mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-07-11 08:57:22 +08:00
Compare commits
11 Commits
6c5e28e957
...
4913d52aeb
| Author | SHA1 | Date | |
|---|---|---|---|
|
4913d52aeb | ||
|
|
091b70edda | ||
|
|
ffbecfffb9 | ||
|
|
b481bc15af | ||
|
|
6880614319 | ||
|
|
51bf508a0b | ||
|
|
a3020f107e | ||
|
|
7cf4e78335 | ||
|
|
7747c342d4 | ||
|
|
439bd807f8 | ||
|
|
aa2ab2415c |
91
.github/workflows/cla.yml
vendored
Normal file
91
.github/workflows/cla.yml
vendored
Normal file
@ -0,0 +1,91 @@
|
||||
name: CLA Assistant
|
||||
|
||||
on:
|
||||
issue_comment:
|
||||
types: [created]
|
||||
pull_request_target:
|
||||
types: [opened, synchronize, closed]
|
||||
|
||||
permissions:
|
||||
actions: write
|
||||
contents: read # 'read' is enough because signatures live in a REMOTE repo
|
||||
pull-requests: write
|
||||
statuses: write
|
||||
|
||||
jobs:
|
||||
cla-assistant:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
# The CLA action normally requires every commit author in a PR to sign.
|
||||
# We only want the PR author to sign, so we allowlist all other committers
|
||||
# by computing them from the PR's commits and excluding the PR author.
|
||||
- name: Build author-only allowlist
|
||||
id: allowlist
|
||||
if: >
|
||||
github.event_name == 'pull_request_target' ||
|
||||
(github.event_name == 'issue_comment' && github.event.issue.pull_request && (
|
||||
github.event.comment.body == 'recheck' ||
|
||||
github.event.comment.body == 'I have read and agree to the Contributor License Agreement'
|
||||
))
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
PR_NUMBER: ${{ github.event.pull_request.number || github.event.issue.number }}
|
||||
PR_AUTHOR: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
|
||||
BASE_ALLOWLIST: action@github.com,actions-user,ampagent,claude,comfy-pr-bot,GitHub Action,github-actions,github-actions[bot],Glary Bot,Glary-Bot,*[bot]
|
||||
run: |
|
||||
others=$(gh api "repos/${{ github.repository }}/pulls/${PR_NUMBER}/commits" --paginate \
|
||||
--jq '.[] | (.author.login // empty), (.committer.login // empty)' \
|
||||
| sort -u | grep -vix "${PR_AUTHOR}" | paste -sd, -)
|
||||
if [ -n "$others" ]; then
|
||||
echo "allowlist=${BASE_ALLOWLIST},${others}" >> "$GITHUB_OUTPUT"
|
||||
else
|
||||
echo "allowlist=${BASE_ALLOWLIST}" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
|
||||
- name: CLA Assistant
|
||||
# Run on PR events, on "recheck" comment, or when someone posts the exact signing phrase.
|
||||
# IMPORTANT: this phrase must match `custom-pr-sign-comment` below.
|
||||
if: >
|
||||
github.event_name == 'pull_request_target' ||
|
||||
(github.event_name == 'issue_comment' && github.event.issue.pull_request && (
|
||||
github.event.comment.body == 'recheck' ||
|
||||
github.event.comment.body == 'I have read and agree to the Contributor License Agreement'
|
||||
))
|
||||
uses: contributor-assistant/github-action@ca4a40a7d1004f18d9960b404b97e5f30a505a08 # v2.6.1
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
# PAT required to write to the centralized signatures repo.
|
||||
PERSONAL_ACCESS_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
|
||||
with:
|
||||
# Where the CLA document lives (shown to contributors)
|
||||
path-to-document: https://github.com/Comfy-Org/comfy-cla/blob/main/comfyui_icla.md
|
||||
|
||||
# Centralized signature storage
|
||||
remote-organization-name: comfy-org
|
||||
remote-repository-name: comfy-cla
|
||||
path-to-signatures: signatures/cla.json
|
||||
branch: main
|
||||
|
||||
# Only the PR author must sign: bots plus every non-author committer
|
||||
# are allowlisted via the "Build author-only allowlist" step above.
|
||||
# *[bot] is a catch-all for any GitHub App bot account.
|
||||
allowlist: ${{ steps.allowlist.outputs.allowlist }}
|
||||
|
||||
# Custom PR comment messages
|
||||
custom-notsigned-prcomment: |
|
||||
🎉 Thank you for your contribution, we really appreciate it! 🎉
|
||||
|
||||
Like many open source projects, we require contributors to sign our [Contributor License Agreement (CLA)](https://github.com/Comfy-Org/comfy-cla/blob/main/comfyui_icla.md). A CLA makes the ownership of contributions explicit, so contributors and the project share a clear understanding of how the code can be used. By signing, you:
|
||||
|
||||
- Confirm that you own your contribution.
|
||||
- Keep the right to reuse your own code.
|
||||
- Grant us a copyright license to include and share it within our projects.
|
||||
|
||||
CLAs are standard practice across major open source projects including those under the Apache Software Foundation and the Linux Foundation. Ours is based on the Apache Software Foundation's CLA. Most importantly, it would enable us to relicense the project under a more permissive license in the future, giving the project and its community greater flexibility.
|
||||
|
||||
✍ **To sign, please post a new comment on this PR with exactly the following text:** ✍
|
||||
|
||||
custom-pr-sign-comment: I have read and agree to the Contributor License Agreement
|
||||
|
||||
custom-allsigned-prcomment: |
|
||||
✅ All contributors have signed the CLA. Thank you! This PR is ready to be merged.
|
||||
@ -127,6 +127,8 @@
|
||||
- Do not add unnecessary `try`/`except` blocks. Use them for optional dependency,
|
||||
platform, or backend capability detection only when the program has a useful
|
||||
fallback. Prefer specific exception types when changing new code.
|
||||
- If a library version is pinned in `requirements.txt`, do not add code to
|
||||
ComfyUI to handle older versions of that library.
|
||||
- Remove any workarounds for PyTorch versions that ComfyUI no longer officially
|
||||
supports. Deprecated workarounds include catching an exception and rerunning
|
||||
the same op with the input cast to float. If a workaround does not have a
|
||||
|
||||
@ -14,6 +14,8 @@
|
||||
[![][github-downloads-shield]][github-downloads-link]
|
||||
[![][github-downloads-latest-shield]][github-downloads-link]
|
||||
|
||||
[中文版 README](README_CN.md)
|
||||
|
||||
[matrix-shield]: https://img.shields.io/badge/Matrix-000000?style=flat&logo=matrix&logoColor=white
|
||||
[matrix-url]: https://app.element.io/#/room/%23comfyui_space%3Amatrix.org
|
||||
[website-shield]: https://img.shields.io/badge/ComfyOrg-4285F4?style=flat
|
||||
@ -229,7 +231,7 @@ Python 3.14 works but some custom nodes may have issues. The free threaded varia
|
||||
|
||||
Python 3.13 is very well supported. If you have trouble with some custom node dependencies on 3.13 you can try 3.12
|
||||
|
||||
torch 2.4 and above is supported but some features and optimizations might only work on newer versions. We generally recommend using the latest major version of pytorch with the latest cuda version unless it is less than 2 weeks old.
|
||||
torch 2.5 is minimally supported but using a newer version is extremely recommended. Some features and optimizations might only work on newer versions. We generally recommend using the latest major version of pytorch with the latest cuda version unless it is less than 2 weeks old. If your pytorch is more than 6 months old, please update it.
