From e8a25a7271c4b66d6c17a2d4ce3007e33c984883 Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Tue, 5 Nov 2024 18:31:58 -0500 Subject: [PATCH] add promptgen-v2 Signed-off-by: Vladimir Mandic --- CHANGELOG.md | 7 +++++++ modules/vqa.py | 2 ++ requirements.txt | 4 ++-- 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 4bb10f5de..724960169 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -28,6 +28,13 @@ This release can be considered an LTS release before we kick off the next round - SD3: all-in-one safetensors - *examples*: [large](https://civitai.com/models/882666/sd35-large-google-flan?modelVersionId=1003031), [medium](https://civitai.com/models/900327) - *note*: enable *bnb* on-the-fly quantization for even bigger gains +- [MiaoshouAI PromptGen v2.0](https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen-v2.0) base and large: + - *in process -> visual query* + - caption modes: + `` generate tags + ``, ``, `` caption image + `` image composition + ``, `` detailed caption and tags with optional analyze - XYZ grid: - optional time benchmark info to individual images - optional add params to individual images diff --git a/modules/vqa.py b/modules/vqa.py index 64ba83696..a0a5d147c 100644 --- a/modules/vqa.py +++ b/modules/vqa.py @@ -14,6 +14,8 @@ MODELS = { "MS Florence 2 Large": "microsoft/Florence-2-large", # 1.5GB "MiaoshouAI PromptGen 1.5 Base": "MiaoshouAI/Florence-2-base-PromptGen-v1.5@c06a5f02cc6071a5d65ee5d294cf3732d3097540", # 1.1GB "MiaoshouAI PromptGen 1.5 Large": "MiaoshouAI/Florence-2-large-PromptGen-v1.5@28a42440e39c9c32b83f7ae74ec2b3d1540404f0", # 3.3GB + "MiaoshouAI PromptGen 2.0 Base": "MiaoshouAI/Florence-2-base-PromptGen-v2.0", # 1.1GB + "MiaoshouAI PromptGen 2.0 Large": "MiaoshouAI/Florence-2-large-PromptGen-v2.0", # 3.3GB "CogFlorence 2.0 Large": "thwri/CogFlorence-2-Large-Freeze", # 1.6GB "CogFlorence 2.2 Large": "thwri/CogFlorence-2.2-Large", # 1.6GB "Moondream 2": "vikhyatk/moondream2", # 3.7GB diff --git a/requirements.txt b/requirements.txt index c6fcf97ec..de0223bd5 100644 --- a/requirements.txt +++ b/requirements.txt @@ -49,8 +49,8 @@ scipy pandas protobuf==4.25.3 pytorch_lightning==1.9.4 -tokenizers==0.20.1 -transformers==4.46.1 +tokenizers==0.20.3 +transformers==4.46.2 urllib3==1.26.19 Pillow==10.4.0 timm==0.9.16