diff --git a/README.md b/README.md index 30da7d3..a859ef8 100644 --- a/README.md +++ b/README.md @@ -13,6 +13,25 @@ [:thinking: Reporting Issues](https://github.com/timerring/bilive/issues/new/choose) | [:speech_balloon: Chat](https://github.com/timerring/bilive/blob/main/assets/wechat.png) +
+ + DMXAPI.cn + + **大模型API(DMXAPI)** 行业领先的 api 聚合平台 **[详细介绍](#特别感谢)** + +
+ DMX = 大模型拼音首字母 + + + +
+ +
+ 支持模型
@@ -77,11 +96,12 @@ - `Recraft` - `Amazon Titan Image Generator V2` - `Hidream I1` + - `kling-v1-5` 项目架构流程如下： -![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-04-30-14-00-48.png) +![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-05-03-22-09-56.png) ## 3. 测试硬件 @@ -205,18 +225,29 @@ MLLM 模型主要用于自动切片后的切片标题生成，此功能默认关 采用图生图多模态模型，自动获取视频截图并上传风格变换后的视频封面，如需使用本功能，请将 `generate_cover` 参数设置为 `true`，并且写下你自己的 prompt，注意部分模型只支持英文，接下来需要配置的参数有 image_gen_model 和对应的 api key，请自行根据链接注册账号并且申请对应 api key，填写在对应的参数中，请注意以下模型只有你在 `image_gen_model` 参数中设置的那个模型会生效。 +推荐使用大模型API([dmxapi.cn](https://www.dmxapi.cn/register?aff=vRzR))，一个 Key 用全球大模型，[查看详细介绍](#特别感谢)。 + +| Company | Model Name | `image_gen_model` | `API Key` | +|--------------|--------------------------------|-------------------|---------------------------------------------------------------------------------| +| Kwai | v1-5 | `kling` | [dmx_api_token](https://www.dmxapi.cn/token) | + +
+其他支持的图像生成模型 + | Company | Model Name | `image_gen_model` | `API Key` | |--------------|--------------------------------|-------------------|---------------------------------------------------------------------------------| -| Minimax | image-01 | `minimax` | [minimax_api_key](https://platform.minimaxi.com/user-center/basic-information/interface-key) | -| Kwai | Kolors | `siliconflow` | [siliconflow_api_key](https://cloud.siliconflow.cn/i/3Szr5BVg) | -| Tencent | Hunyuan | `tencent` | [tencent_secret_id and tencent_secret_key](https://console.cloud.tencent.com/cam/capi) | -| Baidu | ERNIE irag-1.0 | `baidu` | [baidu_api_key](https://console.bce.baidu.com/iam/key/list) | -| Stability AI | Stable Diffusion 3.5 large turbo | `stability` | [stability_api_key](https://platform.stability.ai/account/keys) | -| Luma Labs | Photon | `luma` | [luma_api_key](https://lumalabs.ai/api/keys) | -| Ideogram | Ideogram V_2 | `ideogram` | [ideogram_api_key](https://ideogram.ai/manage-api) | -| Recraft | Recraft V3 | `recraft` | [recraft_api_key](https://www.recraft.ai/profile/api) | -| Amazon | Titan Image Generator V2 | `amazon` | [aws_access_key_id and aws_secret_access_key](https://aws.amazon.com/console/) | -| Hidream | Hidream I1 | `hidream` | [hidream_api_key](https://www.hidreamai.com/platform/token) | +| Minimax | image-01 | `minimax` | minimax_api_key | +| Kwai | Kolors | `siliconflow` | siliconflow_api_key | +| Tencent | Hunyuan | `tencent` | tencent_secret_id and tencent_secret_key | +| Baidu | ERNIE irag-1.0 | `baidu` | baidu_api_key | +| Stability AI | Stable Diffusion 3.5 large turbo | `stability` | stability_api_key | +| Luma Labs | Photon | `luma` | luma_api_key | +| Ideogram | Ideogram V_2 | `ideogram` | ideogram_api_key | +| Recraft | Recraft V3 | `recraft` | recraft_api_key | +| Amazon | Titan Image Generator V2 | `amazon` | aws_access_key_id and aws_secret_access_key | +| Hidream | Hidream I1 | `hidream` | hidream_api_key | + +
