diffsynth-pr
Skill13k starsChanged 6 days agoApache-2.0View on GitHub
Generate a PR description markdown file for a completed model integration in DiffSynth-Studio. Use this skill after all testing is done and the user has confirmed the results, or whenever the user wants to generate a PR description for review. This skill only outputs a markdown file — it does NOT create branches, commit code, or push to remote. SCOPE: Only for integrating a new model or a new model feature into DiffSynth-Studio. Do NOT invoke for PRs from any other development — bug fixes, refactoring, performance tuning, or general code changes.
- Commits and pushes
Trending
More talk lately.about the whole repository
Who's talking about modelscope/DiffSynth-Studio
- kijai/ComfyUI-HunyuanVideoWrapper“VRAM Management”GitHub · Dec 23, 2024 · 6 reactions
- ostris/ai-toolkit“Qwen-Image-2512 support”GitHub · Dec 31, 2025 · 2 reactions
- tdrussell/diffusion-pipe“Wan2.1 LoRA Support”GitHub · Feb 25, 2025 · 2 reactions
- NVIDIA-NeMo/labs-molt“Are community contributions welcome?”GitHub · Jul 30, 2026 · 1 reactions
- NUS-HPC-AI-Lab/Enhance-A-Video“Can you make a pull request to DiffSynth-Studio as well if possible?”GitHub · Mar 8, 2025 · 1 reactions
The biggest 5 of 52 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 52
Talked about on GitHub and Bluesky (52 times).
On GitHub · 50
- Dec 23, 2024VRAM Management — kijai/ComfyUI-HunyuanVideoWrapper6 reactions · 6 comments
- Dec 31, 2025Qwen-Image-2512 support — ostris/ai-toolkit2 reactions · 1 comment
- Feb 25, 2025Wan2.1 LoRA Support — tdrussell/diffusion-pipe2 reactions · 1 comment
- Jul 30, 2026Are community contributions welcome? — NVIDIA-NeMo/labs-molt1 reaction · 3 comments
- Mar 8, 2025Can you make a pull request to DiffSynth-Studio as well if possible? — NUS-HPC-AI-Lab/Enhance-A-Video1 reaction · 1 comment
45 more on GitHub
- Nov 15, 2026chore(deps): bump the minor-and-patch group with 17 updates — shivashar7668-netizen/Removixx0 reactions · 1 comment
- Nov 12, 2026chore(deps): bump DiffSynth-Studio from `dcb6d0b` to `fdad57b` — modelscope/DiffSynth-WebUI0 reactions · 1 comment
- Nov 5, 2026chore(deps): bump DiffSynth-Studio from `dcb6d0b` to `e435f12` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Nov 5, 2026Bump the minor-and-patch group across 1 directory with 5 updates — wiltodelta/remove-ai-watermarks0 reactions
- Nov 3, 2026Bump the minor-and-patch group across 1 directory with 14 updates — lawanyatalodhikar-boop/AI-water-mark-remover0 reactions · 1 comment
- Nov 3, 2026Bump the minor-and-patch group across 1 directory with 14 updates — jsfan3/remove-ai-watermarks-low-vram0 reactions · 1 comment
- Nov 1, 2026Bump the minor-and-patch group across 1 directory with 10 updates — wiltodelta/remove-ai-watermarks0 reactions · 1 comment
- Oct 30, 2026Bump the minor-and-patch group across 1 directory with 7 updates — wiltodelta/remove-ai-watermarks0 reactions · 2 comments
- Oct 29, 2026chore(deps): bump DiffSynth-Studio from `dcb6d0b` to `d55ff19` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Oct 28, 2026Bump the minor-and-patch group across 1 directory with 6 updates — wiltodelta/remove-ai-watermarks0 reactions · 2 comments
- Oct 19, 2026chore(deps): bump DiffSynth-Studio from `7f65ecc` to `2d2d243` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Oct 16, 2026chore(deps): bump DiffSynth-Studio from `7f65ecc` to `cf6d843` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Oct 14, 2026Bump the minor-and-patch group with 6 updates — wiltodelta/remove-ai-watermarks0 reactions · 1 comment
- Oct 13, 2026chore(deps): bump DiffSynth-Studio from `7f65ecc` to `acf2ad2` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Oct 6, 2026Bump the minor-and-patch group across 1 directory with 12 updates — jsfan3/remove-ai-watermarks-low-vram0 reactions · 2 comments
- Oct 5, 2026chore(deps): bump DiffSynth-Studio from `7f65ecc` to `974cfa3` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Oct 2, 2026chore(deps): bump DiffSynth-Studio from `7f65ecc` to `d393669` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Oct 2, 2026Bump the minor-and-patch group across 1 directory with 15 updates — linxiaohuo123/remove-ai-watermarks0 reactions · 2 comments