|
||||
|
||||
### Instructions:
|
||||
|
||||
|
||||
455
README_CN.md
Normal file
455
README_CN.md
Normal file
@ -0,0 +1,455 @@
|
||||
<div align="center">
|
||||
|
||||
# ComfyUI
|
||||
**最强大、模块化的可视化 AI 引擎和应用。**
|
||||
|
||||
|
||||
[![Website][website-shield]][website-url]
|
||||
[![Dynamic JSON Badge][discord-shield]][discord-url]
|
||||
[![Twitter][twitter-shield]][twitter-url]
|
||||
[![Matrix][matrix-shield]][matrix-url]
|
||||
<br>
|
||||
[![][github-release-shield]][github-release-link]
|
||||
[![][github-release-date-shield]][github-release-link]
|
||||
[![][github-downloads-shield]][github-downloads-link]
|
||||
[![][github-downloads-latest-shield]][github-downloads-link]
|
||||
|
||||
[matrix-shield]: https://img.shields.io/badge/Matrix-000000?style=flat&logo=matrix&logoColor=white
|
||||
[matrix-url]: https://app.element.io/#/room/%23comfyui_space%3Amatrix.org
|
||||
[website-shield]: https://img.shields.io/badge/ComfyOrg-4285F4?style=flat
|
||||
[website-url]: https://www.comfy.org/
|
||||
<!-- Workaround to display total user from https://github.com/badges/shields/issues/4500#issuecomment-2060079995 -->
|
||||
[discord-shield]: https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2Fcomfyorg%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&logo=discord&logoColor=white&label=Discord&color=green&suffix=%20total
|
||||
[discord-url]: https://www.comfy.org/discord
|
||||
[twitter-shield]: https://img.shields.io/twitter/follow/ComfyUI
|
||||
[twitter-url]: https://x.com/ComfyUI
|
||||
|
||||
[github-release-shield]: https://img.shields.io/github/v/release/comfyanonymous/ComfyUI?style=flat&sort=semver
|
||||
[github-release-link]: https://github.com/comfyanonymous/ComfyUI/releases
|
||||
[github-release-date-shield]: https://img.shields.io/github/release-date/comfyanonymous/ComfyUI?style=flat
|
||||
[github-downloads-shield]: https://img.shields.io/github/downloads/comfyanonymous/ComfyUI/total?style=flat
|
||||
[github-downloads-latest-shield]: https://img.shields.io/github/downloads/comfyanonymous/ComfyUI/latest/total?style=flat&label=downloads%40latest
|
||||
[github-downloads-link]: https://github.com/comfyanonymous/ComfyUI/releases
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
ComfyUI 让你能够使用基于图形/节点/流程图的界面设计和执行高级的 Stable Diffusion 管道。支持 Windows、Linux 和 macOS。
|
||||
|
||||
## 快速开始
|
||||
|
||||
#### [桌面应用程序](https://www.comfy.org/download)
|
||||
- 最简单的入门方式。
|
||||
- 支持 Windows 和 macOS。
|
||||
|
||||
#### [Windows 便携包](#安装)
|
||||
- 获取最新提交，完全便携。
|
||||
- 支持 Windows。
|
||||
|
||||
#### [手动安装](#手动安装-windows-linux)
|
||||
支持所有操作系统和 GPU 类型（NVIDIA、AMD、Intel、Apple Silicon、Ascend）。
|
||||
|
||||
## [示例](https://comfyanonymous.github.io/ComfyUI_examples/)
|
||||
查看 [示例工作流](https://comfyanonymous.github.io/ComfyUI_examples/) 了解 ComfyUI 能做什么。
|
||||
|
||||
## 特性
|
||||
- 节点/图形/流程图界面，无需编写任何代码即可实验和创建复杂的 Stable Diffusion 工作流。
|
||||
- 图像模型
|
||||
- SD1.x, SD2.x ([unCLIP](https://comfyanonymous.github.io/ComfyUI_examples/unclip/))
|
||||
- [SDXL](https://comfyanonymous.github.io/ComfyUI_examples/sdxl/), [SDXL Turbo](https://comfyanonymous.github.io/ComfyUI_examples/sdturbo/)
|
||||
- [Stable Cascade](https://comfyanonymous.github.io/ComfyUI_examples/stable_cascade/)
|
||||
- [SD3 和 SD3.5](https://comfyanonymous.github.io/ComfyUI_examples/sd3/)
|
||||
- Pixart Alpha 和 Sigma
|
||||
- [AuraFlow](https://comfyanonymous.github.io/ComfyUI_examples/aura_flow/)
|
||||
- [HunyuanDiT](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_dit/)
|
||||
- [Flux](https://comfyanonymous.github.io/ComfyUI_examples/flux/)
|
||||
- [Lumina Image 2.0](https://comfyanonymous.github.io/ComfyUI_examples/lumina2/)
|
||||
- [HiDream](https://comfyanonymous.github.io/ComfyUI_examples/hidream/)
|
||||
- [Qwen Image](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/)
|
||||
- [Hunyuan Image 2.1](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_image/)
|
||||
- [Flux 2](https://comfyanonymous.github.io/ComfyUI_examples/flux2/)
|
||||
- [Z Image](https://comfyanonymous.github.io/ComfyUI_examples/z_image/)
|
||||
- 图像编辑模型
|
||||
- [Omnigen 2](https://comfyanonymous.github.io/ComfyUI_examples/omnigen/)
|
||||
- [Flux Kontext](https://comfyanonymous.github.io/ComfyUI_examples/flux/#flux-kontext-image-editing-model)
|
||||
- [HiDream E1.1](https://comfyanonymous.github.io/ComfyUI_examples/hidream/#hidream-e11)
|
||||
- [Qwen Image Edit](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/#edit-model)
|
||||
- 视频模型
|
||||
- [Stable Video Diffusion](https://comfyanonymous.github.io/ComfyUI_examples/video/)
|
||||
- [Mochi](https://comfyanonymous.github.io/ComfyUI_examples/mochi/)
|
||||
- [LTX-Video](https://comfyanonymous.github.io/ComfyUI_examples/ltxv/)
|
||||
- [Hunyuan Video](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_video/)
|
||||
- [Wan 2.1](https://comfyanonymous.github.io/ComfyUI_examples/wan/)
|
||||
- [Wan 2.2](https://comfyanonymous.github.io/ComfyUI_examples/wan22/)
|
||||
- [Hunyuan Video 1.5](https://docs.comfy.org/tutorials/video/hunyuan/hunyuan-video-1-5)
|
||||
- 音频模型
|
||||
- [Stable Audio](https://comfyanonymous.github.io/ComfyUI_examples/audio/)
|
||||
- [ACE Step](https://comfyanonymous.github.io/ComfyUI_examples/audio/)
|
||||
- 3D 模型
|
||||
- [Hunyuan3D 2.0](https://docs.comfy.org/tutorials/3d/hunyuan3D-2)
|
||||
- 异步队列系统
|
||||
- 许多优化：仅重新执行执行之间更改的工作流部分。
|
||||
- 智能内存管理：可以通过智能卸载在低至 1GB vram 的 GPU 上自动运行大型模型。
|
||||
- 即使没有 GPU 也可以工作：```--cpu```（慢）
|
||||
- 可以加载 ckpt 和 safetensors：一体化检查点或独立扩散模型、VAE 和 CLIP 模型。
|
||||
- 安全加载 ckpt、pt、pth 等文件。
|
||||
- Embeddings/Textual inversion
|
||||
- [Loras (regular, locon and loha)](https://comfyanonymous.github.io/ComfyUI_examples/lora/)
|
||||
- [Hypernetworks](https://comfyanonymous.github.io/ComfyUI_examples/hypernetworks/)
|
||||
- 从生成的 PNG、WebP 和 FLAC 文件加载完整的工作流（带有种子）。
|
||||
- 将工作流保存/加载为 Json 文件。
|
||||
- 节点界面可用于创建复杂的工作流，如 [Hires fix](https://comfyanonymous.github.io/ComfyUI_examples/2_pass_txt2img/) 或更高级的工作流。
|
||||
- [区域合成](https://comfyanonymous.github.io/ComfyUI_examples/area_composition/)
|
||||
- [Inpainting](https://comfyanonymous.github.io/ComfyUI_examples/inpaint/) 支持常规和 inpainting 模型。
|
||||
- [ControlNet 和 T2I-Adapter](https://comfyanonymous.github.io/ComfyUI_examples/controlnet/)
|
||||
- [放大模型 (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)](https://comfyanonymous.github.io/ComfyUI_examples/upscale_models/)
|
||||
- [GLIGEN](https://comfyanonymous.github.io/ComfyUI_examples/gligen/)
|
||||
- [模型合并](https://comfyanonymous.github.io/ComfyUI_examples/model_merging/)
|
||||
- [LCM 模型和 Loras](https://comfyanonymous.github.io/ComfyUI_examples/lcm/)
|
||||
- 使用 [TAESD](#如何显示高质量预览) 进行潜在预览
|
||||
- 完全离线工作：除非你想要，否则核心永远不会下载任何东西。
|
||||
- 可选的 API 节点，通过在线 [Comfy API](https://docs.comfy.org/tutorials/api-nodes/overview) 使用外部提供商的付费模型。
|
||||
- [配置文件](extra_model_paths.yaml.example) 用于设置模型的搜索路径。
|
||||
|
||||
工作流示例可以在 [示例页面](https://comfyanonymous.github.io/ComfyUI_examples/) 找到。
|
||||
|
||||
## 发布流程
|
||||
|
||||
ComfyUI 遵循每周发布周期，目标是周一，但由于模型发布或代码库的重大更改，这经常会发生变化。有三个相互关联的存储库：
|
||||
|
||||
1. **[ComfyUI Core](https://github.com/comfyanonymous/ComfyUI)**
|
||||
- 大约每周发布一个新的稳定版本（例如 v0.7.0）。
|
||||
- 稳定版本标签之外的提交可能非常不稳定，并破坏许多自定义节点。
|
||||
- 作为桌面版本的基础。
|
||||
|
||||
2. **[ComfyUI Desktop](https://github.com/Comfy-Org/desktop)**
|
||||
- 使用最新的稳定核心版本构建新版本。
|
||||
|
||||
3. **[ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend)**
|
||||
- 每周前端更新合并到核心存储库中。
|
||||
- 即将发布的核心版本的功能被冻结。
|
||||
- 下一个发布周期的开发继续进行。
|
||||
|
||||
## 快捷键
|
||||
|
||||
| 快捷键 | 说明 |
|
||||
|------------------------------------|--------------------------------------------------------------------------------------------------------------------|
