From dc7bb9746a571090bd1ce5708fd003d2cdb6e13e Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Tue, 5 Mar 2024 10:41:10 -0500 Subject: [PATCH] update changelog --- CHANGELOG.md | 4 ++-- modules/vqa.py | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index a506f5b0e..0c2d8e02c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -18,8 +18,8 @@ - **Visual Query** visual query & answer in process tab - ask your questions, e.g. "describe the image", "what is behind the subject", "what are predominant colors of the image?" - primary model is [moondream2](https://github.com/vikhyat/moondream), a *tiny* 1.86B vision language model - (its still 3.7GB in size, so not really tiny) - - additional support for multiple variations of several base models: *GIT, BLIP, ViLT, PIX* + *note*: its still 3.7GB in size, so not really tiny + - additional support for multiple variations of several base models: *GIT, BLIP, ViLT, PIX*, sizes range from 0.3 to 1.7GB - **Second Pass / Refine** - independent upscale and hires options: run hires without upscale or upscale without hires or both - upscale can now run 0.1-8.0 scale and will also run if enabled at 1.0 to allow for upscalers that simply improve image quality diff --git a/modules/vqa.py b/modules/vqa.py index 019ca2719..3de7bef91 100644 --- a/modules/vqa.py +++ b/modules/vqa.py @@ -118,7 +118,6 @@ def moondream(question: str, image: Image.Image, repo: str = None): question = "Describe the image." encoded = model.encode_image(image) with devices.inference_context(): - print('HERE', question) response = model.answer_question(encoded, question, processor) shared.log.debug(f'VQA: response="{response}"')