- Oct 1, 2026chore(deps): bump DiffSynth-Studio from `7f65ecc` to `7539a33` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 30, 2026Refresh needs review: wan-dancer-14b-disk-offload-pytorch-single — CarstVaartjes/vonk-forge-recipes0 reactions · 1 comment
- Sep 29, 2026Bump the minor-and-patch group across 1 directory with 11 updates — jsfan3/remove-ai-watermarks-low-vram0 reactions · 2 comments
- Sep 24, 2026chore(deps): bump DiffSynth-Studio from `7f65ecc` to `7686e54` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 23, 2026chore(deps): bump DiffSynth-Studio from `7f65ecc` to `d2d684a` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 18, 2026chore(deps): bump DiffSynth-Studio from `84f93fc` to `c458cb4` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 18, 2026Bump the minor-and-patch group across 1 directory with 16 updates — linxiaohuo123/remove-ai-watermarks0 reactions · 2 comments
- Sep 17, 2026chore(deps): bump DiffSynth-Studio from `84f93fc` to `cc36552` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 16, 2026Spike: controllable music generation with audio-conditioned KV-cache adapters — DanMarshall909/dandrum0 reactions
- Sep 15, 2026Bump the minor-and-patch group across 1 directory with 12 updates — jsfan3/remove-ai-watermarks-low-vram0 reactions · 2 comments
- Sep 14, 2026chore(deps): bump DiffSynth-Studio from `84f93fc` to `32ef37e` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 11, 2026[BUG] Memory leak in loss backward when enabled torch activation checkpoint & zero3 & single-model-multi-branch network — deepspeedai/DeepSpeed0 reactions · 1 comment
- Sep 11, 2026chore(deps): bump DiffSynth-Studio from `84f93fc` to `7822d17` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 11, 2026Bump the minor-and-patch group across 1 directory with 13 updates — linxiaohuo123/remove-ai-watermarks0 reactions · 2 comments
- Sep 10, 2026chore(deps): bump DiffSynth-Studio from `84f93fc` to `183007e` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 8, 2026Add: custom nodes of DiffSynth-Studio — Comfy-Org/ComfyUI-Manager0 reactions · 1 comment
- Sep 8, 2026Bump the minor-and-patch group across 1 directory with 10 updates — jsfan3/remove-ai-watermarks-low-vram0 reactions · 2 comments
- Sep 7, 2026chore(deps): bump DiffSynth-Studio from `84f93fc` to `4dbf980` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 4, 2026chore(deps): bump DiffSynth-Studio from `84f93fc` to `1c7782a` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Sep 3, 2026chore(deps): bump DiffSynth-Studio from `3f3df52` to `84f93fc` — modelscope/DiffSynth-WebUI0 reactions · 1 comment
- Sep 2, 2026Bump the minor-and-patch group across 1 directory with 3 updates — wiltodelta/remove-ai-watermarks0 reactions · 1 comment
- Sep 1, 2026Bump the minor-and-patch group across 1 directory with 7 updates — jsfan3/remove-ai-watermarks-low-vram0 reactions · 2 comments
- Aug 31, 2026chore(deps): bump DiffSynth-Studio from `3f3df52` to `102fe99` — modelscope/DiffSynth-WebUI0 reactions · 2 comments
- Aug 25, 2026chore(deps): bump DiffSynth-Studio from `fed7b18` to `3f3df52` — modelscope/DiffSynth-WebUI0 reactions · 1 comment
- Jul 22, 2026Vibe Research: Actions Become Video Masks: Robots May Learn by Editing the Future — aven-pantom/aven-research-lab0 reactions
- Feb 13, 2026fix: convert boundary_ratio from timestep space to index space — OpenMOSS/MOVA0 reactions · 3 comments
- Sep 25, 2025Not able to repomix this repo, what is wrong here? — yamadashy/repomix0 reactions · 3 comments
On Bluesky · 2
- Jun 28, 2024🎉 Celebrating! 🎉 (500+ new stars) 📦 modelscope / DiffSynth-Studio ⭐ 4,818 (+988) 🗒 Python Enjoy the magic of Diffusion models! — @github-trending.bsky.social0 likes and reposts · 1 reply
- Jun 24, 2024🚀 Skyrocketing! 🚀 (200+ new stars) 📦 modelscope / DiffSynth-Studio ⭐ 1,295 (+362) 🗒 Python Enjoy the magic of Diffusion models! — @github-trending.bsky.social0 likes and reposts · 1 reply
In this repository17 other files it gives its agents.
