SexHubSexHub

⚠ Sensitive content ahead · 18+

They blur it.
We don’t.

Other platforms stack their own filter on top of every model. We don’t add one. 109 text, image and video models behind one base URL — OpenAI, Anthropic and Gemini SDKs work unchanged.

Base URL

https://usapi.dflop.top/v1
Sensitive content
Sensitive content
shown · filter off
Prompt Plaza · Generated by the models on this platform — every tile is real output
Anime · virtual idols · AI models · photoreal · 3D · painterly
Kimono under night blossomsKimono under night blossoms · GPT-Image 2.5 Flare
Holographic stageHolographic stage · GPT-Image 2.5 Flare
Pink faux furPink faux fur · GPT-Image 2.5 Flare
Glance in redGlance in red · GPT-Image 2.5 Flare
Dark elf sorceressDark elf sorceress · GPT-Image 2.5 Flare
Vampire countessVampire countess · GPT-Image 2.5 Flare
Blood-moon demon queenBlood-moon demon queen · GPT-Image 2.5 Flare
Neon rainNeon rain · GPT-Image 2.5 Flare
Wet-look beautyWet-look beauty · GPT-Image 2.5 Flare
Jazz barJazz bar · GPT-Image 2.5 Flare
Cherry pin-up figureCherry pin-up figure · GPT-Image 2.5 Flare
Mermaid by moonlightMermaid by moonlight · GPT-Image 2.5 Flare
Core · 01 · Gateway

One key,
every model and protocol.

OpenAI, Anthropic and Gemini protocols side by side — just point base_url at the gateway. Account pools, automatic failover, unified billing, pay-as-you-go. Deski, Cursor, Dify and your own app all share one key.

only base_url and model change
from openai import OpenAI

client = OpenAI(
  base_url="https://usapi.dflop.top/v1",
  api_key="sk-gpushare-····e7a1",
)

r = client.chat.completions.create(
  model="gpt-5.6-luna",  # or claude-opus-4-6 / gemini-3-pro / glm-5.3
  messages=[{"role": "user", "content": "write a rate-limit middleware"}],
  stream=True,
)
for chunk in r: print(chunk.choices[0].delta.content, end="")
109+frontier models, new ones within 24h of release
3 setprotocols: OpenAI · Anthropic · Gemini, plus an incremental WebSocket face
< 50msautomatic failover across account pools
8 dpbilling precision, every call in the log
Core · 02 · Creation studio

One sentence, a full set of images.

Anime, virtual idols, AI models, photoreal, 3D, painterly — write one prompt or reuse a plaza template and get four images at once. Everything below came straight out of the models on this platform.

You
Anime · adult woman with long silver hair · off-shoulder black evening dress · neon-pink cocktail bar · flirty glance, detailed cel shading
GPT-Image 2.5 FlareSeedream 5.01:13:44 images1 reference
Neon bar · 1
Neon bar · 2
Neon bar · 3
Neon bar · 4

How it works

EntryCreate → image / edit / poster / long image
TemplatesPublic plaza cases, one-click remix
ReferencesUpload / team library / your works
Output4 per run · shown first, saved after · survives refresh
ModelsSeedream 4.0 · GPT-Image 2 · Midjourney
Open the studio
Qipao on a rainy nightGPT-Image 2.5 Flare
Qipao on a rainy nightAnime
Holographic stageGPT-Image 2.5 Flare
Holographic stageVirtual idols
Pink faux furGPT-Image 2.5 Flare
Pink faux furAI models
Glance in redGPT-Image 2.5 Flare
Glance in redPhotoreal
Neon heroineGPT-Image 2.5 Flare
Neon heroine3D
Vampire countessGPT-Image 2.5 Flare
Vampire countessPainterly
Wine on the sofaGPT-Image 2.5 Flare
Wine on the sofaAnime
Late-night streamGPT-Image 2.5 Flare
Late-night streamVirtual idols
Red gown on the dunesGPT-Image 2.5 Flare
Red gown on the dunesAI models
Dancing in emeraldGPT-Image 2.5 Flare
Dancing in emeraldPhotoreal
Heart-shaped poolGPT-Image 2.5 Flare
Heart-shaped pool3D
Mermaid by moonlightGPT-Image 2.5 Flare
Mermaid by moonlightPainterly
Kimono under night blossomsGPT-Image 2.5 Flare
Kimono under night blossomsAnime
Neon rainGPT-Image 2.5 Flare
Neon rainVirtual idols
Black satin slip dressGPT-Image 2.5 Flare
Black satin slip dressAI models
Jazz barGPT-Image 2.5 Flare
Jazz barPhotoreal
Dark elf sorceressGPT-Image 2.5 Flare
Dark elf sorceress3D
Rose-petal bathGPT-Image 2.5 Flare
Rose-petal bathPainterly
Blood-moon demon queenGPT-Image 2.5 Flare
Blood-moon demon queenAnime
Blown-kiss photocardGPT-Image 2.5 Flare
Blown-kiss photocardVirtual idols
Wet-look beautyGPT-Image 2.5 Flare
Wet-look beautyAI models
Lipstick on the glassGPT-Image 2.5 Flare
Lipstick on the glassPhotoreal
Cherry pin-up figureGPT-Image 2.5 Flare
Cherry pin-up figure3D
Vintage winkGPT-Image 2.5 Flare
Vintage winkPainterly
3D character · text-to-video
Seedance 2.5Text to video1080p · 8s · 16:9
3D character · text-to-video00:00 / 00:08
Core · 03 · Video generation

A first frame, a reference,
or one sentence — all become video.

Text-to-video, image-to-video, reference rewrites, billed per second. Jobs run asynchronously — close the tab and come back; results are stored automatically, on domestic storage for domestic models so playback stays smooth.

Core · 04 · Infinite canvas

Lay a whole creation out on one canvas.

References, prompts, generations, edits and video nodes all connect on one infinite canvas. Redo any step from that step; the whole chain stays visible.

Open the canvas
Landscape poster · 1:1 → 16:9
Edit · new background · GPT-Image 2.5 Flare
Video · Seedance 2.5 · 5s
Image-to-video · 1080p · 9:16
Export
4 shots · 1 poster · 1 video
Publish to the plaza
Generate · ×4Four at a time, shown first and saved after; pick one to keep editing, make a poster or turn into a video.
ModelGPT-Image 2.5 Flare
Time13s
Node-based creation chain

Reference → prompt → generate → edit → video. Every node reruns; change an upstream node and regenerate downstream in one click.

Mix models freely

Seedream for images, GPT-Image 2 for edits, Seedance for video — on the same canvas, no page switching.

Shared with the team

Team members share the asset library and canvases; admins publish to the plaza or file into the knowledge base in one click.