|
||||
| `Ctrl` + `Enter` | 将当前图形排队生成 |
|
||||
| `Ctrl` + `Shift` + `Enter` | 将当前图形作为第一个排队生成 |
|
||||
| `Ctrl` + `Alt` + `Enter` | 取消当前生成 |
|
||||
| `Ctrl` + `Z`/`Ctrl` + `Y` | 撤销/重做 |
|
||||
| `Ctrl` + `S` | 保存工作流 |
|
||||
| `Ctrl` + `O` | 加载工作流 |
|
||||
| `Ctrl` + `A` | 选择所有节点 |
|
||||
| `Alt `+ `C` | 折叠/展开选定的节点 |
|
||||
| `Ctrl` + `M` | 静音/取消静音选定的节点 |
|
||||
| `Ctrl` + `B` | 绕过选定的节点（就像节点从图中移除并且连线重新连接通过一样） |
|
||||
| `Delete`/`Backspace` | 删除选定的节点 |
|
||||
| `Ctrl` + `Backspace` | 删除当前图形 |
|
||||
| `Space` | 按住并移动光标时移动画布 |
|
||||
| `Ctrl`/`Shift` + `Click` | 将点击的节点添加到选择中 |
|
||||
| `Ctrl` + `C`/`Ctrl` + `V` | 复制并粘贴选定的节点（不保持与未选定节点输出的连接） |
|
||||
| `Ctrl` + `C`/`Ctrl` + `Shift` + `V` | 复制并粘贴选定的节点（保持从未选定节点的输出到粘贴节点的输入的连接） |
|
||||
| `Shift` + `Drag` | 同时移动多个选定的节点 |
|
||||
| `Ctrl` + `D` | 加载默认图形 |
|
||||
| `Alt` + `+` | 画布放大 |
|
||||
| `Alt` + `-` | 画布缩小 |
|
||||
| `Ctrl` + `Shift` + LMB + 垂直拖动 | 画布放大/缩小 |
|
||||
| `P` | 固定/取消固定选定的节点 |
|
||||
| `Ctrl` + `G` | 组合选定的节点 |
|
||||
| `Q` | 切换队列的可见性 |
|
||||
| `H` | 切换历史记录的可见性 |
|
||||
| `R` | 刷新图形 |
|
||||
| `F` | 显示/隐藏菜单 |
|
||||
| `.` | 适应视图到选择（未选择任何内容时适应整个图形） |
|
||||
| 双击 LMB | 打开节点快速搜索面板 |
|
||||
| `Shift` + 拖动 | 一次移动多条连线 |
|
||||
| `Ctrl` + `Alt` + LMB | 断开点击插槽的所有连线 |
|
||||
|
||||
macOS 用户可以将 `Ctrl` 替换为 `Cmd`
|
||||
|
||||
# 安装
|
||||
|
||||
## Windows 便携版
|
||||
|
||||
在 [发布页面](https://github.com/comfyanonymous/ComfyUI/releases) 上有一个适用于 Windows 的便携式独立构建，应该可以在 Nvidia GPU 上运行，或者仅在 CPU 上运行。
|
||||
|
||||
### [直接下载链接](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia.7z)
|
||||
|
||||
只需下载，使用 [7-Zip](https://7-zip.org) 解压，或者在最近的 Windows 版本上使用资源管理器解压并运行。对于较小的模型，通常只需要将 checkpoints（巨大的 ckpt/safetensors 文件）放在：ComfyUI\models\checkpoints 中，但许多较大的模型有多个文件。请务必按照说明了解将它们放在 ComfyUI\models\ 的哪个子文件夹中。
|
||||
|
||||
如果解压有问题，请右键单击文件 -> 属性 -> 解除锁定
|
||||
|
||||
如果无法启动，请更新您的 Nvidia 驱动程序。
|
||||
|
||||
#### 替代下载：
|
||||
|
||||
[适用于 AMD GPU 的实验性便携版](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_amd.7z)
|
||||
|
||||
[带有 pytorch cuda 12.8 和 python 3.12 的便携版](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu128.7z)。
|
||||
|
||||
[带有 pytorch cuda 12.6 和 python 3.12 的便携版](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu126.7z)（支持 Nvidia 10 系列及更旧的 GPU）。
|
||||
|
||||
#### 如何在另一个 UI 和 ComfyUI 之间共享模型？
|
||||
|
||||
请参阅 [配置文件](extra_model_paths.yaml.example) 以设置模型的搜索路径。在独立的 Windows 构建中，您可以在 ComfyUI 目录中找到此文件。将此文件重命名为 extra_model_paths.yaml 并使用您喜欢的文本编辑器进行编辑。
|
||||
|
||||
|
||||
## [comfy-cli](https://docs.comfy.org/comfy-cli/getting-started)
|
||||
|
||||
您可以使用 comfy-cli 安装并启动 ComfyUI：
|
||||
```bash
|
||||
pip install comfy-cli
|
||||
comfy install
|
||||
```
|
||||
|
||||
## 手动安装 (Windows, Linux)
|
||||
|
||||
Python 3.14 可以工作，但您可能会遇到 torch 编译节点的问题。自由线程变体仍然缺少一些依赖项。
|
||||
|
||||
Python 3.13 支持得很好。如果您在 3.13 上遇到某些自定义节点依赖项的问题，可以尝试 3.12。
|
||||
|
||||
### 说明：
|
||||
|
||||
Git clone 此仓库。
|
||||
|
||||
将您的 SD checkpoints（巨大的 ckpt/safetensors 文件）放在：models/checkpoints
|
||||
|
||||
将您的 VAE 放在：models/vae
|
||||
|
||||
|
||||
### AMD GPU (Linux)
|
||||
|
||||
AMD 用户如果尚未安装，可以使用 pip 安装 rocm 和 pytorch，这是安装稳定版本的命令：
|
||||
|
||||
```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.4```
|
||||
|
||||
这是安装带有 ROCm 7.0 的 nightly 版本的命令，可能会有一些性能改进：
|
||||
|
||||
```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.1```
|
||||
|
||||
|
||||
### AMD GPU（实验性：Windows 和 Linux），仅限 RDNA 3, 3.5 和 4。
|
||||
|
||||
这些硬件支持比上面的构建少，但它们可以在 Windows 上运行。您还需要安装特定于您的硬件的 pytorch 版本。
|
||||
|
||||
RDNA 3 (RX 7000 系列):
|
||||
|
||||
```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx110X-dgpu/```
|
||||
|
||||
RDNA 3.5 (Strix halo/Ryzen AI Max+ 365):
|
||||
|
||||
```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx1151/```
|
||||
|
||||
RDNA 4 (RX 9000 系列):
|
||||
|
||||
```pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx120X-all/```
|
||||
|
||||
### Intel GPU (Windows 和 Linux)
|
||||
|
||||
Intel Arc GPU 用户可以使用 pip 安装具有 torch.xpu 支持的原生 PyTorch。更多信息可以在 [这里](https://pytorch.org/docs/main/notes/get_start_xpu.html) 找到。
|
||||
|
||||
1. 要安装 PyTorch xpu，请使用以下命令：
|
||||
|
||||
```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/xpu```
|
||||
|
||||
这是安装 Pytorch xpu nightly 的命令，可能会有一些性能改进：
|
||||
|
||||
```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/xpu```
|
||||
|
||||
### NVIDIA
|
||||
|
||||
Nvidia 用户应使用此命令安装稳定的 pytorch：
|
||||
|
||||
```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130```
|
||||
|
||||
这是安装 pytorch nightly 的命令，可能会有性能改进。
|
||||
|
||||
```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu130```
|
||||
|
||||
#### 故障排除
|
||||
|
||||
如果您收到 "Torch not compiled with CUDA enabled" 错误，请使用以下命令卸载 torch：
|
||||
|
||||
```pip uninstall torch```
|
||||
|
||||
并再次使用上面的命令安装它。
|
||||
|
||||
### 依赖项
|
||||
|
||||
通过在 ComfyUI 文件夹中打开终端并运行以下命令来安装依赖项：
|
||||
|
||||
```pip install -r requirements.txt```
|
||||
|
||||
在此之后，您应该已经安装了所有内容，并可以继续运行 ComfyUI。
|
||||
|
||||
### 其他：
|
||||
|
||||
#### Apple Mac silicon
|
||||
|
||||
您可以在任何最近的 macOS 版本上在 Apple Mac silicon (M1 或 M2) 上安装 ComfyUI。
|
||||
|
||||
1. 安装 pytorch nightly。有关说明，请阅读 [Mac 上的加速 PyTorch 训练](https://developer.apple.com/metal/pytorch/) Apple 开发者指南（确保安装最新的 pytorch nightly）。
|
||||
1. 按照 Windows 和 Linux 的 [ComfyUI 手动安装](#手动安装-windows-linux) 说明进行操作。
|
||||
1. 安装 ComfyUI [依赖项](#依赖项)。如果您安装了另一个 Stable Diffusion UI，[您可能能够重用依赖项](#我已经安装了另一个-stable-diffusion-ui-我真的必须安装所有这些依赖项吗)。
|
||||
1. 通过运行 `python main.py` 启动 ComfyUI
|
||||
|
||||
> **注意**：请记住将您的模型、VAE、LoRA 等添加到相应的 Comfy 文件夹中，如 [ComfyUI 手动安装](#手动安装-windows-linux) 中所述。
|
||||
|
||||
#### Ascend NPU
|
||||
|
||||
对于与 Ascend Extension for PyTorch (torch_npu) 兼容的模型。首先，确保您的环境满足 [安装](https://ascend.github.io/docs/sources/ascend/quick_install.html) 页面上列出的先决条件。这是针对您的平台和安装方法的逐步指南：
|
||||
|
||||
1. 如果需要，首先安装 torch-npu 安装页面中指定的推荐或更新的 Linux 内核版本。
|
||||
2. 按照针对您特定平台的说明，继续安装 Ascend Basekit，其中包括驱动程序、固件和 CANN。
|
||||
3. 接下来，按照 [安装](https://ascend.github.io/docs/sources/pytorch/install.html#pytorch) 页面上的特定于平台的说明安装 torch-npu 的必要包。
|
||||
4. 最后，遵循 Linux 的 [ComfyUI 手动安装](#手动安装-windows-linux) 指南。安装所有组件后，您可以如前所述运行 ComfyUI。
|
||||
|
||||
#### Cambricon MLU
|
||||
|
||||
对于与 Cambricon Extension for PyTorch (torch_mlu) 兼容的模型。这是针对您的平台和安装方法的逐步指南：
|
||||
|
||||
1. 按照 [安装](https://www.cambricon.com/docs/sdk_1.15.0/cntoolkit_3.7.2/cntoolkit_install_3.7.2/index.html) 上的特定于平台的说明安装 Cambricon CNToolkit
|
||||
2. 接下来，按照 [安装](https://www.cambricon.com/docs/sdk_1.15.0/cambricon_pytorch_1.17.0/user_guide_1.9/index.html) 上的说明安装 PyTorch(torch_mlu)
|
||||
3. 通过运行 `python main.py` 启动 ComfyUI
|
||||
|
||||
#### Iluvatar Corex
|
||||
|
||||
对于与 Iluvatar Extension for PyTorch 兼容的模型。这是针对您的平台和安装方法的逐步指南：
|
||||
|
||||
1. 按照 [安装](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536) 上的特定于平台的说明安装 Iluvatar Corex Toolkit
|
||||
2. 通过运行 `python main.py` 启动 ComfyUI
|
||||
|
||||
|
||||
## [ComfyUI-Manager](https://github.com/Comfy-Org/ComfyUI-Manager/tree/manager-v4)
|
||||
|
||||
**ComfyUI-Manager** 是一个扩展，允许您轻松安装、更新和管理 ComfyUI 的自定义节点。
|
||||
|
||||
### 设置
|
||||
|
||||
1. 安装管理器依赖项：
|
||||
```bash
|
||||
pip install -r manager_requirements.txt
|
||||
```
|
||||
|
||||
2. 运行 ComfyUI 时使用 `--enable-manager` 标志启用管理器：
|
||||
```bash
|
||||
python main.py --enable-manager
|
||||
```
|
||||
|
||||
### 命令行选项
|
||||
|
||||
| 标志 | 描述 |
|
||||
|------|-------------|
|
||||
| `--enable-manager` | 启用 ComfyUI-Manager |
|
||||
| `--enable-manager-legacy-ui` | 使用旧版管理器 UI 而不是新 UI（需要 `--enable-manager`） |
|
||||
| `--disable-manager-ui` | 禁用管理器 UI 和端点，同时保留后台功能，如安全检查和计划安装完成（需要 `--enable-manager`） |
|
||||
|
||||
|
||||
# 运行
|
||||
|
||||
```python main.py```
|
||||
|
||||
### 对于 ROCm 未正式支持的 AMD 卡
|
||||
|
||||
如果有问题，请尝试使用此命令运行它：
|
||||
|
||||
对于 6700, 6600 和可能的其他 RDNA2 或更旧的卡：```HSA_OVERRIDE_GFX_VERSION=10.3.0 python main.py```