- diffsynth-analyze-targetSkill
- diffsynth-docsSkill
- diffsynth-environmentSkill
- diffsynth-integratorSkill
- diffsynth-model-codeSkill
- diffsynth-pipeline-lowvramSkill
- diffsynth-pipelineSkill
- diffsynth-pipeline-trainingSkill
- diffsynth-pr-reviewSkill
- diffsynth-styleSkill
- diffsynth-testingSkill
- diffsynth-user-datasetSkill
- diffsynth-user-evaluationSkill
- diffsynth-user-inferenceSkill
- diffsynth-user-researchSkill
- diffsynth-user-setupSkill
- diffsynth-user-trainingSkill
The file
Files
DiffSynth-Studio: PR 描述生成
读取接入信息,生成 PR 描述 Markdown 文件。
配置
从 diffsynth-integrator/config.yaml 读取配置。
路径确定:
- 所有路径基于
packages/{model-name}/结构 diffsynth_root:packages/{model-name}/DiffSynth-Studio/.sisyphus目录:packages/{model-name}/.sisyphus/
工作流程
0. 读取蓝图信息
📖 开始前:重读本步骤描述,确认流程与报告路径
每个 skill 执行的第一步,强制要求。 从蓝图报告中读取 Python 运行环境信息和本 skill 必要的信息。
# 从 CLAUDE.md 或 config.yaml 获取模型名称
MODEL_NAME="{model-name}"
BLUEPRINT_PATH="packages/${MODEL_NAME}/.sisyphus/integration-blueprints/${MODEL_NAME}-blueprint.md"本 skill 必须从蓝图报告中读取的信息:
| 蓝图信息 | 用途 |
基本信息表中的 Conda 环境名称 | PR 信息 |
| 接入类型 | PR 描述中的集成类型说明 |
| Pipeline 功能规划表 | 接入的功能列表 |
如果蓝图报告不存在,向用户说明原因并中止。
📝 完成后:更新渐进式报告 →
skill_work_report/pr-report.md
1. 初始化执行日志目录
📖 开始前:重读本步骤描述,确认流程与报告路径
读取蓝图信息后, 创建执行日志目录结构:
EXEC_LOG_DIR="packages/{model-name}/.sisyphus/execution-logs/$(date +%Y%m%d_%H%M%S)_pr"
mkdir -p ${EXEC_LOG_DIR}/{outputs,scripts,checkpoints}📝 完成后:更新渐进式报告 →
skill_work_report/pr-report.md
2. 以实际代码为准,校验蓝图信息
📖 开始前:重读本步骤描述,确认流程与报告路径
蓝图是接入前的计划文档,实际代码在开发过程中可能已经变化。生成 PR 描述时必须以磁盘上的实际代码为准。
校验流程:
- Pipeline 文件:扫描
{diffsynth_root}/diffsynth/pipelines/下与本次模型相关的文件,逐行读取__call__签名和 Pipeline 类名,不要依赖蓝图中的功能规划表 - 模型组件:扫描
{diffsynth_root}/diffsynth/models/下与本次模型相关的文件,不要依赖蓝图中的组件清单 - State dict converter:扫描
{diffsynth_root}/diffsynth/utils/state_dict_converters/下与本次模型相关的文件 - 推理脚本:扫描
{diffsynth_root}/examples/下与本次模型相关的脚本(含model_inference/、model_inference_low_vram/、model_training/),不要依赖蓝图中的推理规划 - model_configs.py:读取
{diffsynth_root}/diffsynth/configs/model_configs.py中新增的注册项 - 显存管理配置:读取
{diffsynth_root}/diffsynth/configs/vram_management_module_maps.py中新增的 module_map 条目 - 文档:读取
