A Flux.1 LoRA that generates vibrant, whimsical digital icons with bold outlines. Great for game props like potions, shields, crowns, and fantasy items.
Models
All Models
Flux.1 LoRA for Gwendolyn, a red-haired character in a comic cartoon style. Generates consistent portraits across varied settings and scenes.
A Flux LoRA for colorful, eerie character icons. Generates creatures and characters with bold expressions, themed costumes, and clean solid-color backgrounds.
A Flux.1 LoRA that generates stylized game-ready backgrounds with vibrant colors and whimsical architecture, from fantasy villages to sci-fi cityscapes.
A Flux.1 LoRA that renders game props and objects in a minimalist 3D cartoon style, with clean shapes, smooth textures, and solid color backgrounds.
A Flux.1 LoRA for 3D cartoon character art. Generates stylized figurines across fantasy archetypes, occupations, and creatures with vibrant, clean rendering.
Flux.1 LoRA for vibrant cartoon backgrounds. Generates bold, whimsical scenes: fantasy forests, alien planets, ancient ruins, undersea reefs, and more.
Flux.1 LoRA for top-down tower defense maps. Generates stylized 2D landscapes, forests, deserts, caves, and volcanic zones with clear paths and terrain.
A Flux.1 LoRA that renders clean black-and-white line art in a coloring book style. Works on humans, vehicles, and animals.
FLUX.1 Dev by Black Forest Labs. High-quality text-to-image and image-to-image with strong prompt adherence, ControlNet, and a top base for LoRA fine-tuning.
FLUX.1 Schnell by Black Forest Labs. A fast, few-step text-to-image model delivering quality results in as few as 4 inference steps.
Meshy 7 text-to-3D: higher-fidelity geometry than Meshy 6, optional Ultra mode for finer surface detail, and 2K/4K/8K PBR texturing in one generation.
Meshy 7 multi-view image-to-3D: fuse 1-4 photos into one consistent mesh, then apply a separate set of texture reference images to restyle the surface.
Meshy 7 image-to-3D: turn one reference image (or up to four angles) into a clean, fully textured mesh, with optional Ultra mode for finer geometry and 2K/4K/8K PBR texturing.
Automatically split a 3D mesh into editable parts. Tripo Segmentation v1 uses geometry analysis to separate characters, props, and hard-surface models.
Subject-consistent 720p video with native audio from 1 to 3 reference images and an optional prompt. Your characters, products, or place stays the same across the clip.
Restyle an existing video with a plain-language instruction. Motion is preserved, look changes: season, wardrobe, palette, weather, style. Native audio comes with it.
Gemini Omni is Google's breakthrough any-input video model: create and conversationally edit from text, images, audio, or video, with native sound. 720p, 3-10s.
ElevenLabs Music v2 by ElevenLabs generates studio-quality music from text: any genre, vocal or instrumental, 3 to 180 seconds, exported as MP3 or Opus.
ElevenLabs Music Advanced v2 by ElevenLabs. Compose full songs section by section, with per-section styles, lyrics, duration, and a context-adherence dial.
Uthana Video-to-Motion by Uthana extracts 3D human motion from any reference video and retargets it to your own character model. Outputs GLB or FBX.
Uthana Text-to-Motion by Uthana. Describe any movement in text and get a ready-to-use animated 3D character in GLB or FBX.
Meshy Multi Image to 3D by Meshy. Upload 1-4 photos from different angles to generate a textured 3D mesh, with PBR maps, pose modes, and polycount control.
Google's fast TTS model with 30 voices, 24 languages, and inline audio tags for precise emotion and pacing control. Outputs mono MP3 at 24kHz.
LTX-2.3 Pro Audio to Video by Lightricks generates video synchronized to your audio. Voice cadence shapes pacing, music drives motion. Up to 20s, 1080p.
Minimax Music 2.6 by MiniMax generates full songs from a text prompt. Vocal or instrumental, custom or AI-written lyrics, studio-quality 44.1kHz output.
Dub video or audio into 30 languages, preserving each speaker's voice via cloning. Auto-detects source language and up to 10 speakers; optional background audio removal.
Seedance 2.0 by ByteDance: text, image, and video to video generation with up to 1080p output, synced audio, and multi-reference support.
Wan 2.7 by Alibaba. Text-to-video at up to 1080p, 2-15 seconds, five aspect ratios, optional synced audio, and built-in prompt expansion.
Wan 2.7 I2V by Alibaba animates images into 720p or 1080p video, 2-15s. Supports first/last frame bracketing, clip continuation, and optional audio input.
Minimax Music 2.5 by MiniMax generates full songs from lyrics and a style prompt, with 14 arrangement tags, vocal and instrumental modes, up to 44.1kHz / 256kbps.
Tripo P1 Multi View by Tripo AI. Generate high-fidelity 3D meshes with PBR maps from up to four reference angles using native 3D diffusion.
LTX 2.3 Pro by Lightricks. High-fidelity text-to-video and image-to-video at up to 4K, with synchronized audio and optional start/end frame interpolation.
LTX 2.3 Fast by Lightricks: speed-optimized video generation with synchronized audio, up to 4K, 6-20s clips, portrait or landscape support, and camera motion controls.
Qwen Edit Plus by Alibaba. Edit images from plain-language instructions: change objects, styles, or in-image text. Supports LoRA fine-tuning and up to 2048x2048 output.
Qwen Edit 2509 by Alibaba edits images from text instructions, with multi-image input, up to 6 LoRA styles, and precise portrait and text editing.
Vidu Q2 by Shengshu Technology generates text-to-video clips up to 10 seconds in up to 1080p, with cinematic camera control and optional background music.
Vidu Q2 Reference2V by Shengshu Technology generates videos with up to 7 reference images to maintain consistent characters, props, and costumes across every frame.
Vidu Q2 Turbo I2V by Shengshu Technology. Fast image-to-video with smooth motion, first/last-frame control, up to 1080p and 10 seconds.
Vidu Q2 Pro Fast by Shengshu Technology animates still images into video at speed, with 720p or 1080p output, up to 10 seconds, and optional background music.
Vidu Q2 Pro I2V by Shengshu Technology animates a single image or bridges two frames into cinematic video up to 1080p, with strong subject fidelity.
Generate 5-second 1080p videos from up to 7 reference images. Vidu Q1 preserves subject appearance, style, and texture through motion. 16:9, 1:1, or 9:16.
Vidu Q1 Classic by Shengshu Technology. Animate a still image or define start and end frames for natural, composition-preserving 1080p video.
Vidu Q1 I2V by Shengshu Technology. Animate one image or bridge two frames into a smooth clip. Strong anime and general motion styles, with optional audio.
Vidu Q1 by Shengshu Technology. Generate 5-second 1080p videos from text in general or anime style, with control over motion intensity and aspect ratio.
Vidu 2.0 Reference2V by Shengshu Technology generates 4-second videos from up to 7 reference images, keeping subjects and styles consistent.
Vidu 2.0 by Shengshu Technology. Animate one image into video, or define start and end frames. 4s or 8s, up to 1080p, with adjustable motion.
Tripo Rigging 1.0 by Tripo AI auto-rigs biped character meshes for animation. Upload a GLB, OBJ, FBX, or STL and get a skeleton-ready biped model back.