Skip to content

Commit d986a8f

Browse files
Update changelog with comfyui v0.3.60 (#434)
* Add/update changelog/index.mdx * Add/update zh-CN/changelog/index.mdx * Update Changelog --------- Co-authored-by: ComfyUI Wiki <[email protected]>
1 parent e5b6227 commit d986a8f

File tree

2 files changed

+50
-2
lines changed

2 files changed

+50
-2
lines changed

changelog/index.mdx

Lines changed: 25 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,31 @@ description: "Track ComfyUI's latest features, improvements, and bug fixes"
44
icon: "clock-rotate-left"
55
---
66

7+
<Update label="v0.3.60" description="September 23, 2025">
8+
9+
**New Model Support**
10+
- **Wan2.2 Animate**: Support for Wan2.2 Animate video generation model with character replacement and motion transfer capabilities
11+
- **Qwen Image Edit 2509 Support**: Support for the updated Qwen Image Edit 2509 with multi-image editing, higher consistency, and native ControlNet support
12+
- **HuMo Models**: Added support for both 1.7B and 17B HuMo models that use audio to drive video generation while maintaining lip sync
13+
- **Chroma Radiance**: A model that performs image generation in pixel space, reducing losses during the image generation process
14+
- **Omnigen2 UMO LoRA**: Added support for Omnigen2 UMO LoRA models
15+
16+
**API Node Additions**
17+
- **Kling v2.1 Support**: Added kling-v2-1 model to KlingStartEndFrame node
18+
- **Seedream4 Fixes**: Fixed the flag that ignores errors on partial success, making workflows more robust
19+
20+
**Node Schema Migration (V3)**
21+
- **Core Node Updates**: Migrated multiple node categories to V3 schema including Minimax API, Cosmos, conditioning, CFG, and Canny nodes
22+
23+
**Performance & Technical Improvements**
24+
- **FP8 Operations**: Enabled FP8 operations by default on gfx1200 hardware for faster processing
25+
- **LoRA Trainer Fixes**: Resolved bugs with FP8 model compatibility in LoRA training workflows
26+
27+
**Frontend Updates**
28+
- **Frontend Version Update**: Updated to version 1.26.13
29+
30+
</Update>
31+
732
<Update label="v0.3.59" description="September 10, 2025">
833

934
**ByteDance Seedream 4.0 Integration**
@@ -41,7 +66,6 @@ icon: "clock-rotate-left"
4166
- **ByteDance Image Nodes**: Added support for ByteDance image generation services
4267
- **Ideogram Character Reference**: Ideogram v3 API now supports character reference
4368
</Update>
44-
4569
<Update label="v0.3.56" description="August 30, 2025">
4670

4771
**Performance Enhancement**

zh-CN/changelog/index.mdx

Lines changed: 25 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,33 @@
11
---
22
title: "更新日志"
3-
description: "追踪 ComfyUI 的最新功能、改进和错误修复"
3+
description: "跟踪ComfyUI的最新功能、改进和错误修复"
44
icon: "clock-rotate-left"
55
---
66

7+
<Update label="v0.3.60" description="2025年9月23日">
8+
9+
**新模型支持**
10+
- **Wan2.2 Animate**: 支持 Wan2.2 Animate 视频生成模型,支持视频角色替换及动作迁移
11+
- **Qwen Image Edit 2509支持**: 支持迭代后的Qwen Image Edit 2509,支持多图编辑、更高的一致性、原生ControlNet支持
12+
- **HuMo模型**: 添加了对1.7B和17B HuMo模型的支持,用音频来驱动视频生成,并保持口型一致
13+
- **Chroma Radiance**: 一个在像素空间进行图像生成的模型,可减少图像生成过程中的损失
14+
- **Omnigen2 UMO LoRA**: 添加了对Omnigen2 UMO LoRA模型的支持
15+
16+
**API节点新增**
17+
- **Kling v2.1支持**: 在KlingStartEndFrame节点中添加了kling-v2-1模型
18+
- **Seedream4修复**: 修复了在部分成功时忽略错误的标志,使工作流更加稳健
19+
20+
**节点架构迁移 (V3)**
21+
- **核心节点更新**: 将多个节点类别迁移到V3架构,包括Minimax API、Cosmos、条件、CFG和Canny节点
22+
23+
**性能和技术改进**
24+
- **FP8操作**: 在gfx1200硬件上默认启用FP8操作,实现更快的处理速度
25+
- **LoRA训练器修复**: 解决了LoRA训练工作流中FP8模型兼容性的错误
26+
27+
**前端更新**
28+
- **前端版本更新**: 更新到版本1.26.13
29+
30+
</Update>
731
<Update label="v0.3.59" description="2025年9月10日">
832

933
**字节跳动 Seedream 4.0 集成**

0 commit comments

Comments
 (0)