|
||||
|
||||
对于 AMD 7600 和可能的其他 RDNA3 卡：```HSA_OVERRIDE_GFX_VERSION=11.0.0 python main.py```
|
||||
|
||||
### AMD ROCm 提示
|
||||
|
||||
您可以使用此命令在某些 AMD GPU 上的 ComfyUI 中启用最近 pytorch 的实验性内存高效注意力，它应该已经在 RDNA3 上默认启用。如果这提高了您 GPU 上最新 pytorch 的速度，请报告它，以便我可以默认启用它。
|
||||
|
||||
```TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attention```
|
||||
|
||||
您也可以尝试设置此环境变量 `PYTORCH_TUNABLEOP_ENABLED=1`，这可能会加快速度，但代价是非常慢的初始运行。
|
||||
|
||||
# 注意事项
|
||||
|
||||
只有具有所有正确输入的输出的图形部分才会被执行。
|
||||
|
||||
只有从每次执行到下一次执行发生更改的图形部分才会被执行，如果您提交相同的图形两次，只有第一次会被执行。如果您更改图形的最后一部分，只有您更改的部分和依赖于它的部分会被执行。
|
||||
|
||||
将生成的 png 拖到网页上或加载它将为您提供完整的工作流，包括用于创建它的种子。
|
||||
|
||||
您可以使用 () 来更改单词或短语的强调，例如：(good code:1.2) 或 (bad code:0.8)。() 的默认强调是 1.1。要在实际提示中使用 () 字符，请像 \\( 或 \\) 一样转义它们。
|
||||
|
||||
您可以使用 {day|night} 进行通配符/动态提示。使用此语法 "{wild|card|test}" 将在每次您排队提示时由前端随机替换为 "wild"、"card" 或 "test"。要在实际提示中使用 {} 字符，请像：\\{ or \\} 一样转义它们。
|
||||
|
||||
动态提示还支持 C 风格的注释，如 `// comment` 或 `/* comment */`。
|
||||
|
||||
要在文本提示中使用文本反转概念/嵌入，请将它们放在 models/embeddings 目录中，并在 CLIPTextEncode 节点中像这样使用它们（您可以省略 .pt 扩展名）：
|
||||
|
||||
```embedding:embedding_filename.pt```
|
||||
|
||||
|
||||
## 如何显示高质量预览？
|
||||
|
||||
使用 ```--preview-method auto``` 启用预览。
|
||||
|
||||
默认安装包括一种快速的潜在预览方法，分辨率较低。要使用 [TAESD](https://github.com/madebyollin/taesd) 启用更高质量的预览，请下载 [taesd_decoder.pth, taesdxl_decoder.pth, taesd3_decoder.pth 和 taef1_decoder.pth](https://github.com/madebyollin/taesd/) 并将它们放在 `models/vae_approx` 文件夹中。安装完成后，重新启动 ComfyUI 并使用 `--preview-method taesd` 启动它以启用高质量预览。
|
||||
|
||||
## 如何使用 TLS/SSL？
|
||||
通过运行以下命令生成自签名证书（不适合共享/生产使用）和密钥：`openssl req -x509 -newkey rsa:4096 -keyout key.pem -out cert.pem -sha256 -days 3650 -nodes -subj "/C=XX/ST=StateName/L=CityName/O=CompanyName/OU=CompanySectionName/CN=CommonNameOrHostname"`
|
||||
|
||||
使用 `--tls-keyfile key.pem --tls-certfile cert.pem` 启用 TLS/SSL，应用程序现在将可以通过 `https://...` 而不是 `http://...` 访问。
|
||||
|
||||
> 注意：Windows 用户可以使用 [alexisrolland/docker-openssl](https://github.com/alexisrolland/docker-openssl) 或 [第三方二进制发行版](https://wiki.openssl.org/index.php/Binaries) 之一来运行上面的命令示例。
|
||||
<br/><br/>如果您使用容器，请注意卷挂载 `-v` 可以是相对路径，因此 `... -v ".\:/openssl-certs" ...` 将在命令提示符或 powershell 终端的当前目录中创建密钥和证书文件。
|
||||
|
||||
## 支持和开发频道
|
||||
|
||||
[Discord](https://comfy.org/discord): 尝试 #help 或 #feedback 频道。
|
||||
|
||||
[Matrix space: #comfyui_space:matrix.org](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) (它像 discord 但是开源的)。
|
||||
|
||||
另请参阅：[https://www.comfy.org/](https://www.comfy.org/)
|
||||
|
||||
## 前端开发
|
||||
|
||||
截至 2024 年 8 月 15 日，我们已过渡到新的前端，该前端现在托管在一个单独的存储库中：[ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend)。此存储库现在在 `web/` 目录下托管编译后的 JS（来自 TS/Vue）。
|
||||
|
||||
### 报告问题和请求功能
|
||||
|
||||
对于与前端相关的任何错误、问题或功能请求，请使用 [ComfyUI Frontend 存储库](https://github.com/Comfy-Org/ComfyUI_frontend)。这将帮助我们更有效地管理和解决前端特定的问题。
|
||||
|
||||
### 使用最新前端
|
||||
|
||||
新前端现在是 ComfyUI 的默认前端。但是，请注意：
|
||||
|
||||
1. 主 ComfyUI 存储库中的前端每两周更新一次。
|
||||
2. 每日发布在单独的前端存储库中可用。
|
||||
|
||||
要使用最新的前端版本：
|
||||
|
||||
1. 对于最新的每日发布，使用此命令行参数启动 ComfyUI：
|
||||
|
||||
```
|
||||
--front-end-version Comfy-Org/ComfyUI_frontend@latest
|
||||
```
|
||||
|
||||
2. 对于特定版本，将 `latest` 替换为所需的版本号：
|
||||
|
||||
```
|
||||
--front-end-version Comfy-Org/ComfyUI_frontend@1.2.2
|
||||
```
|
||||
|
||||
这种方法允许您轻松地在稳定的每两周发布和前沿的每日更新之间切换，甚至可以切换到特定版本进行测试。
|
||||
|
||||
### 访问旧版前端
|
||||
|
||||
如果您因任何原因需要使用旧版前端，可以使用以下命令行参数访问它：
|
||||
|
||||
```
|
||||
--front-end-version Comfy-Org/ComfyUI_legacy_frontend@latest
|
||||
```
|
||||
|
||||
这将使用保存在 [ComfyUI Legacy Frontend 存储库](https://github.com/Comfy-Org/ComfyUI_legacy_frontend) 中的旧版前端快照。
|
||||
|
||||
# QA
|
||||
|
||||
### 我应该为此购买哪种 GPU？
|
||||
|
||||
[请参阅此页面以获取一些建议](https://github.com/comfyanonymous/ComfyUI/wiki/Which-GPU-should-I-buy-for-ComfyUI)
|
||||
@ -225,6 +225,7 @@ parser.add_argument(
|
||||
)
|
||||
|
||||
parser.add_argument("--user-directory", type=is_valid_directory, default=None, help="Set the ComfyUI user directory with an absolute path. Overrides --base-directory.")
|
||||
parser.add_argument("--models-directory", type=is_valid_directory, default=None, help="Set the ComfyUI models directory. Overrides the models folder in --base-directory.")
|
||||
|
||||
parser.add_argument("--enable-compress-response-body", action="store_true", help="Enable compressing response body.")
|
||||
|
||||
|
||||
@ -217,10 +217,7 @@ class AceStepAttention(nn.Module):
|
||||
cos, sin = position_embeddings
|
||||
query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
|
||||
|
||||
n_rep = self.num_heads // self.num_kv_heads
|
||||
if n_rep > 1:
|
||||
key_states = key_states.repeat_interleave(n_rep, dim=1)
|
||||
value_states = value_states.repeat_interleave(n_rep, dim=1)
|
||||
gqa_kwargs = {"enable_gqa": True} if self.num_heads != self.num_kv_heads else {}
|
||||
|
||||
attn_bias = None
|
||||
if self.sliding_window is not None and not self.is_cross_attention:
|
||||
@ -244,7 +241,7 @@ class AceStepAttention(nn.Module):
|
||||
else:
|
||||
attn_bias = window_bias
|
||||
|
||||
attn_output = optimized_attention(query_states, key_states, value_states, self.num_heads, attn_bias, skip_reshape=True, low_precision_attention=False)
|
||||
attn_output = optimized_attention(query_states, key_states, value_states, self.num_heads, attn_bias, skip_reshape=True, low_precision_attention=False, **gqa_kwargs)
|
||||
attn_output = self.o_proj(attn_output)
|
||||
|
||||
return attn_output
|
||||
|
||||
@ -425,19 +425,16 @@ class Attention(nn.Module):
|
||||
if n == 1 and causal:
|
||||
causal = False
|
||||
|
||||
if h != kv_h:
|
||||
# Repeat interleave kv_heads to match q_heads
|
||||
heads_per_kv_head = h // kv_h
|
||||
k, v = map(lambda t: t.repeat_interleave(heads_per_kv_head, dim = 1), (k, v))
|
||||
gqa_kwargs = {"enable_gqa": True} if h != kv_h else {}
|
||||
|
||||
if self.differential:
|
||||
q, q_diff = q.unbind(dim=1)
|
||||
k, k_diff = k.unbind(dim=1)
|
||||
out = optimized_attention(q, k, v, h, skip_reshape=True, low_precision_attention=False, transformer_options=transformer_options)
|
||||
out_diff = optimized_attention(q_diff, k_diff, v, h, skip_reshape=True, low_precision_attention=False, transformer_options=transformer_options)
|
||||
out = optimized_attention(q, k, v, h, skip_reshape=True, low_precision_attention=False, transformer_options=transformer_options, **gqa_kwargs)
|
||||
out_diff = optimized_attention(q_diff, k_diff, v, h, skip_reshape=True, low_precision_attention=False, transformer_options=transformer_options, **gqa_kwargs)
|
||||
out = out - out_diff
|
||||
else:
|
||||
out = optimized_attention(q, k, v, h, skip_reshape=True, low_precision_attention=False, transformer_options=transformer_options)
|
||||
out = optimized_attention(q, k, v, h, skip_reshape=True, low_precision_attention=False, transformer_options=transformer_options, **gqa_kwargs)
|
||||
|
||||
out = self.to_out(out)
|
||||
|
||||
|
||||
@ -74,11 +74,8 @@ class BooguDoubleStreamProcessor(nn.Module):
|
||||
key = key.transpose(1, 2)
|
||||
value = value.transpose(1, 2)
|
||||
|
||||
if attn.kv_heads < attn.heads:
|
||||
key = key.repeat_interleave(attn.heads // attn.kv_heads, dim=1)
|
||||
value = value.repeat_interleave(attn.heads // attn.kv_heads, dim=1)
|
||||
|
||||
hidden_states = optimized_attention_masked(query, key, value, attn.heads, attention_mask, skip_reshape=True, transformer_options=transformer_options)
|
||||
gqa_kwargs = {"enable_gqa": True} if attn.kv_heads < attn.heads else {}
|
||||
hidden_states = optimized_attention_masked(query, key, value, attn.heads, attention_mask, skip_reshape=True, transformer_options=transformer_options, **gqa_kwargs)
