From 48e8c42a33f88b7cfcfd6524983e49782988937d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B3=A0=E9=9F=B3?= Date: Sat, 31 May 2025 00:39:35 +0800 Subject: [PATCH 1/5] Update Gemini Model --- src/autoslice/mllm_sdk/gemini_new_sdk.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/autoslice/mllm_sdk/gemini_new_sdk.py b/src/autoslice/mllm_sdk/gemini_new_sdk.py index 8c0f392..2736024 100644 --- a/src/autoslice/mllm_sdk/gemini_new_sdk.py +++ b/src/autoslice/mllm_sdk/gemini_new_sdk.py @@ -12,7 +12,7 @@ def gemini_generate_title(video_path, artist): video_bytes = open(video_path, "rb").read() response = client.models.generate_content( - model="models/gemini-2.0-flash", + model="models/gemini-2.5-flash", contents=types.Content( parts=[ types.Part(text=SLICE_PROMPT.format(artist=artist)), @@ -22,7 +22,7 @@ def gemini_generate_title(video_path, artist): ] ), ) - scan_log.info("Using Gemini-2.0-flash to generate slice title") + scan_log.info("Using Gemini-2.5-Flash to generate slice title") scan_log.info(f"Prompt: {SLICE_PROMPT.format(artist=artist)}") scan_log.info(f"Generated slice title: {response.text}") return response.text From 4dff808da2dbb1cd238e4fa0ad59045104cdf235 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B3=A0=E9=9F=B3?= Date: Sat, 31 May 2025 00:40:12 +0800 Subject: [PATCH 2/5] Update Gemini Model --- src/autoslice/mllm_sdk/gemini_old_sdk.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/autoslice/mllm_sdk/gemini_old_sdk.py b/src/autoslice/mllm_sdk/gemini_old_sdk.py index 1023017..eeab7a5 100644 --- a/src/autoslice/mllm_sdk/gemini_old_sdk.py +++ b/src/autoslice/mllm_sdk/gemini_old_sdk.py @@ -26,14 +26,14 @@ def gemini_generate_title(video_path, artist): prompt = SLICE_PROMPT.format(artist=artist) # Set the model to Gemini Flash. - model = genai.GenerativeModel(model_name="models/gemini-2.0-flash") + model = genai.GenerativeModel(model_name="models/gemini-2.5-flash") response = model.generate_content( [prompt, video_file], request_options={"timeout": 600} ) # delete the video file genai.delete_file(video_file.name) - scan_log.info("Using Gemini-2.0-flash to generate slice title") + scan_log.info("Using Gemini-2.5-Flash to generate slice title") scan_log.info(f"Prompt: {SLICE_PROMPT.format(artist=artist)}") scan_log.info(f"Generated slice title: {response.text}") return response.text From da0173825bda1e25d2a5095040405436f9d5f95a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B3=A0=E9=9F=B3?= Date: Sat, 31 May 2025 00:41:32 +0800 Subject: [PATCH 3/5] Update Gemini Model --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index a859ef8..70cd706 100644 --- a/README.md +++ b/README.md @@ -80,7 +80,7 @@ - **( :tada: NEW)自动渲染字幕**:采用 OpenAI 的开源模型 `whisper`,自动识别视频内语音并转换为字幕渲染至视频中。 - **( :tada: NEW)自动切片上传**:根据弹幕密度计算寻找高能片段并切片,该自动切片工具库已开源 [auto-slice-video](https://github.com/timerring/auto-slice-video),结合多模态视频理解大模型自动生成有意思的切片标题及内容,并且自动上传,目前已经支持的模型有: - `GLM-4V-PLUS` - - `Gemini-2.0-flash` + - `Gemini-2.5-flash` - `Qwen-2.5-72B-Instruct` - `SenseNova V6 Pro` - **( :tada: NEW)持久化登录/下载/上传视频(支持多p投稿)**:[bilitool](https://github.com/timerring/bilitool) 已经开源,实现持久化登录,下载视频及弹幕(含多p)/上传视频(可分p投稿),查询投稿状态,查询详细信息等功能,一键pip安装,可以使用命令行 cli 操作,也可以作为api调用。 From 59f91d940b289369130074c8b8fd91d4b3010b7f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B3=A0=E9=9F=B3?= Date: Sat, 31 May 2025 15:16:05 +0800 Subject: [PATCH 4/5] Update gemini_new_sdk.py --- src/autoslice/mllm_sdk/gemini_new_sdk.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/autoslice/mllm_sdk/gemini_new_sdk.py b/src/autoslice/mllm_sdk/gemini_new_sdk.py index 2736024..646063b 100644 --- a/src/autoslice/mllm_sdk/gemini_new_sdk.py +++ b/src/autoslice/mllm_sdk/gemini_new_sdk.py @@ -12,7 +12,7 @@ def gemini_generate_title(video_path, artist): video_bytes = open(video_path, "rb").read() response = client.models.generate_content( - model="models/gemini-2.5-flash", + model="gemini-2.5-flash-preview-05-20", contents=types.Content( parts=[ types.Part(text=SLICE_PROMPT.format(artist=artist)), From 0a98d681598f95bf173464426e99937fcabdee0e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B3=A0=E9=9F=B3?= Date: Sat, 31 May 2025 15:16:21 +0800 Subject: [PATCH 5/5] Update gemini_old_sdk.py --- src/autoslice/mllm_sdk/gemini_old_sdk.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/autoslice/mllm_sdk/gemini_old_sdk.py b/src/autoslice/mllm_sdk/gemini_old_sdk.py index eeab7a5..f3eff86 100644 --- a/src/autoslice/mllm_sdk/gemini_old_sdk.py +++ b/src/autoslice/mllm_sdk/gemini_old_sdk.py @@ -26,7 +26,7 @@ def gemini_generate_title(video_path, artist): prompt = SLICE_PROMPT.format(artist=artist) # Set the model to Gemini Flash. - model = genai.GenerativeModel(model_name="models/gemini-2.5-flash") + model = genai.GenerativeModel(model_name="gemini-2.5-flash-preview-05-20") response = model.generate_content( [prompt, video_file], request_options={"timeout": 600}