[bug]: Z-Image, Qwen-Image and Anima LoRA converters ignore `.alpha` and drop DoRA magnitudes on lora_A/lora_B layers
![[bug]: Z-Image, Qwen-Image and Anima LoRA converters ignore `.alpha` and drop DoRA magnitudes on lora_A/lora_B layers](https://www.chat-gpts.plus/wp-content/uploads/2026/11/10019-f156d1bf-768x403.jpg)
该问题出现在使用 InvokeAI 加载 Z-Image、Qwen-Image 或 Anima 的 LoRA 转换器(A/B 键 LoRA,即 lora_A/lora_B 键)时:如果 LoRA 文件把 .alpha 放在 lora_A / lora_B 键上,或文件包含 DoRA 幅度( .dor



![[CI Failure]: V1 KV Connectors Shard 2/4 - test_lmcache_connector.py::test_engine_shutdown_stops_lmcache_threads](https://www.chat-gpts.plus/wp-content/uploads/2026/11/67121-fa96c4dc-768x403.jpg)
![[RFC]: FlashInfer NVFP4 KV serving on pre-SM100 GPUs](https://www.chat-gpts.plus/wp-content/uploads/2026/11/47684-bfcf3e55-768x403.jpg)
![issue: [regression] [dev] an automation deleted from the list stays open in its own tab](https://www.chat-gpts.plus/wp-content/uploads/2026/11/34324-33492280-768x403.jpg)
![[Bug]: resume_from_checkpoint silently skips the root-level (trained) adapter when the checkpoint contains adapter subdirectories — DPO loss](https://www.chat-gpts.plus/wp-content/uploads/2026/11/50204-623d1300-768x403.jpg)