{diffsynth_root}/docs/zh/Model_Details/和docs/en/Model_Details/下本次新增或修改的文档,以及docs/{zh,en}/index.rst、docs/{zh,en}/README.md的改动 - 根 README:读取
{diffsynth_root}/README.md和README_zh.md的改动(更新历史、全局模型表、基础框架分类列表) - 依赖变更:读取
{diffsynth_root}/pyproject.toml的实际内容
用
git status/git diff --stat核对实际改动文件清单,避免漏项。
发现不一致时:蓝图中的功能名、组件名、Pipeline 类名等可能与实际代码不同,一律以实际代码为准,不修正代码去匹配蓝图。仅在报告中注明主要差异供用户参考。
📝 完成后:更新渐进式报告 →
skill_work_report/pr-report.md
3. 收集接入信息
📖 开始前:重读本步骤描述,确认流程与报告路径
以实际代码为准,收集生成 PR 描述所需的所有信息:
- 接入类型:从蓝图报告读取(new_series / version_upgrade)
- 功能列表:从实际 Pipeline 文件的类名和
__call__签名提取(见 Step 2 扫描结果) - 模型组件:从
{diffsynth_root}/diffsynth/models/下实际存在的文件提取 - Pipeline 文件:从
{diffsynth_root}/diffsynth/pipelines/下实际存在的文件提取 - State dict converter:从
{diffsynth_root}/diffsynth/utils/state_dict_converters/下实际存在的文件提取 - 推理与训练脚本:从
{diffsynth_root}/examples/下实际存在的脚本提取 - 显存管理配置:从
vram_management_module_maps.py实际新增的条目提取 - 文档改动:从
docs/{zh,en}/Model_Details/、index.rst、docs/{zh,en}/README.md的实际改动提取 - 根 README 改动:从
README.md/README_zh.md的实际改动提取 - 依赖变更:从
{diffsynth_root}/pyproject.toml实际内容中提取 - 模型信息:从
model_configs.py实际注册项中提取
不要直接复制蓝图中的功能列表或组件清单到 PR 描述中。蓝图是计划,代码是事实。
📝 完成后:更新渐进式报告 →
skill_work_report/pr-report.md
4. 生成 PR 描述
📖 开始前:重读本步骤描述,确认流程与报告路径
完整 PR 描述模板见 references/pr-template.md。
根据收集到的信息,填充 PR 描述模板,输出到:
packages/{model-name}/.sisyphus/pr/description.md语言要求:PR 描述必须全部使用英文。 包括标题、摘要、功能列表、组件说明、依赖列表、注意事项等所有内容。不要使用中文或其他非英文语言。DiffSynth-Studio 是面向全球开发者的开源项目,PR 描述使用英文才能让所有贡献者和使用者都能理解。
PR 描述应聚焦于新功能介绍,不包含接入过程的测试等细节:
- 接入的模型名称和功能列表(支持哪些 pipeline)
- 模型组件清单(组件名、文件名、参数量)
- 新增的依赖包
- 注意事项(硬件要求、已知限制等)
📝 完成后:更新渐进式报告 →
skill_work_report/pr-report.md
5. 最终验证
📖 开始前:重读本步骤描述,确认流程与报告路径
在 PR 描述生成完成后,执行最终验证:
# 检查三个报告文件是否存在
for f in \
"packages/{model-name}/.sisyphus/plans/pr-plan.md" \
"packages/{model-name}/.sisyphus/skill_work_report/pr-report.md" \
"packages/{model-name}/.sisyphus/user_report/pr-report.md"; do
if [ ! -f "$f" ]; then
echo "WARNING: 缺失报告文件: $f"
fi
done
# 检查 PR 描述文件是否存在
if [ ! -f "packages/{model-name}/.sisyphus/pr/description.md" ]; then
echo "WARNING: PR 描述文件缺失"
fi如有缺失,立即补充。
📝 完成后:更新渐进式报告 →
skill_work_report/pr-report.md
输出
执行日志
所有执行过程保存到:
- 执行日志目录:
packages/{model-name}/.sisyphus/execution-logs/latest/ - 脚本目录:
scripts/- 保存的验证脚本 - 输出目录:
outputs/- 命令执行日志 - PR 目录:
packages/{model-name}/.sisyphus/pr/- PR 描述文件
PR 描述
输出到 packages/{model-name}/.sisyphus/pr/description.md,用户可自行复制使用。
Plan
在制定执行计划步骤,将详细执行计划输出到 packages/{model-name}/.sisyphus/plans/pr-plan.md。Plan 文件采用统一的步骤章节格式,每个步骤包含「目标、执行内容、产出物、注意事项」。模板如下:
# PR 执行 Plan
## 基本信息
| 字段 | 值 |
|------|-----|
| 模型名称 | {model-name} |
| Skill | diffsynth-pr |
| 执行时间 | {timestamp} |
| 接入类型 | {new_series / version_upgrade} |
## 执行步骤规划
以下按顺序列出所有执行步骤。每个步骤包含:目标、具体执行内容、产出物、注意事项。
### Step 0: 读取蓝图信息
**目标**:从蓝图报告中获取 PR 描述生成所需的上下文信息。
**执行内容**:
- 读取 `packages/{model-name}/.sisyphus/integration-blueprints/{model-name}-blueprint.md`
- 提取:Conda 环境名称、接入类型、Pipeline 功能规划表
- 如果蓝图报告不存在,向用户说明原因并中止
**产出物**:确认蓝图信息可用
---
### Step 1: 初始化执行日志目录
**目标**:创建执行日志目录结构。
**执行内容**:
- 创建 `packages/{model-name}/.sisyphus/execution-logs/{timestamp}_pr/` 目录及子目录
**产出物**:执行日志目录
---
### Step 2: 以实际代码为准,校验蓝图信息
**目标**:对比蓝图计划与实际代码,确保 PR 描述基于最新代码状态。
**执行内容**:
- 扫描 `{diffsynth_root}/diffsynth/pipelines/` 下与本次模型相关的文件,逐行读取 `__call__` 签名和 Pipeline 类名
- 扫描 `{diffsynth_root}/diffsynth/models/` 下与本次模型相关的文件
- 扫描 `{diffsynth_root}/examples/` 下与本次模型相关的推理脚本
- 读取 `model_configs.py` 中新增的注册项
- 读取 `pyproject.toml` 的实际内容
- 发现蓝图与实际代码不一致时,以实际代码为准
**产出物**:代码状态确认清单,主要差异记录
**注意事项**:
- 蓝图是计划,代码是事实。不要修正代码去匹配蓝图
- 仅在报告中注明主要差异供用户参考
---
### Step 3: 收集接入信息
**目标**:收集生成 PR 描述所需的所有信息。
**执行内容**:
- 从蓝图报告提取接入类型
- 从实际 Pipeline 文件提取功能列表、类名、参数签名
- 从 `diffsynth/models/` 和 `diffsynth/pipelines/` 提取实际存在的文件
- 从 `examples/` 提取实际存在的推理脚本
- 从 `pyproject.toml` 提取依赖变更
- 从 `model_configs.py` 提取模型信息
**产出物**:信息收集清单
---
### Step 4: 生成 PR 描述
**目标**:根据收集到的信息生成完整的 PR 描述。
**执行内容**:
- 参考 `references/pr-template.md` 模板
- 填入模型名称、接入的功能列表、模型组件清单、新增依赖、注意事项
- 功能列表、组件清单等信息必须以实际代码为准,不要直接复制蓝图
- **PR 描述必须全部使用英文**,不要混入中文
- 输出到 `packages/{model-name}/.sisyphus/pr/description.md`
**产出物**:
- `packages/{model-name}/.sisyphus/pr/description.md`
---
### Step 5: 最终验证
**目标**:确认所有报告文件和输出文件完整性。
**执行内容**:
- 检查三个报告文件是否存在:Plan 文件、skill_work_report、user_report
- 检查 PR 描述文件是否存在
- 如有缺失,立即补充
**产出物**:验证通过确认
---
## PR 规划
### PR 描述要点
- **PR 描述必须全部使用英文**,包括所有标题、描述、注释
- 模型名称和接入的功能列表(支持哪些 pipeline)
- 模型组件清单(组件名、参数量)
- 新增依赖包
- 注意事项(硬件要求、已知限制等)