#### 3. 配置上传参数 @@ -374,6 +405,12 @@ docker compose up -d ## 特别感谢 +- [大模型API](https://www.dmxapi.cn/register?aff=vRzR)([DMXAPI.cn](https://www.dmxapi.cn/register?aff=vRzR))，**DMX 取自“大模型”的拼音首字母，行业领先的智能API聚合服务平台**，旨在帮助 LLM 应用开发的初学者轻松接入多种大模型，快速进入 AI 应用的广阔领域。 + 1. **人民币计价全球人工智能大模型API**，[聚合中国和全球**300+多模态大模型**](https://www.dmxapi.cn/pricing)，直连畅通使用国内外领先大模型 API 服务，1个Key使用全模型，涵盖各个领域模型，应有尽有。 + 2. **RPM / TPM 无上限**，注册就是顶级账号，不设 RPM / TPM 限制，企业客户集群服务器，支持无限并发。 + 3. **合规发票 充值即开**，企业客户支持公对公付款，开具正规发票。 + 4. **海外模型低至 7 折，模型原厂集采直供**，通过直接与大模型原厂合作，我们采用集中采购的方式获取资源，确保为您提供极具竞争力的价格，**以更低的成本获取顶级的大模型服务**。 + 5. **坚守诚信与专业**，确保向客户提供真实、可靠的模型服务，维护客户的信任与满意度，[服务与承诺](https://dmxapi.cn/chengnuo.html)。 - [acgnhiki/blrec](https://github.com/acgnhiki/blrec) - [OpenAI/whisper](https://github.com/OpenAI/whisper) - [biliup/biliup-rs](https://github.com/biliup/biliup-rs) diff --git a/assets/dmx.png b/assets/dmx.png new file mode 100644 index 0000000..643723f Binary files /dev/null and b/assets/dmx.png differ diff --git a/bilive.toml b/bilive.toml index f692415..96968c8 100644 --- a/bilive.toml +++ b/bilive.toml @@ -40,7 +40,12 @@ sensenova_api_key = "" # Apply for your own SenseNova API key at https://console generate_cover = false # whether to generate cover cover_prompt = "" # Write your own cover prompt here image_gen_model = "minimax" # the image generation model, can be "minimax" or "siliconflow" or "tencent" or "baidu" or "stability" or "luma" or "ideogram" or "recraft" or "amazon" or "hidream" -dmx_api_token = "" # Apply for your own dmxapi token at https://www.dmxapi.cn/token + +# 大模型 API(DMXAPI) 行业领先的 api 聚合平台 +# DMXAPI.cn 一个key用全球大模型 GPT Claude Gemini 6.8折起 +# ssvip.DMXAPI.com 提供生产级稳定服务 官方 +dmx_api_token = "" # Apply for your own dmxapi token at https://www.dmxapi.cn/register?aff=vRzR + minimax_api_key = "" # Apply for your own Minimax API key at https://platform.minimaxi.com/user-center/basic-information/interface-key siliconflow_api_key = "" # Apply for your own SiliconFlow API key at https://cloud.siliconflow.cn/i/3Szr5BVg tencent_secret_id = "" # Apply for your own Tencent Cloud API key at https://console.cloud.tencent.com/cam/capi diff --git a/docs/getting-started.md b/docs/getting-started.md index 2c2eb7e..c625991 100644 --- a/docs/getting-started.md +++ b/docs/getting-started.md @@ -5,6 +5,27 @@ Automatically monitors and records Bilibili live broadcasts and danmaku (including paid comments, gifts, etc.), converts danmaku according to resolution, recognizes speech and renders subtitles into videos, splits exciting fragments according to danmaku density, and generates interesting titles through video understanding models, automatically generates video covers using image generation models, and automatically posts videos and slices to Bilibili, compatible with the version without GPU, compatible with low-configuration servers and hosts. +# Sponsorship + +![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-05-04-01-45-57.png) + +
+ + **大模型API(DMXAPI)** Industry-leading API aggregation platform **[Details](https://bilive.timerring.com/reference.html)** + +
+ DMX = The abbreviation of 大模型 + +
    +
  • DMXAPI.cn A key with a global model
    • +
  • GPT Claude Gemini from 62% off