|
||||
|
||||
# Split back to instruction/image, apply per-stream output projections, recombine.
|
||||
instruct_hidden_states = self.instruct_out(hidden_states[:, :L_instruct])
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
import math
|
||||
import sys
|
||||
import inspect
|
||||
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
@ -14,16 +15,16 @@ from .sub_quadratic_attention import efficient_dot_product_attention
|
||||
|
||||
from comfy import model_management
|
||||
|
||||
TORCH_HAS_GQA = model_management.torch_version_numeric >= (2, 5)
|
||||
|
||||
if model_management.xformers_enabled():
|
||||
import xformers
|
||||
import xformers.ops
|
||||
|
||||
SAGE_ATTENTION_IS_AVAILABLE = False
|
||||
SAGE_ATTENTION_SUPPORTS_MASK = False
|
||||
try:
|
||||
from sageattention import sageattn
|
||||
SAGE_ATTENTION_IS_AVAILABLE = True
|
||||
SAGE_ATTENTION_SUPPORTS_MASK = "attn_mask" in inspect.signature(sageattn).parameters
|
||||
except ImportError as e:
|
||||
if model_management.sage_attention_enabled():
|
||||
if e.name == "sageattention":
|
||||
@ -89,6 +90,44 @@ def default(val, d):
|
||||
return val
|
||||
return d
|
||||
|
||||
def _gqa_repeat_factor(query_heads, key_heads, value_heads):
|
||||
if key_heads != value_heads:
|
||||
raise ValueError(f"Key/value head count mismatch for GQA: {key_heads} != {value_heads}")
|
||||
if query_heads == key_heads:
|
||||
return 1
|
||||
if query_heads % key_heads != 0:
|
||||
raise ValueError(f"Query heads must be divisible by key/value heads for GQA: {query_heads} vs {key_heads}")
|
||||
return query_heads // key_heads
|
||||
|
||||
def _repeat_kv_for_gqa(k, v, query_heads, head_dim):
|
||||
n_rep = _gqa_repeat_factor(query_heads, k.shape[head_dim], v.shape[head_dim])
|
||||
if n_rep > 1:
|
||||
k = k.repeat_interleave(n_rep, dim=head_dim)
|
||||
v = v.repeat_interleave(n_rep, dim=head_dim)
|
||||
return k, v
|
||||
|
||||
def _heads_from_dim(tensor, dim_head, name):
|
||||
inner_dim = tensor.shape[-1]
|
||||
if inner_dim % dim_head != 0:
|
||||
raise ValueError(f"{name} inner dimension {inner_dim} is not divisible by head dimension {dim_head}")
|
||||
return inner_dim // dim_head
|
||||
|
||||
def _reshape_qkv_to_heads(q, k, v, b, heads, dim_head, enable_gqa=False, expand_kv=True):
|
||||
q = q.unsqueeze(3).reshape(b, -1, heads, dim_head)
|
||||
if enable_gqa:
|
||||
key_heads = _heads_from_dim(k, dim_head, "Key")
|
||||
value_heads = _heads_from_dim(v, dim_head, "Value")
|
||||
else:
|
||||
key_heads = heads
|
||||
value_heads = heads
|
||||
k = k.unsqueeze(3).reshape(b, -1, key_heads, dim_head)
|
||||
v = v.unsqueeze(3).reshape(b, -1, value_heads, dim_head)
|
||||
if enable_gqa:
|
||||
_gqa_repeat_factor(heads, key_heads, value_heads)
|
||||
if expand_kv:
|
||||
k, v = _repeat_kv_for_gqa(k, v, heads, -2)
|
||||
return q, k, v
|
||||
|
||||
|
||||
# feedforward
|
||||
class GEGLU(nn.Module):
|
||||
@ -152,28 +191,19 @@ def attention_basic(q, k, v, heads, mask=None, attn_precision=None, skip_reshape
|
||||
b, _, dim_head = q.shape
|
||||
dim_head //= heads
|
||||
|
||||
if kwargs.get("enable_gqa", False) and q.shape[-3] != k.shape[-3]:
|
||||
n_rep = q.shape[-3] // k.shape[-3]
|
||||
k = k.repeat_interleave(n_rep, dim=-3)
|
||||
v = v.repeat_interleave(n_rep, dim=-3)
|
||||
|
||||
scale = kwargs.get("scale", dim_head ** -0.5)
|
||||
|
||||
h = heads
|
||||
if skip_reshape:
|
||||
q, k, v = map(
|
||||
if kwargs.get("enable_gqa", False):
|
||||
k, v = _repeat_kv_for_gqa(k, v, q.shape[-3], -3)
|
||||
q, k, v = map(
|
||||
lambda t: t.reshape(b * heads, -1, dim_head),
|
||||
(q, k, v),
|
||||
)
|
||||
else:
|
||||
q, k, v = map(
|
||||
lambda t: t.unsqueeze(3)
|
||||
.reshape(b, -1, heads, dim_head)
|
||||
.permute(0, 2, 1, 3)
|
||||
.reshape(b * heads, -1, dim_head)
|
||||
.contiguous(),
|
||||
(q, k, v),
|
||||
)
|
||||
q, k, v = _reshape_qkv_to_heads(q, k, v, b, heads, dim_head, kwargs.get("enable_gqa", False))
|
||||
q, k, v = map(lambda t: t.permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head).contiguous(), (q, k, v))
|
||||
|
||||
# force cast to fp32 to avoid overflowing
|
||||
if attn_precision == torch.float32:
|
||||
@ -231,13 +261,16 @@ def attention_sub_quad(query, key, value, heads, mask=None, attn_precision=None,
|
||||
query = query * (kwargs["scale"] * dim_head ** 0.5)
|
||||
|
||||
if skip_reshape:
|
||||
if kwargs.get("enable_gqa", False):
|
||||
key, value = _repeat_kv_for_gqa(key, value, query.shape[-3], -3)
|
||||
query = query.reshape(b * heads, -1, dim_head)
|
||||
value = value.reshape(b * heads, -1, dim_head)
|
||||
key = key.reshape(b * heads, -1, dim_head).movedim(1, 2)
|
||||
else:
|
||||
query = query.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
|
||||
value = value.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
|
||||
key = key.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 3, 1).reshape(b * heads, dim_head, -1)
|
||||
query, key, value = _reshape_qkv_to_heads(query, key, value, b, heads, dim_head, kwargs.get("enable_gqa", False))
|
||||
query = query.permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
|
||||
value = value.permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
|
||||
key = key.permute(0, 2, 3, 1).reshape(b * heads, dim_head, -1)
|
||||
|
||||
|
||||
dtype = query.dtype
|
||||
@ -304,19 +337,15 @@ def attention_split(q, k, v, heads, mask=None, attn_precision=None, skip_reshape
|
||||
scale = kwargs.get("scale", dim_head ** -0.5)
|
||||
|
||||
if skip_reshape:
|
||||
q, k, v = map(
|
||||
if kwargs.get("enable_gqa", False):
|
||||
k, v = _repeat_kv_for_gqa(k, v, q.shape[-3], -3)
|
||||
q, k, v = map(
|
||||
lambda t: t.reshape(b * heads, -1, dim_head),
|
||||
(q, k, v),
|
||||
)
|
||||
else:
|
||||
q, k, v = map(
|
||||
lambda t: t.unsqueeze(3)
|
||||
.reshape(b, -1, heads, dim_head)
|
||||
.permute(0, 2, 1, 3)
|
||||
.reshape(b * heads, -1, dim_head)
|
||||
.contiguous(),
|
||||
(q, k, v),
|
||||
)
|
||||
q, k, v = _reshape_qkv_to_heads(q, k, v, b, heads, dim_head, kwargs.get("enable_gqa", False))
|
||||
q, k, v = map(lambda t: t.permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head).contiguous(), (q, k, v))
|
||||
|
||||
r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
|
||||
|
||||
@ -438,7 +467,7 @@ def attention_xformers(q, k, v, heads, mask=None, attn_precision=None, skip_resh
|
||||
disabled_xformers = True
|
||||
|
||||
if disabled_xformers:
|
||||
return attention_pytorch(q, k, v, heads, mask, skip_reshape=skip_reshape, **kwargs)
|
||||
return attention_pytorch(q, k, v, heads, mask, skip_reshape=skip_reshape, skip_output_reshape=skip_output_reshape, **kwargs)
|
||||
|
||||
if skip_reshape:
|
||||
# b h k d -> b k h d
|
||||
@ -446,13 +475,12 @@ def attention_xformers(q, k, v, heads, mask=None, attn_precision=None, skip_resh
|
