The AI App Directory MiniCPM-V 4.7 Demo MiniCPM-V 4.7 Ultra-Efficient Multimodal AI LLM 3D Worlds Arena Generate a custom world instantly via the web Direct Fish Audio Drama 3, streaming on ZeroGPU MOSS-Image Workflow MOSS-Image text-to-image as a gr.Workflow node canvas. Speech to Decisions with Granite Live speech, heard and sized up by one Granite Switch model Generate depth maps and 3D view from your photos FLUX 3 Image Klein 5.6B open weights. Text-to-image, editing, bounding boxes Steer a robot with words Free text to a VLA through a VLM planner, in LeRobot Wan2.2 14B Preview generate a video from an image with a text prompt BFS Best Face Swap Head swap with the BFS LoRA on Qwen-Image-2.1 (+turbo) Jev Decision Index Benchmarks and news on various repros of TypeSafe's Jev FLUX 3 Image Klein 5.6B open weights. Text-to-image, editing, bounding boxes Direct Fish Audio Drama 3, streaming on ZeroGPU MOSS-Image Workflow MOSS-Image text-to-image as a gr.Workflow node canvas. Qwen 2511 + Flux.2 Klein Edit images with Qwen and enhance with FLUX.2 Klein MiniMax-H3 360° Orbit LoRA

One photo into a frozen-instant 360° camera orbit Qwen-Image-2.1-Turbo 8-step text-to-image and editing with Qwen-Image-2.1-Turbo Viggle Turbo for Qwen-Image-2.1 6-step Qwen-Image-2.1, T2I + editing, vs-base comparison Krea 2 Turbo Image Generator Krea 2 Turbo text2image and image editing minimax h3 turbo + lora's Video generation with a synchronized soundtrack Wan2.2 14B Cum explosion lora generate a video from an image with a text prompt with text LightOnOCR-3 Demo OCR to Markdown with layout grounding Qwen Image 2.1 Uncensored All-In-One LoRA Studio Uncensored Qwen 2.1 with All-In-One LoRAs Omni Video Factory text to video, image to video, video extend Pixel-space generation & general vision learner Hugging Face model download stats, history & trends QIE-2511 Rapid-AIO LoRAs Fast (Experimental) Demo of the Collection of Qwen Image Edit LoRAs Qwen-Image-Edit-2511-LoRAs-Fast AnyPose pose still with a strong pose-reference lock Generate or edit images from text and optional photos MiniMax H3 Turbo Lora UNCENSORED Workflow Video generation with a synchronized soundtrack Speech to Decisions with Granite Live speech, heard and sized up by one Granite Switch model High-fidelity 3D Generation from images