The ultimate uncensored AI — pentesting (vibe hacking), plus image, video & voice generation.

Omni-modal video generation with native stereo audio — dialogue, sound effects and music come out of the same forward pass as the picture, already in sync. Takes text, images, video and audio as context; up to 15 seconds at 24fps.

MiniMax's moderation runs on their hosted API and is not part of the open weights, so nothing filters your prompts here — but what the base model itself was trained to refuse is undocumented and untested by us.

Generates video clips from a text prompt, image, audio, or video with LTX Director 2.0. An uncensored version of LTX 2.3.

An uncensored build of LTX 2.3 — its safety filters were removed, so it generates freely with no refusals.

Lip-sync add-on for LTX 2.3 / Sulphur-2. Re-generates a clip so the mouth matches speech you supply — dub into another language or change what the person says.

An uncensored build of LTX 2.3 — its safety filters were removed, so it generates freely with no refusals.

Animates or replaces a character in a video — give it a reference image plus a driving motion video and it transfers the motion (people auto-masked, no manual rigging). Built on Wan2.1 14B.

The Wan2.1 base ships with no content filter — it generates any content out of the box, nothing was removed.

Fast 9B FLUX.2 klein, uncensored — the "True V3" aesthetic fine-tune with an abliterated text encoder. Text-to-image, multi-reference editing, and RefControl depth/structure control, light enough for a single 24GB GPU.

Its safety-tuned base is freed by the 'True V3' fine-tune plus an abliterated text encoder — generates freely with no refusals.

DarkBeast Klein 9b V2 BFS — a face-swap-specialized fine-tune of FLUX.2 klein 9B, uncensored. Distilled for 5 steps at CFG 1 (Best Face Swap tech): give it a target photo and a reference face and it pastes the identity in while keeping pose, expression and lighting. Ships alongside the True V3 tune — just pick it in the loader. fp8 on a 24GB card, bf16 on 32GB.

Its safety-tuned base is freed by the 'True V3' fine-tune plus an abliterated text encoder — generates freely with no refusals.

Text-to-image with strong typography — great for legible text & design. Visually place text and elements at exact positions on a canvas (regional layout control).

The abliterated encoder removes prompt refusals, but NSFW was filtered from the model's training data, so results in that area are still inconsistent.

Generates images from text with high prompt fidelity and strong text-in-image rendering.

Trained on unrestricted data and run with an abliterated text encoder — no refusals and no quality loss on any content.

Edits existing images by prompt — background swaps, object add/remove, restyling (up to 3 input images).

Trained on unrestricted data and run with an abliterated text encoder — no refusals and no quality loss on any content.

Fast 4-step text-to-image with strong photorealism and bilingual (English/Chinese) text rendering.

The abliterated encoder removes prompt refusals, but the model has soft safety and results in that area can still be inconsistent.

Instruction-based image editing — describe the change in text to insert, replace, or restyle objects in an image.

The abliterated encoder removes prompt refusals, but the model has soft safety and results in that area can still be inconsistent.

Fast, photorealistic text-to-image at up to 2K resolution, with 9 selectable style LoRAs for different looks.

Natively NSFW-capable and run with an abliterated text encoder — no refusals and no quality loss on any content.

TTS + voice cloning across 80+ languages with best-in-class accuracy scores.

A text-to-speech model with no content restrictions — it speaks whatever text you provide.

Speech-to-text engine for voice-to-SRT (default). Whisper core plus phoneme forced-alignment for very tight word-level subtitle timing, plus speaker diarization.

A text-to-speech model with no content restrictions — it speaks whatever text you provide.

Text-to-speech and voice cloning / conversion, plus voice-to-SRT and SRT-to-voice. A reference voice sample defines the output voice.

A text-to-speech model with no content restrictions — it speaks whatever text you provide.

Voice design model — describe the voice you want in plain words (gender, age, mood, accent) and it speaks your text with that voice. 10 languages.

A text-to-speech model with no content restrictions — it speaks whatever text you provide.

Voice cloning model — a 3-second reference sample defines the output voice. 10 languages.

A text-to-speech model with no content restrictions — it speaks whatever text you provide.

Alternative speech-to-text engine for voice-to-SRT, shipped only in the Qwen3-TTS bundle. Built-in word-level timestamps.

A text-to-speech model with no content restrictions — it speaks whatever text you provide.

TTS + voice cloning + native voice conversion in 23 languages. Preferred over ElevenLabs in blind listening tests.

A text-to-speech model with no content restrictions — it speaks whatever text you provide.