Theodore
Theodore
@neiltian-tencent hi, I have used onediff to accelerate Moore-AnimateAnyone demo: /MooreAnimateAnyone/scripts/pose2vid.py  and it doesn't seem to have any problem  could you tell me exactlly how do you use...
> convert failed: Transform failed of : 'function' object has no attribute '' @wangerlie I compile denoising_unet by oneflow_compile. compile_pipe has no acceleration effect, although the above error is not...
> @wangerlie AnimateAnyone pipeline has two unets(denoising_unet and reference_unet). compile_pipe may filter the two unets, this is the onediff filter _PARTS info. _PARTS = [ "text_encoder", "text_encoder_2", "image_encoder", "unet", "controlnet",...
the two components 'denoising_unet' and 'reference_unet' can be compiled after add the following code in compile: ```python def compile_pipe( pipe, *, backend="oneflow", options=None, ignores=(), fuse_qkv_projections=False, ): if fuse_qkv_projections: pipe =...
@LuckyIvan ## 环境对齐 本地复现环境： ComfyUI_IPAdapter_Plus:  ComfyUI:  ## 问题复现 ### 准备工作 1. 首先验证OneDiff Node能在ComfyUI中正常使用：  2. 下载相应的safetensors文件 https://hf-mirror.com/h94/IP-Adapter/resolve/main/models/image_encoder/model.safetensors https://hf-mirror.com/h94/IP-Adapter-FaceID/resolve/main/ip-adapter-faceid_sd15_lora.safetensors https://hf-mirror.com/creatorbest/myposes/resolve/main/OpenPoseXL2.safetensors https://hf-mirror.com/h94/IP-Adapter-FaceID/resolve/main/ip-adapter-faceid-plusv2_sdxl_lora.safetensors https://hf-mirror.com/h94/IP-Adapter/resolve/main/sdxl_models/ip-adapter-plus-face_sdxl_vit-h.safetensors https://hf-mirror.com/stabilityai/sdxl-vae/resolve/main/sdxl_vae.safetensors 3. 用户没有提供POSE2的图片，所以在本流程中使用随便选取了一张图片做为POSE2 ### 本地运行复现 本地流程截图 ...
更新环境后完成问题复现 ``` oneflow 0.9.1.dev20240411+cu121 onediff 0.13.0.dev1 ``` 完成问题复现   删除sd15的lora后能够正常运行   尝试将下面lora换为sdxl与基底模型对齐   更换为上述两种模型后都会报错  **在`IPAdapter`和`KSampler`中添加`LoraLoaderModelOnly`时都会出现相同错误** ``` Failed to update obj_entity in place. Exception: Not support with...
@LuckyIvan 问题已解决，请您更新至最新版本ComfyUI，onediff请使用[该分支](https://github.com/siliconflow/onediff/tree/dev_ipa%2Bisntantid)。 在本地验证结果如下：LoraLoaderModelOnly节点能够正常使用  
> Hello, > > I tried the same config with the repo and got the same good performance with the paper. However, when I tried the env halfcheetah and the...
I am also wondering do you have the same warning as following, I think it's not reasonable, there may have some problem within the normalization code? 