||||
lambda t: t.permute(0, 2, 1, 3),
|
||||
(q, k, v),
|
||||
)
|
||||
if kwargs.get("enable_gqa", False):
|
||||
k, v = _repeat_kv_for_gqa(k, v, q.shape[-2], -2)
|
||||
# actually do the reshaping
|
||||
else:
|
||||
dim_head //= heads
|
||||
q, k, v = map(
|
||||
lambda t: t.reshape(b, -1, heads, dim_head),
|
||||
(q, k, v),
|
||||
)
|
||||
q, k, v = _reshape_qkv_to_heads(q, k, v, b, heads, dim_head, kwargs.get("enable_gqa", False))
|
||||
|
||||
if mask is not None:
|
||||
# add a singleton batch dimension
|
||||
@ -474,7 +502,7 @@ def attention_xformers(q, k, v, heads, mask=None, attn_precision=None, skip_resh
|
||||
mask = mask_out[..., :mask.shape[-1]]
|
||||
mask = mask.expand(b, heads, -1, -1)
|
||||
|
||||
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=mask)
|
||||
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=mask, scale=kwargs.get("scale", None))
|
||||
|
||||
if skip_output_reshape:
|
||||
out = out.permute(0, 2, 1, 3)
|
||||
@ -498,10 +526,8 @@ def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, skip_resha
|
||||
else:
|
||||
b, _, dim_head = q.shape
|
||||
dim_head //= heads
|
||||
q, k, v = map(
|
||||
lambda t: t.view(b, -1, heads, dim_head).transpose(1, 2),
|
||||
(q, k, v),
|
||||
)
|
||||
q, k, v = _reshape_qkv_to_heads(q, k, v, b, heads, dim_head, kwargs.get("enable_gqa", False), expand_kv=False)
|
||||
q, k, v = map(lambda t: t.transpose(1, 2), (q, k, v))
|
||||
|
||||
if mask is not None:
|
||||
# add a batch dimension if there isn't already one
|
||||
@ -511,9 +537,7 @@ def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, skip_resha
|
||||
if mask.ndim == 3:
|
||||
mask = mask.unsqueeze(1)
|
||||
|
||||
# Pass through extra SDPA kwargs (scale, enable_gqa) if provided
|
||||
# enable_gqa requires PyTorch 2.5+; older versions use manual KV expansion above
|
||||
sdpa_keys = ("scale", "enable_gqa") if TORCH_HAS_GQA else ("scale",)
|
||||
sdpa_keys = ("scale", "enable_gqa")
|
||||
sdpa_extra = {k: v for k, v in kwargs.items() if k in sdpa_keys}
|
||||
|
||||
if SDP_BATCH_LIMIT >= b:
|
||||
@ -541,20 +565,19 @@ def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, skip_resha
|
||||
|
||||
@wrap_attn
|
||||
def attention_sage(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False, skip_output_reshape=False, **kwargs):
|
||||
if kwargs.get("low_precision_attention", True) is False:
|
||||
if kwargs.get("low_precision_attention", True) is False or (mask is not None and not SAGE_ATTENTION_SUPPORTS_MASK):
|
||||
return attention_pytorch(q, k, v, heads, mask=mask, skip_reshape=skip_reshape, skip_output_reshape=skip_output_reshape, **kwargs)
|
||||
|
||||
exception_fallback = False
|
||||
if skip_reshape:
|
||||
b, _, _, dim_head = q.shape
|
||||
tensor_layout = "HND"
|
||||
if kwargs.get("enable_gqa", False):
|
||||
k, v = _repeat_kv_for_gqa(k, v, q.shape[-3], -3)
|
||||
else:
|
||||
b, _, dim_head = q.shape
|
||||
dim_head //= heads
|
||||
q, k, v = map(
|
||||
lambda t: t.view(b, -1, heads, dim_head),
|
||||
(q, k, v),
|
||||
)
|
||||
q, k, v = _reshape_qkv_to_heads(q, k, v, b, heads, dim_head, kwargs.get("enable_gqa", False))
|
||||
tensor_layout = "NHD"
|
||||
|
||||
if mask is not None:
|
||||
@ -565,8 +588,12 @@ def attention_sage(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=
|
||||
if mask.ndim == 3:
|
||||
mask = mask.unsqueeze(1)
|
||||
|
||||
sage_kwargs = {"is_causal": False, "tensor_layout": tensor_layout, "sm_scale": kwargs.get("scale", None), "smooth_k": False}
|
||||
if mask is not None:
|
||||
sage_kwargs["attn_mask"] = mask
|
||||
|
||||
try:
|
||||
out = sageattn(q, k, v, attn_mask=mask, is_causal=False, tensor_layout=tensor_layout)
|
||||
out = sageattn(q, k, v, **sage_kwargs)
|
||||
except Exception as e:
|
||||
logging.error("Error running sage attention: {}, using pytorch attention instead.".format(e))
|
||||
exception_fallback = True
|
||||
@ -616,7 +643,6 @@ def attention3_sage(q, k, v, heads, mask=None, attn_precision=None, skip_reshape
|
||||
skip_output_reshape=skip_output_reshape,
|
||||
**kwargs
|
||||
)
|
||||
q_s, k_s, v_s = q, k, v
|
||||
N = q.shape[2]
|
||||
dim_head = D
|
||||
else:
|
||||
@ -642,11 +668,15 @@ def attention3_sage(q, k, v, heads, mask=None, attn_precision=None, skip_reshape
|
||||
**kwargs
|
||||
)
|
||||
|
||||
if not skip_reshape:
|
||||
q_s, k_s, v_s = map(
|
||||
lambda t: t.view(B, -1, heads, dim_head).permute(0, 2, 1, 3).contiguous(),
|
||||
(q, k, v),
|
||||
)
|
||||
if skip_reshape:
|
||||
q_s = q
|
||||
if kwargs.get("enable_gqa", False):
|
||||
k_s, v_s = _repeat_kv_for_gqa(k, v, H, -3)
|
||||
else:
|
||||
k_s, v_s = k, v
|
||||
else:
|
||||
q_s, k_s, v_s = _reshape_qkv_to_heads(q, k, v, B, heads, dim_head, kwargs.get("enable_gqa", False))
|
||||
q_s, k_s, v_s = map(lambda t: t.permute(0, 2, 1, 3).contiguous(), (q_s, k_s, v_s))
|
||||
B, H, L, D = q_s.shape
|
||||
|
||||
try:
|
||||
@ -662,7 +692,7 @@ def attention3_sage(q, k, v, heads, mask=None, attn_precision=None, skip_reshape
|
||||
q, k, v, heads,
|
||||
mask=mask,
|
||||
attn_precision=attn_precision,
|
||||
skip_reshape=False,
|
||||
skip_reshape=skip_reshape,
|
||||
skip_output_reshape=skip_output_reshape,
|
||||
**kwargs
|
||||
)
|
||||
@ -681,19 +711,20 @@ def attention3_sage(q, k, v, heads, mask=None, attn_precision=None, skip_reshape
|
||||
try:
|
||||
@torch.library.custom_op("flash_attention::flash_attn", mutates_args=())
|
||||
def flash_attn_wrapper(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor,
|
||||
dropout_p: float = 0.0, causal: bool = False) -> torch.Tensor:
|
||||
return flash_attn_func(q, k, v, dropout_p=dropout_p, causal=causal)
|
||||
dropout_p: float = 0.0, causal: bool = False, softmax_scale: float = -1.0) -> torch.Tensor:
|
||||
softmax_scale_arg = None if softmax_scale == -1.0 else softmax_scale
|
||||
return flash_attn_func(q, k, v, dropout_p=dropout_p, causal=causal, softmax_scale=softmax_scale_arg)
|
||||
|
||||
|
||||
@flash_attn_wrapper.register_fake
|
||||
def flash_attn_fake(q, k, v, dropout_p=0.0, causal=False):
|
||||
def flash_attn_fake(q, k, v, dropout_p=0.0, causal=False, softmax_scale=-1.0):
|
||||
# Output shape is the same as q
|
||||
return q.new_empty(q.shape)
|
||||
except AttributeError as error:
|
||||
FLASH_ATTN_ERROR = error
|
||||
|
||||
def flash_attn_wrapper(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor,
|
||||
dropout_p: float = 0.0, causal: bool = False) -> torch.Tensor:
|
||||
dropout_p: float = 0.0, causal: bool = False, softmax_scale: float = -1.0) -> torch.Tensor:
|
||||
assert False, f"Could not define flash_attn_wrapper: {FLASH_ATTN_ERROR}"
|
||||
|
||||
@wrap_attn
|
||||
@ -703,10 +734,8 @@ def attention_flash(q, k, v, heads, mask=None, attn_precision=None, skip_reshape
|
||||
else:
|
||||
b, _, dim_head = q.shape
|
||||
dim_head //= heads
|
