Models tagged "visual-question-answering"

🤖 Model 🖼️ → 📝

spuuntries/urna-kp3l

Caption images and answer visual questions from an image and a text prompt. Accepts an input image and an instruction (e...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 108 runs

🤖 Model 🖼️ → 📝

bytedance/sa2va-26b-image

Segment objects in images from natural-language instructions and answer visual questions. Provide an image plus a text i...

🖼️ → 📝 • image-segmentation • image-to-text • 6.4K runs

🤖 Model 🖼️ → 📝

bytedance/sa2va-8b-image

Segment objects in images from natural-language instructions and answer grounded visual questions. Takes an image and a...

🖼️ → 📝 • image-segmentation • image-to-text • visual-question-answering • 19.8K runs

🤖 Model 🖼️ → 📝

salesforce/blip

Caption images and answer visual questions from an input image. Optionally evaluate image–text matching. Provide an imag...

🖼️ → 📝 • image-to-text • visual-question-answering • image-text-matching • 168.6M runs

🤖 Model 🖼️ → 📝

andreasjansson/blip-2

Answer questions about images and generate captions from a single input image. Provide an image and a natural-language q...

🖼️ → 📝 • image-to-text • visual-question-answering • image-captioning • 30.9M runs

🤖 Model 🖼️ → 📝

zsxkib/blip-3

Answer questions about images. Provide an image and a natural-language question to receive a text answer, or switch to c...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 1.3M runs

🤖 Model 🖼️ → 📝

yorickvp/llava-13b

Answer questions about images and generate image-grounded text from an image and a text prompt. Perform visual question...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 31.8M runs

🤖 Model 🖼️ → 📝

lucataco/moondream2

Answer questions about images and generate captions from an input image and a text prompt, returning text. Handle genera...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 4.5M runs

🤖 Model 🖼️ → 📝

deepseek-ai/deepseek-vl2

Analyze images and answer questions from an image plus text prompt, returning text. Handle visual question answering (VQ...

🖼️ → 📝 • image-to-text • ocr • image-analysis • 71.6K runs

🤖 Model 🖼️ → 📝

cjwbw/cogvlm

Caption images and answer visual questions from an input image and text query, returning a text response. Handle general...

🖼️ → 📝 • image-to-text • image-captioning • visual-understanding • 1.5M runs

🤖 Model 🖼️ → 📝

deepseek-ai/janus-pro-7b

Answer questions about images and return text. Accepts an image and a natural-language question and outputs a textual an...

🖼️ → 📝 • image-to-text • visual-question-answering • ocr • 13.4K runs

🤖 Model 🖼️ → 📝

lucataco/bakllava

Caption images and answer questions about images. Takes an image and a text prompt as input and returns text, enabling i...

🖼️ → 📝 • image-to-text • visual-question-answering • visual-understanding • 39.8K runs

🤖 Model 🖼️ → 📝

adirik/vila-2.7b

Answer questions about images and generate text descriptions. Accepts an image and a natural-language prompt; returns te...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 2.6K runs

🤖 Model 🖼️ → 📝

lucataco/qvq-72b-preview

Answer questions about images from a single image input and a text prompt, returning a single-turn text response. Perfor...

🖼️ → 📝 • image-to-text • image-captioning • visual-understanding • 276 runs

🤖 Model 🖼️ → 📝

naklecha/cogvlm

Answer questions about images and generate captions from an input image and text prompt. Output free-form text grounded...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 12.4K runs

🤖 Model 🖼️ → 📝

lucataco/idefics-8b

Answer questions about images from an image and text prompt, returning text. Perform visual question answering, image ca...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 1.1K runs

🤖 Model 🖼️ → 📝

adirik/vila-7b

Answer questions about an image and generate captions, returning text based on visual content. Provide a single image an...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 2.2K runs

🤖 Model 🖼️ → 📝

deepseek-ai/janus-pro-1b

Answer questions about images. Takes an image and a natural-language question and returns text, enabling visual question...

🖼️ → 📝 • image-to-text • visual-understanding • 6.7K runs

🤖 Model 🖼️

zsxkib/idefics3

Answer questions about images and generate captions from an image and a text prompt, outputting text. Perform visual que...

🖼️ • image-captioning • image-analysis • visual-understanding • 2.5K runs

🤖 Model 🖼️

lucataco/smolvlm-instruct

Answer questions about images and documents from an image and a text prompt, returning text. Handle visual question answ...

🖼️ • image-captioning • image-analysis • visual-understanding • 3.3K runs