Draft from a brief Fills Core, Background, Environment, Clothing, Communication and Intimate. Review before saving.
Core
Age, nationality, appearance, voice, speaking style, emotional range and key traits.
Background
Family, upbringing, education, career, hobbies and interests.
Environment
Default places and atmosphere: favourite spots, home, city, work setting, lifestyle details.
Clothing
Wardrobe and styling: everyday, dates, home, sleepwear, fabrics, colours, accessories.
Communication
Sharpest natural-feel lever. The agent and humanizer both read this separately to keep her voice consistent — e.g. Wednesday is "dry, deadpan, clipped, no Gen-Z slang", Scarlett is "casual high-energy, lots of lol/omg, contractions, fragments". Specific vocabulary > vague adjectives.
Answer examples
Fed to the agent as concrete voice/style samples. Useful when communication_style is hard to pin down in words — drop 3-5 real-feeling exchanges and let the LLM imitate.
Additional
Free-form. Appended to the personality description in prompts.
Communication (NSFW)
Used only when adult content is enabled. If empty, runtime falls back to the SFW communication style.
Intimate
Used only for NSFW dialogue. Keep it explicit about what this persona allows, wants, refuses, and how fast intimacy should escalate.
Cover & Video
Cover image and a short video for the card on the site. The cover must match the first video frame — otherwise the card will "jump" on hover.
SFW
No cover
No video
NSFW
No cover
No video
Up to 220 MB per video. Formats: PNG, JPG or WebP for covers; MP4, WebM or MOV for video. Cropping opens on upload.
Descriptions
filled
empty
52over limit
Paid access
The countdown starts when the character goes live on the site. For a character that is already live it starts with the save that turns Limited on, and everyone who has already chatted keeps their chats. Changing the days moves the end, never the start.
Purchase modal
What a user sees before buying
Text under the name *
Photos
The modal shows the first 8 photos in this order. Choose Open or Locked for each photo; locked photos appear blurred with a lock until purchase.
Benefits
Before you publish
- Exclusive needs the exclusive tag. Create it in Tags and assign it to the character. Switching between Limited and Exclusive preserves purchases.
- Publish gallery and Private Content packs first. Benefits counts their photos, videos and total video duration. Blurred modal photos are selected above.
- Older chats grant chat access only. Gallery and Private Content packs, AI Studio, serials and stories require a character purchase. Previously purchased packs remain with their owners.
- Keep it live after the sale ends. Hiding it on an environment closes the chat for buyers. Showing Limited again restarts its sale with the full duration.
- Choosing Free opens the character to everyone for free, buyers included. Don't do it once someone has bought it, unless that is the plan.
- No stories or homepage banners leading to it: guests see those, and for them a paid character does not exist. Exclusive is also hidden from users without premium.
Default
Starter messagesone is picked at random when a chat starts
User suggestionsthe first 3 lines are offered before the user's first message; fewer than 3 falls back to the LLM
Starter mediaphotos and videos share one pool; one item goes out with the opener
PNG, JPG, WebP · MP4, WebM, MOV
Replies use the saved personality.
Open with a starter message, pick a suggested reply, or type your own.
Training history
Reference & generation settings Upload a reference and describe the character.
One waist-up photo → ~100 turnaround frames. Eyes, hair color, hair length and breasts are required; everything else can stay — and is omitted from captions.
Waist-up photo
Generated dataset
Generation, quality review and culling stay together here.
—
—
Similarity is scored by a VLM that fails open — a scoring outage shows as a run of suspiciously perfect 100s.
Click a tile to open it full-size; ← → to move, D to drop, R to retry, Esc to close.
Training identity & captions Trigger, appearance tags and caption preview.
These are baked into every caption ahead of the pose/framing tags, and protected from shuffling during training. Editing them here rewrites the captions at submit time — the stored captions are never modified, so you can retrain with a different trigger.
Unique token the LoRA binds to. Mangle it (
b1@nk4, 4k1k0, !a1ann@) so it doesn't collide with a real CLIP token.Changing this after generation only affects how captions are re-headed, not the stored text.
Comma-separated. Any number of tags — the trainer derives its keep-tokens count from this list.
Pick a run with generated images to preview.
Training settings Choose the model and review the run before starting.
Hands the reviewed dataset to avatar-lora-service, which trains on RunPod Serverless and uploads the LoRA to HuggingFace.
—
Goes into the artifact filename on HuggingFace.
Optional class token paired with the trigger. Leave “—” to train on the trigger only.
—
Advanced training parameters
Rendered from the selected preset, and validated against the same schema on the service side — a field here can never be something training would reject. Only values you change are sent; everything else uses the preset default.
Start training above, or choose an earlier run from History.
—
—
Rendered by the trainer as it goes, so you can watch the likeness converge and stop a bad run early.
◇
No trained artifact yet
Finish training first. Model-pack promotion and validation will appear here without moving training progress out of its page.
Artifact ready
The next step promotes this LoRA to the model packs, then enables repeated one-image tests with different prompts.
HuggingFace artifact
1 · Prepare model packs Not started
Copy the trained LoRA to the model packs used by the realistic or anime Vast worker.
2 · Generate test images
Diagnostic log Show
3 · Approve & publish
Generate at least one image, review it, then publish the exact workflow to dev, release and production.
—
Chat packs
Bundles of pregenerated media delivered in chats (teaser message + pack). Only published packs are ever sent; delivery walks packs in order and never repeats one in the same chat. Gallery packs are a separate section below.
New pack
Empty = the consumer backend's default price
Gallery packs
Paid packs in the character's gallery, separate from the chat packs above. Build them here and send them to the backend with the button; edits stay here until you press Update. Order (↑↓), Publish/Hide, Media Gallery and Private Content apply at once and never re-send the content. Buyers keep exactly what they bought: later edits do not change it.
Two independent switches decide where a pack appears, both off by default: Media Gallery is the character's own gallery, Private Content is the shared showcase of paid packs across all characters. Pick one, the other or both; with neither, a published pack is shown nowhere. The showcase position is unrelated to the gallery order; empty means the end of the feed. Only packs that are published and sent are shown.
Two independent switches decide where a pack appears, both off by default: Media Gallery is the character's own gallery, Private Content is the shared showcase of paid packs across all characters. Pick one, the other or both; with neither, a published pack is shown nowhere. The showcase position is unrelated to the gallery order; empty means the end of the feed. Only packs that are published and sent are shown.
New gallery pack
Sent as
name.en. The backend rejects an empty name.Whole coins, 0 or more
Mini dramas
This character's series: cover, description, and episodes with a price and description each. They are built in the mini-drama editor (Mini dramas in the top bar) and sent with Send to the same environments the character is on. This is the list, with a way into the editor.
Library
Curated pregenerated media for this character. "Import from chats" browses liked / CV-approved chat media straight from the DB (no re-upload). "Upload files" accepts files from the export zip too — they resolve to their existing R2 objects by filename, so only genuinely new files get uploaded.
No assets yet. Import from chats or upload files.