    • +
  • ssvip.DMXAPI.com Provide production-level stable services
    • +
+ +
+ +
+ ## Major features - **Fast**：Use the `pipeline` pipeline to process videos, in ideal conditions, the recording and live broadcast differ by half an hour, and the recording can be上线录播，**Currently the fastest version of Bilibili recording**! @@ -33,7 +54,9 @@ Automatically monitors and records Bilibili live broadcasts and danmaku (includi - `Ideogram V_2` - `Recraft` - `Amazon Titan Image Generator V2` + - `Hidream I1` + - `kling-v1-5` The project architecture process is as follows: -![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-04-12-17-04-11.png) \ No newline at end of file +![](https://cdn.jsdelivr.net/gh/timerring/scratchpad2023/2024/2025-05-03-22-09-56.png) \ No newline at end of file diff --git a/docs/reference.md b/docs/reference.md index 3085e8b..fc7e94a 100644 --- a/docs/reference.md +++ b/docs/reference.md @@ -1,5 +1,18 @@ ## Reference +- [大模型API](https://www.dmxapi.cn/register?aff=vRzR)([DMXAPI.cn](https://www.dmxapi.cn/register?aff=vRzR))，**DMX 取自“大模型”的拼音首字母，行业领先的智能API聚合服务平台**，旨在帮助 LLM 应用开发的初学者轻松接入多种大模型，快速进入 AI 应用的广阔领域。 + 1. **人民币计价全球人工智能大模型API**，[聚合中国和全球**300+多模态大模型**](https://www.dmxapi.cn/pricing)，直连畅通使用国内外领先大模型 API 服务，1个Key使用全模型，涵盖各个领域模型，应有尽有。 + 2. **RPM / TPM 无上限**，注册就是顶级账号，不设 RPM / TPM 限制，企业客户集群服务器，支持无限并发。 + 3. **合规发票 充值即开**，企业客户支持公对公付款，开具正规发票。 + 4. **海外模型低至 7 折，模型原厂集采直供**，通过直接与大模型原厂合作，我们采用集中采购的方式获取资源，确保为您提供极具竞争力的价格，**以更低的成本获取顶级的大模型服务**。 + 5. **坚守诚信与专业**，确保向客户提供真实、可靠的模型服务，维护客户的信任与满意度，[服务与承诺](https://dmxapi.cn/chengnuo.html)。 + +- [DMX API](https://www.dmxapi.cn/register?aff=vRzR) ([DMXAPI.cn](https://www.dmxapi.cn/register?aff=vRzR)), **DMX comes from the pinyin initials of "Da Mo Xing" (Large Model), a leading intelligent API aggregation platform** designed to help LLM application developers easily integrate various large models and quickly enter the vast field of AI applications. + 1. **Global AI Large Model APIs priced in RMB**, [aggregating **300+ multimodal large models** from China and worldwide](https://www.dmxapi.cn/pricing). Direct and smooth access to leading model API services both domestically and internationally. One Key for all models, covering various domains, comprehensive and inclusive. + 2. **Unlimited RPM / TPM**, register to become a top-tier account with no RPM / TPM restrictions. Enterprise customers get cluster server support with unlimited concurrency. + 3. **Compliant invoices available immediately upon recharge**, enterprise customers support B2B payment with official invoices. + 4. **Overseas models at up to 30% discount, direct supply through model vendor bulk procurement**. Through direct cooperation with large model vendors, we obtain resources through centralized procurement to ensure highly competitive pricing, **accessing top-tier large model services at lower costs**. + 5. **Upholding integrity and professionalism**, ensuring the provision of authentic and reliable model services to maintain customer trust and satisfaction, [Services and Commitments](https://dmxapi.cn/chengnuo.html). - [acgnhiki/blrec](https://github.com/acgnhiki/blrec) - [OpenAI/whisper](https://github.com/OpenAI/whisper) - [biliup/biliup-rs](https://github.com/biliup/biliup-rs)