Flux.2-klein-4B
This space uses โComfy-Org/vae-text-encorder-for-flux-...โ.
This space uses โComfy-Org/vae-text-encorder-for-flux-...โ.
Text-to-image and editing with FLUX.2 Klein on CPU
High-fidelity 3D Generation from images
Train Krea 2 LoRAs on your images via HF Jobs
Vectorizer AI | Convert Image to SVG
Turn any photo into a collectible 3D figurine
Generate 3d animation from monocular video.
Convert images into 3D assets with background removal and enhancement
Image to 3D to auto-rigged GLB/FBX for Blender
Image-to-3D via DeepSDF shared decoder + latent diffusion
Versatile Single-Image 3D Face Reconstruction
Generate 3D human motion from text prompts
Next-Gen High-Resolution 3D Model Generation
A small LLM writes, draws & directs original ASCII films
4D face reconstruction & tracking from an image sequence
Generate depth maps from your photos
Generate depth maps from your photos
CPU ONNX demo for DepthPolyp.
Text and Image to 3D Model Generator
Enhance and upscale images with advanced models
Create a story from any uploaded image
Space for quantizing models for use in ComfyUI
Generate consistent image sequences from text and photos
Reference-image conditioned generation with Krea 2
Embodied MoE video generation โ T2V, I2V, T2I
Generate video from an image and audio file
Generate short videos from an image and text prompt
Talk to Gemma 4 face to face, with a 3D lip-synced avatar
Generate images from text prompts with customizable aspect ratio
Generate professional AI image prompts from text or photos
Generate images from a text prompt
Image edit, text to image, image upscale, remove watermark
Run complete 3.96M and 9.36M text-to-waveform models live.
Unified audio-text intelligence
Generate pixel art game assets from a prompt
High-fidelity pixel-aligned image-to-3D generation.
Free AI voice clone & multilingual TTS (600+ langs)
Uncensored General Intelligence Leaderboard
Chat with Moonshot AI's Kimi K3 via Inference Providers