||||
q, k, v = map(
|
||||
lambda t: t.view(b, -1, heads, dim_head).transpose(1, 2),
|
||||
(q, k, v),
|
||||
)
|
||||
q, k, v = _reshape_qkv_to_heads(q, k, v, b, heads, dim_head, kwargs.get("enable_gqa", False), expand_kv=False)
|
||||
q, k, v = map(lambda t: t.transpose(1, 2), (q, k, v))
|
||||
|
||||
if mask is not None:
|
||||
# add a batch dimension if there isn't already one
|
||||
@ -725,10 +754,16 @@ def attention_flash(q, k, v, heads, mask=None, attn_precision=None, skip_reshape
|
||||
v.transpose(1, 2),
|
||||
dropout_p=0.0,
|
||||
causal=False,
|
||||
softmax_scale=kwargs.get("scale", -1.0),
|
||||
).transpose(1, 2)
|
||||
except Exception as e:
|
||||
logging.warning(f"Flash Attention failed, using default SDPA: {e}")
|
||||
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
|
||||
sdpa_extra = {}
|
||||
if kwargs.get("enable_gqa", False):
|
||||
sdpa_extra["enable_gqa"] = True
|
||||
if "scale" in kwargs:
|
||||
sdpa_extra["scale"] = kwargs["scale"]
|
||||
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False, **sdpa_extra)
|
||||
if not skip_output_reshape:
|
||||
out = (
|
||||
out.transpose(1, 2).reshape(b, -1, heads * dim_head)
|
||||
@ -1209,5 +1244,3 @@ class SpatialVideoTransformer(SpatialTransformer):
|
||||
x = self.proj_out(x)
|
||||
out = x + x_in
|
||||
return out
|
||||
|
||||
|
||||
|
||||
@ -141,11 +141,8 @@ class Attention(nn.Module):
|
||||
key = key.transpose(1, 2)
|
||||
value = value.transpose(1, 2)
|
||||
|
||||
if self.kv_heads < self.heads:
|
||||
key = key.repeat_interleave(self.heads // self.kv_heads, dim=1)
|
||||
value = value.repeat_interleave(self.heads // self.kv_heads, dim=1)
|
||||
|
||||
hidden_states = optimized_attention_masked(query, key, value, self.heads, attention_mask, skip_reshape=True, transformer_options=transformer_options)
|
||||
gqa_kwargs = {"enable_gqa": True} if self.kv_heads < self.heads else {}
|
||||
hidden_states = optimized_attention_masked(query, key, value, self.heads, attention_mask, skip_reshape=True, transformer_options=transformer_options, **gqa_kwargs)
|
||||
hidden_states = self.to_out[0](hidden_states)
|
||||
return hidden_states
|
||||
|
||||
|
||||
@ -174,6 +174,8 @@ def cast_modules_with_vbar(comfy_modules, dtype, device, bias_dtype, non_blockin
|
||||
elif xfer_dest2 is not None:
|
||||
xfer_source.prepare(xfer_dest2, stream, copy=True, commit=False)
|
||||
return
|
||||
else:
|
||||
return
|
||||
comfy.model_management.cast_to_gathered(xfer_source, xfer_dest, non_blocking=non_blocking, stream=stream, r2=xfer_dest2)
|
||||
|
||||
def handle_pin(m, pin, source, dest, subset="weights", size=None):
|
||||
|
||||
@ -468,6 +468,9 @@ class CLIP:
|
||||
def decode(self, token_ids, skip_special_tokens=True):
|
||||
return self.tokenizer.decode(token_ids, skip_special_tokens=skip_special_tokens)
|
||||
|
||||
def is_dynamic(self):
|
||||
return self.patcher.is_dynamic()
|
||||
|
||||
class VAE:
|
||||
def __init__(self, sd=None, device=None, config=None, dtype=None, metadata=None):
|
||||
if 'decoder.up_blocks.0.resnets.0.norm1.weight' in sd.keys(): #diffusers format
|
||||
@ -1251,6 +1254,8 @@ class VAE:
|
||||
except:
|
||||
return None
|
||||
|
||||
def is_dynamic(self):
|
||||
return self.patcher.is_dynamic()
|
||||
|
||||
class StyleModel:
|
||||
def __init__(self, model, device="cpu"):
|
||||
|
||||
@ -12,7 +12,7 @@ import torch.nn.functional as F
|
||||
|
||||
import comfy.ops
|
||||
from comfy import sd1_clip
|
||||
from comfy.ldm.modules.attention import TORCH_HAS_GQA, optimized_attention_for_device
|
||||
from comfy.ldm.modules.attention import optimized_attention_for_device
|
||||
from comfy.text_encoders.llama import RMSNorm, apply_rope
|
||||
|
||||
|
||||
@ -110,10 +110,6 @@ def _attention_with_sinks(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, sin
|
||||
putting the sink logit in the mask at that column.
|
||||
"""
|
||||
|
||||
if num_kv_groups > 1 and not TORCH_HAS_GQA:
|
||||
k = k.repeat_interleave(num_kv_groups, dim=1)
|
||||
v = v.repeat_interleave(num_kv_groups, dim=1)
|
||||
|
||||
B, _, S_q, D = q.shape
|
||||
H_kv = k.shape[1]
|
||||
S_kv = k.shape[-2]
|
||||
|
||||
@ -550,10 +550,8 @@ class Attention(nn.Module):
|
||||
xv = xv[:, :, -sliding_window:]
|
||||
attention_mask = attention_mask[..., -sliding_window:] if attention_mask is not None else None
|
||||
|
||||
xk = xk.repeat_interleave(self.num_heads // self.num_kv_heads, dim=1)
|
||||
xv = xv.repeat_interleave(self.num_heads // self.num_kv_heads, dim=1)
|
||||
|
||||
output = optimized_attention(xq, xk, xv, self.num_heads, mask=attention_mask, skip_reshape=True)
|
||||
gqa_kwargs = {"enable_gqa": True} if self.num_heads != self.num_kv_heads else {}
|
||||
output = optimized_attention(xq, xk, xv, self.num_heads, mask=attention_mask, skip_reshape=True, **gqa_kwargs)
|
||||
return self.o_proj(output), present_key_value
|
||||
|
||||
class MLP(nn.Module):
|
||||
|
||||
@ -366,12 +366,8 @@ class GatedAttention(nn.Module):
|
||||
xv = torch.cat((past_value[:, :, :index], xv), dim=2)
|
||||
present_key_value = (xk, xv, index + num_tokens)
|
||||
|
||||
# Expand KV heads for GQA
|
||||
if self.num_heads != self.num_kv_heads:
|
||||
xk = xk.repeat_interleave(self.num_heads // self.num_kv_heads, dim=1)
|
||||
xv = xv.repeat_interleave(self.num_heads // self.num_kv_heads, dim=1)
|
||||
|
||||
output = optimized_attention(xq, xk, xv, self.num_heads, mask=attention_mask, skip_reshape=True)
|
||||
gqa_kwargs = {"enable_gqa": True} if self.num_heads != self.num_kv_heads else {}
|
||||
output = optimized_attention(xq, xk, xv, self.num_heads, mask=attention_mask, skip_reshape=True, **gqa_kwargs)
|
||||
output = output * gate.sigmoid()
|
||||
|
||||
return self.o_proj(output), present_key_value
|
||||
|
||||
@ -281,11 +281,18 @@ class VideoFromFile(VideoInput):
|
||||
video_done = False
|
||||
audio_done = True
|
||||
|
||||
if len(container.streams.audio):
|
||||
audio_stream = container.streams.audio[-1]
|
||||
# Use the last decodable audio stream. Streams FFmpeg has no decoder for have no codec context,
|
||||
# and decoding their packets crashes the process. (e.g. APAC spatial-audio track in iPhone)
|
||||
audio_stream = next(
|
||||
(s for s in reversed(container.streams.audio) if s.codec_context is not None),
|
||||
None,
|
||||
)
|
||||
if audio_stream is not None:
|
||||
streams += [audio_stream]
|
||||
resampler = av.audio.resampler.AudioResampler(format='fltp')
|
||||
audio_done = False
|
||||
elif len(container.streams.audio):
|
||||
logging.warning("No decodable audio stream found in video; ignoring audio.")
|
||||
|
||||
for packet in container.demux(*streams):
|
||||
if video_done and audio_done:
|
||||
@ -457,10 +464,13 @@ class VideoFromFile(VideoInput):
|
||||
else:
|
||||
output_container.metadata[key] = json.dumps(value)