- 聚焦新功能介绍,不包含接入过程的测试、验证等细节渐进式步骤报告
每个步骤完成后立即追加记录。格式详见 step-report.md。
报告路径:packages/{model-name}/.sisyphus/skill_work_report/pr-report.md
步骤划分(与上方「工作流程」章节的 Step 0-5 一一对应):
| Step | 名称 | 对应 Workflow |
| 0 | 读取蓝图信息 | Step 0 |
| 1 | 初始化执行日志目录 | Step 1 |
| 2 | 以实际代码为准,校验蓝图信息 | Step 2 |
| 3 | 收集接入信息 | Step 3 |
| 4 | 生成 PR 描述 | Step 4 |
| 5 | 最终验证 | Step 5 |
每完成一个步骤,执行:
cat >> packages/{model-name}/.sisyphus/skill_work_report/pr-report.md << EOF
### Step {N}: {步骤名称}
- **状态**: ✅ 完成 / ❌ 失败
- **完成时间**: \$(date -Iseconds)
- **做了什么**: {简要描述}
- **关键结果**: {1-2 句话说明结果}
- **输出文件**: \`{文件路径}\`
EOF向用户报告
PR 描述生成完成后,向用户报告 必须写入文件:
cat > packages/{model-name}/.sisyphus/user_report/pr-report.md << 'OUTER_EOF'
## ✅ PR 描述生成完成
执行日志: `packages/{model-name}/.sisyphus/execution-logs/latest/`
### 📋 PR 描述
- 文件路径: `packages/{model-name}/.sisyphus/pr/description.md`
- 接入类型: {new_series / version_upgrade}
### ⚠️ 安全提醒
本 skill 仅生成 PR 描述 Markdown 文件,**不执行任何 git 操作**(不创建分支、不提交、不推送)。请用户自行处理代码版本管理并创建 PR,以确保安全。
请 Review PR 描述内容,确认无误后手动执行 git 操作。
### 📦 数据集上传提醒
PR 描述中使用的推理样例数据集(`data/diffsynth_example_dataset/{series}/{FeatureName}/`)**不会包含在代码 PR 中**,需要单独上传到 ModelScope 数据集仓库:
1. **确认数据集目录存在**:`data/diffsynth_example_dataset/{series}/{FeatureName}/`
2. **上传到 ModelScope**:`modelscope upload --dataset DiffSynth-Studio/diffsynth_example_dataset --local_dir ./data/diffsynth_example_dataset`
3. **确认推理脚本中的数据集路径**与实际上传路径一致
> 数据集是独立的,不随代码 PR 一起提交。忘记上传数据集会导致推理脚本无法正常获取样例数据。
### 📦 代码推送提醒
本 integration 生成的 DiffSynth-Studio 代码位于 `packages/{model-name}/DiffSynth-Studio/` 目录下,这些代码**不会自动包含在 PR 中**,需要你先推送到自己 fork 的 DiffSynth-Studio 仓库的对应模型分支:
cd packages/{model-name}/DiffSynth-Studio
# 1. 先将 origin 重定向到你自己的 fork(如果尚未配置)
git remote set-url origin https://github.com/{your-username}/DiffSynth-Studio.git
# 2. 将本地 main 分支推送到 fork 的模型分支(如 ernie-image)
git push origin main:{model-branch}
# 3. (可选)添加官方仓库为 upstream,方便后续同步
git remote add upstream https://github.com/modelscope/DiffSynth-Studio.git
> `{model-branch}` 是当前接好的模型分支名(如 `ernie-image`)。本地代码保持在 main 分支,push 时映射到远程的模型分支即可。模型代码和 Pipeline 文件的引用链接依赖于你的 fork 仓库中该分支上是否存在对应文件。
OUTER_EOFDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

