Search the full model catalog.

The 8B instruction-tuned model of Meta's Llama 3.1 collection, for chat and code in eight languages. It was pretrained on roughly 15 trillion tokens, and its knowledge stops at December 2023.

Qwen2.5's 7B chat model (7.61B parameters) with JSON mode, function calling and up to 32,768 input tokens on Wiro. Qwen reports 75.5 on MATH and 84.8 on HumanEval.

One set of chat inputs for open-weight models hosted on Wiro, such as Llama, Qwen, Mistral and DeepSeek. Choose the base model on each request and keep separate conversation histories per user and session.

Wiro AI's 8B Turkish chat model: Llama 3.1 8B Instruct fine-tuned on more than 500,000 Turkish instructions, with a focus on Turkish idioms and local context.

Wiro's Turkish chat model, fine-tuned from Google's Gemma 2 9B on more than 500,000 Turkish instructions to answer in natural Turkish with local and cultural context.

Detects the faces in a photo and covers each one with a blurred oval, leaving the rest of the image untouched. One image in, one PNG out at the original size.

The pretrained 13B-parameter Llama 2 base model from Meta, with no chat or instruction tuning. It continues the text you give it, for story drafting and pattern completion in English.

FP8 checkpoint of Black Forest Labs' 12B FLUX.1 [dev] text-to-image model, stored at one byte per weight instead of two. A run returns up to eight PNG images at up to 2048 pixels per side.

Answers questions about one image or captions it, using Google's instruction-tuned Flan-T5-XL as the language model inside BLIP-2. Only the answer text comes back.

The larger BLIP captioning checkpoint from Salesforce, with a ViT-L image encoder and trained on COCO. It takes one image plus an optional opening phrase and returns a short English caption.

BLIP captioning checkpoint from Salesforce with a ViT-B image encoder, trained on COCO. It writes a short English caption for an image and can continue an opening phrase you give it.

Repaints an existing image from a text prompt with a FLUX.1 checkpoint you pick. A strength setting decides how much of the source survives, from a light restyle to a near full redraw.

Generate images from a text prompt with a FLUX.1 base model and a LoRA of your choice: a public style listed on Wiro, one of your private LoRAs, or a .safetensors file by URL.

Inpainting and outpainting model from Black Forest Labs. Upload a photo and a mask, describe what belongs in the masked area, and only that area is repainted to fit the rest of the image.

Writes a detailed English description of a video clip, guided by your prompt. Built on THUDM's CogVLM2-Llama3-Caption, the model that captioned training data for CogVideoX.

Writes one detailed English paragraph describing a video clip from start to finish. THUDM built it to caption training data for its CogVideoX text-to-video model.

Meta's 7B Llama 2 chat model, aligned for English dialogue with supervised fine-tuning and RLHF. Text in, text out, with a 4k-token context window.

Cuts the main subject out of a photo and returns it on a transparent background at the original size. BiRefNet is a high-resolution segmentation model that uses gradient maps to keep fine edges.

A Wiro app that runs NVIDIA's 1.6B Sana text-to-image model with a base model picker, switching between four checkpoints that target 1024px, 2K and 4K output.

Renders a text prompt with the FLUX.1 checkpoint you pick, such as FLUX.1 [dev], [schnell] or Krea [dev], or with one of your private FLUX.1 fine-tunes.