A curated catalog of uncensored spicy models across chat, image, video, and voice — hand-picked, battle-tested, ready to ship.
Photoreal NSFW images, no content filters
Spicy 1.0 Image Edit (Qwen Image Edit Spicy) applies precise, instruction-based edits to any image: remove or change clothing, adjust pose and expression, relight the scene, swap backgrounds — while explicitly preserving everything else. Supports (keyword:weight) emphasis syntax for fine control. The refinement stage of every Spicy pipeline.
Generate images from text prompts using the SpicyRouter 1.0 Image Pro model with prompt rewriting, This model delivers stronger image‑generation capabilities compared to the Lite version of the model.
Spicy 1.0 Image (Z-Image Spicy) generates uncensored, photoreal or stylized images from text. Multi-stage sampling with DPO LoRA lifts diversity and aesthetic scores, while free built-in prompt expansion turns short ideas into detailed scenes. Composition controls are tuned for downstream image-to-video: clean backgrounds, movement space, action-ready poses.
Realistic motion, async task API
Uncensored Seedance 2.5 (spicy) — text to video. 4-30s (or smart auto) at 1080p with native audio and next-gen motion realism.
Uncensored Seedance 2.5 (spicy) — image to video (1-2 images, first/last frame). 4-30s (or smart auto) at 1080p with native audio and next-gen motion realism.
Uncensored Seedance 2.5 (spicy) — reference-driven video (images, videos and audio clips as cast). 4-30s (or smart auto) at 1080p with native audio and next-gen motion realism.
Uncensored Seedance 2.5 (spicy) — instruction video editing (requires at least one reference video; duration follows the source). 4-30s (or smart auto) at 1080p with native audio and next-gen motion realism.
Uncensored Seedance 2.5 (spicy) — video extension (requires at least one reference video; adds up to 30 more seconds). 4-30s (or smart auto) at 1080p with native audio and next-gen motion realism.
Uncensored Seedance 2.0 (spicy) — text to video. 4-15s clips up to 4K with native audio and precise prompt adherence.
Uncensored Seedance 2.0 (spicy) — image to video (1-2 images, first/last frame). 4-15s clips up to 4K with native audio and precise prompt adherence.
Uncensored Seedance 2.0 (spicy) — reference-driven video (images, videos and audio clips as cast). 4-15s clips up to 4K with native audio and precise prompt adherence.
Spicy 1.0 Pro I2V (Wan 2.7 LoRA Spicy) turns a single image into a 2-15 second cinematic video with synchronized native audio. Script every second with the At 00:XX frame-by-frame structure, steer dialogue with emotion tags, and let the built-in prompt optimizer expand short briefs into production-grade scripts. Supports photoreal, anime and Asian-face LoRA styles.
Spicy 1.0 Lite I2V (Wan 2.2 LoRA Spicy) is the mass-production tier of the Spicy lineup: fixed 5s/8s silent clips at 480p/720p, first and last frame control for precise start-to-end transitions, and a price point that makes thousands of variants affordable. Silent output pairs freely with your own TTS, BGM or platform audio trends.