|
||||
|
||||
# Add streams to the new container
|
||||
# Add streams to the new container. Streams with no codec context cannot be used as an output template.
|
||||
stream_map = {}
|
||||
for stream in streams:
|
||||
if isinstance(stream, (av.VideoStream, av.AudioStream, SubtitleStream)):
|
||||
if stream.codec_context is None:
|
||||
logging.warning("Skipping %s stream %d with unsupported codec", stream.type, stream.index)
|
||||
continue
|
||||
out_stream = output_container.add_stream_from_template(template=stream, opaque=True)
|
||||
stream_map[stream] = out_stream
|
||||
|
||||
|
||||
@ -158,7 +158,14 @@ async def upload_video_to_comfyapi(
|
||||
|
||||
# Convert VideoInput to BytesIO using specified container/codec
|
||||
video_bytes_io = BytesIO()
|
||||
video.save_to(video_bytes_io, format=container, codec=codec)
|
||||
try:
|
||||
video.save_to(video_bytes_io, format=container, codec=codec)
|
||||
except Exception as e:
|
||||
raise ValueError(
|
||||
f"Could not convert the input video to {container.value.upper()} for upload; "
|
||||
f"the file may be corrupted or use an unsupported codec. "
|
||||
f"Try re-exporting it as MP4 (H.264). Original error: {e}"
|
||||
) from e
|
||||
video_bytes_io.seek(0)
|
||||
|
||||
return await upload_file_to_comfyapi(cls, video_bytes_io, filename, upload_mime_type, wait_label)
|
||||
|
||||
@ -503,6 +503,21 @@ RAM_CACHE_DEFAULT_RAM_USAGE = 0.05
|
||||
|
||||
RAM_CACHE_OLD_WORKFLOW_OOM_MULTIPLIER = 1.3
|
||||
|
||||
|
||||
def all_outputs_dynamic(outputs):
|
||||
if outputs is None:
|
||||
return False
|
||||
|
||||
for output in outputs:
|
||||
if isinstance(output, (list, tuple)):
|
||||
if not all_outputs_dynamic(output):
|
||||
return False
|
||||
elif not hasattr(output, "is_dynamic") or not output.is_dynamic():
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
|
||||
class RAMPressureCache(LRUCache):
|
||||
|
||||
def __init__(self, key_class, enable_providers=False):
|
||||
@ -533,7 +548,11 @@ class RAMPressureCache(LRUCache):
|
||||
for key, cache_entry in self.cache.items():
|
||||
if not free_active and self.used_generation[key] == self.generation:
|
||||
continue
|
||||
oom_score = RAM_CACHE_OLD_WORKFLOW_OOM_MULTIPLIER ** (self.generation - self.used_generation[key])
|
||||
|
||||
if all_outputs_dynamic(cache_entry.outputs) and self.used_generation[key] == self.generation:
|
||||
continue
|
||||
|
||||
oom_score = RAM_CACHE_OLD_WORKFLOW_OOM_MULTIPLIER ** (self.generation - self.used_generation[key])
|
||||
|
||||
ram_usage = RAM_CACHE_DEFAULT_RAM_USAGE
|
||||
def scan_list_for_ram_usage(outputs):
|
||||
|
||||
150
comfy_extras/nodes_text_overlay.py
Normal file
150
comfy_extras/nodes_text_overlay.py
Normal file
@ -0,0 +1,150 @@
|
||||
import numpy as np
|
||||
import torch
|
||||
from PIL import Image as PILImage, ImageColor, ImageDraw, ImageFont
|
||||
from typing_extensions import override
|
||||
|
||||
from comfy_api.latest import ComfyExtension, IO
|
||||
|
||||
|
||||
class TextOverlay(IO.ComfyNode):
|
||||
@classmethod
|
||||
def define_schema(cls):
|
||||
return IO.Schema(
|
||||
node_id="TextOverlay",
|
||||
display_name="Draw Text Overlay",
|
||||
category="text",
|
||||
description="Draw text overlay on an image or batch of images.",
|
||||
search_aliases=["text", "label", "caption", "subtitle", "watermark", "title", "addlabel", "overlay"],
|
||||
inputs=[
|
||||
IO.Image.Input("images"),
|
||||
IO.String.Input("text", multiline=True, default=""),
|
||||
IO.Float.Input("font_size", default=5.0, min=0.5, max=50.0, step=0.5, tooltip="Font size as a percentage of the image height."),
|
||||
IO.Color.Input("color", default="#ffffff", tooltip="Color of the text."),
|
||||
IO.Combo.Input("position", options=["top", "bottom"], default="top"),
|
||||
IO.Combo.Input("align", options=["left", "center", "right"], default="left"),
|
||||
IO.Boolean.Input("outline", default=True, tooltip="Draw a black outline around the text."),
|
||||
],
|
||||
outputs=[IO.Image.Output(display_name="images")],
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def execute(cls, images, text, font_size, color, position, align, outline) -> IO.NodeOutput:
|
||||
if text.strip() == "":
|
||||
return IO.NodeOutput(images)
|
||||
|
||||
text = text.replace("\\n", "\n").replace("\\t", "\t")
|
||||
|
||||
text_rgba = cls.parse_color_to_rgba(color)
|
||||
outline_rgba = (0, 0, 0, 255) if outline else (0, 0, 0, 0)
|
||||
|
||||
# Render the overlay once and composite it across all frames in the batch
|
||||
height = images.shape[1]
|
||||
width = images.shape[2]
|
||||
overlay_rgb, overlay_alpha = cls.render_overlay_text(width, height, text, position, align, font_size, text_rgba, outline_rgba)
|
||||
overlay_rgb = overlay_rgb.to(device=images.device, dtype=images.dtype)
|
||||
overlay_alpha = overlay_alpha.to(device=images.device, dtype=images.dtype)
|
||||
|
||||
result = images * (1.0 - overlay_alpha) + overlay_rgb * overlay_alpha
|
||||
return IO.NodeOutput(result)
|
||||
|
||||
@staticmethod
|
||||
def parse_color_to_rgba(color_string):
|
||||
parsed = ImageColor.getrgb(color_string)
|
||||
|
||||
if len(parsed) == 3:
|
||||
return (*parsed, 255)
|
||||
|
||||
return parsed
|
||||
|
||||
@classmethod
|
||||
def render_overlay_text(cls, width, height, text, position, align, font_size, text_rgba, outline_rgba):
|
||||
line_spacing = 1.2
|
||||
margin_percent = 1.0
|
||||
min_font_percent = 2.0
|
||||
min_font_pixels = 10
|
||||
outline_thickness_factor = 0.04
|
||||
|
||||
# Draw onto a transparent layer so the result can be alpha-composited over any frame.
|
||||
layer = PILImage.new("RGBA", (width, height), (0, 0, 0, 0))
|
||||
draw = ImageDraw.Draw(layer)
|
||||
|
||||
margin = int(round(margin_percent / 100.0 * min(width, height)))
|
||||
max_width = max(1, width - 2 * margin)
|
||||
max_height = max(1, height - 2 * margin)
|
||||
|
||||
# Font scales with resolution, then shrinks to fit the height.
|
||||
size = max(1, int(round(font_size / 100.0 * height)))
|
||||
floor = min(size, max(min_font_pixels, int(round(min_font_percent / 100.0 * height))))
|
||||
|
||||
while True:
|
||||
font = ImageFont.load_default(size=size)
|
||||
stroke = max(1, int(round(size * outline_thickness_factor))) if outline_rgba[3] > 0 else 0
|
||||
block = "\n".join(cls.wrap_text(text, font, max_width))
|
||||
# convert line spacing to pixel spacing
|
||||
single = draw.textbbox((0, 0), "Ay", font=font, stroke_width=stroke)
|
||||
double = draw.multiline_textbbox((0, 0), "Ay\nAy", font=font, spacing=0, stroke_width=stroke)
|
||||
natural_advance = (double[3] - double[1]) - (single[3] - single[1])
|
||||
pixel_spacing = int(round(size * line_spacing - natural_advance))
|
||||
box = draw.multiline_textbbox((0, 0), block, font=font, spacing=pixel_spacing, stroke_width=stroke)
|
||||
block_height = box[3] - box[1]
|
||||
|
||||
if block_height <= max_height or size <= floor:
|
||||
break
|
||||
|
||||
size = max(floor, int(size * 0.9))
|
||||
|
||||
anchor_h, x = {"left": ("l", margin), "center": ("m", width / 2), "right": ("r", width - margin)}[align]
|
||||
|
||||
# Offset y so the rendered text sits flush against the margin
|
||||
if position == "bottom":
|
||||
y = height - margin - box[3]
|
||||
else:
|
||||
y = margin - box[1]
|
||||
|
||||
draw.multiline_text((x, y), block, font=font, fill=text_rgba, anchor=anchor_h + "a",
|
||||
align=align, spacing=pixel_spacing, stroke_width=stroke, stroke_fill=outline_rgba)
|
||||
|
||||
overlay = np.array(layer).astype(np.float32) / 255.0
|
||||
overlay_rgb = torch.from_numpy(overlay[:, :, :3])
|
||||
overlay_alpha = torch.from_numpy(overlay[:, :, 3:4])
|
||||
return overlay_rgb, overlay_alpha
|
||||
|
||||
@staticmethod
|
||||
def wrap_text(text, font, max_width):
|
||||
lines = []
|
||||
for raw_line in text.split("\n"):
|
||||
words = raw_line.split()
|
||||
if not words:
|
||||
lines.append("")
|
||||
continue
|
||||
current = ""
|
||||
# Break the line into words and split words that are too long
|
||||
for word in words:
|
||||
while font.getlength(word) > max_width and len(word) > 1:
|
||||
cut = 1
|
||||
while cut < len(word) and font.getlength(word[:cut + 1]) <= max_width:
|
||||
cut += 1
|
||||
if current:
|
||||
lines.append(current)
|
||||
current = ""
|
||||
lines.append(word[:cut])
|
||||
word = word[cut:]
|
||||
candidate = word if not current else current + " " + word
|
||||
if not current or font.getlength(candidate) <= max_width:
|
||||
current = candidate
|
||||
else:
|
||||
lines.append(current)
|
||||
current = word
|
||||
if current:
|
||||
lines.append(current)
|
||||
return lines
|
||||
|
||||
|
||||
class TextOverlayExtension(ComfyExtension):
|
||||
@override
|
||||
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
|
||||
return [TextOverlay]
|
||||
|
||||
|
||||
async def comfy_entrypoint() -> TextOverlayExtension:
|
||||
return TextOverlayExtension()
|
||||
@ -17,7 +17,11 @@ if args.base_directory:
|
||||
else:
|
||||
base_path = os.path.dirname(os.path.realpath(__file__))
|
||||
|
||||
models_dir = os.path.join(base_path, "models")
|
||||
if args.models_directory:
|
||||
models_dir = os.path.abspath(args.models_directory)
|
||||
else:
|
||||
models_dir = os.path.join(base_path, "models")
|
||||
|
||||
folder_names_and_paths["checkpoints"] = ([os.path.join(models_dir, "checkpoints")], supported_pt_extensions)
|
||||
folder_names_and_paths["configs"] = ([os.path.join(models_dir, "configs")], [".yaml"])
|
||||
|
||||
|
||||
4
main.py
4
main.py
@ -131,6 +131,10 @@ def apply_custom_paths():
|
||||
if args.base_directory:
|
||||
logging.info(f"Setting base directory to: {folder_paths.base_path}")
|
||||
|
||||
# --models-directory
|
||||
if args.models_directory:
|
||||
logging.info(f"Setting models directory to: {folder_paths.models_dir}")
|
||||
|
||||
# --output-directory, --input-directory, --user-directory
|
||||
if args.output_directory:
|
||||
output_dir = os.path.abspath(args.output_directory)
|
||||
|
||||
1
nodes.py
1
nodes.py
@ -2478,6 +2478,7 @@ async def init_builtin_extra_nodes():
|
||||
"nodes_glsl.py",
|
||||
"nodes_lora_debug.py",
|
||||
"nodes_textgen.py",
|
||||
"nodes_text_overlay.py",
|
||||
"nodes_color.py",
|
||||
"nodes_toolkit.py",
|
||||
"nodes_replacements.py",
|
||||
|
||||
@ -163,3 +163,20 @@ def test_base_path_change_clears_old(set_base_dir):
|
||||
|
||||
for name in ["controlnet", "diffusion_models", "text_encoders"]:
|
||||
assert len(folder_paths.get_folder_paths(name)) == 2
|
||||
|
||||
|
||||
def test_models_directory_cli_and_getters(temp_dir):
|
||||
try:
|
||||
with patch.object(sys, 'argv', ["main.py", "--models-directory", temp_dir]):
|
||||
reload(comfy.cli_args)
|
||||
reload(folder_paths)
|
||||
|
||||
assert folder_paths.models_dir == os.path.abspath(temp_dir)
|
||||
|
||||
with pytest.raises(Exception):
|
||||
comfy.cli_args.is_valid_directory(os.path.join(temp_dir, "non_existent_folder_path"))
|
||||
finally:
|
||||
with patch.object(sys, 'argv', ["main.py"]):
|
||||
reload(comfy.cli_args)
|
||||
reload(folder_paths)
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user