Comments (10)
ppdiffusers里attention.py里GEGLU模块缺少
def gelu(self, gate): if gate.device.type != "mps": return F.gelu(gate)
,但这并不在代码差异中,需要更改吗
from paddlemix.
似乎缺少models/attention.py的单测
from paddlemix.
ppdiffusers里attention.py里GEGLU模块缺少
def gelu(self, gate): if gate.device.type != "mps": return F.gelu(gate)
,但这并不在代码差异中,需要更改吗
不需要
from paddlemix.
似乎缺少models/attention.py的单测
如果torch 的diffusers里有这个单测则添加上去,如果没有就不需要添加
from paddlemix.
diffusers的attention_processor.py里存在的pytorch2.0版本的类需要在ppdiffusers里实现吗 像:
AttnAddedKVProcessor2_0,AttnProcessor2_0,LoRAAttnProcessor2_0
from paddlemix.
缺少2_0的类会导致新增的
ADDED_KV_ATTENTION_PROCESSORS = (
AttnAddedKVProcessor,
SlicedAttnAddedKVProcessor,
AttnAddedKVProcessor2_0,
XFormersAttnAddedKVProcessor,
LoRAAttnAddedKVProcessor,
)
CROSS_ATTENTION_PROCESSORS = (
AttnProcessor,
AttnProcessor2_0,
XFormersAttnProcessor,
SlicedAttnProcessor,
LoRAAttnProcessor,
LoRAAttnProcessor2_0,
LoRAXFormersAttnProcessor,
)
AttentionProcessor = Union[
AttnProcessor,
AttnProcessor2_0,
XFormersAttnProcessor,
SlicedAttnProcessor,
AttnAddedKVProcessor,
SlicedAttnAddedKVProcessor,
AttnAddedKVProcessor2_0,
XFormersAttnAddedKVProcessor,
CustomDiffusionAttnProcessor,
CustomDiffusionXFormersAttnProcessor,
# depraceted
LoRAAttnProcessor,
LoRAAttnProcessor2_0,
LoRAXFormersAttnProcessor,
LoRAAttnAddedKVProcessor,
]
部分出现类似于"AttnProcessor2_0" is not defined的warning
from paddlemix.
@LokeZhou 请问这个PR #322 是否很快就能合入。
from paddlemix.
ci通过后合入
from paddlemix.
diffusers的attention_processor.py里存在的pytorch2.0版本的类需要在ppdiffusers里实现吗 像: AttnAddedKVProcessor2_0,AttnProcessor2_0,LoRAAttnProcessor2_0
如果功能一致不需要;如果是因为2.0版本导致新增功能,则需要。
from paddlemix.
任务已完成 by @co63oc ,close issue。
from paddlemix.
Related Issues (20)
- GroundDino模型导出后,无法在C++上推理。 HOT 16
- GroundDino模型导出后,无法在C++上推理。 HOT 3
- 请问paddle的GroundDino模型和pytorch的GroundDino模型之间是做了某种转换吗? HOT 1
- 请问有ppdiffusers模型convert成hugginface diffusers可用的模型的代码吗?希望可以加上,让模型之间可以相互转化 HOT 1
- torchsde分解器在paddle中的替换函数
- thrust::system::system_error 问题 HOT 4
- 'Namespace' object has no attribute 'report_to' HOT 1
- train_lvdm_short.py测试运行错误 HOT 6
- 支持zero123XL吗? HOT 1
- clip微调时IN_1K_DIR数据哪里找? 这个和直接下载的还不一样,里面要templates.txt文件 HOT 1
- Do you have this dataset?
- StableDiffusion Pipeline 升级
- subtract不支持 int8类型 HOT 3
- NameError: name 'method' is not defined HOT 1
- SDXL-turbo训练 HOT 1
- 🎁PaddleMIX 快乐开源活动表单 HOT 11
- 新增模型Hotshot-XL HOT 11
- 新增模型VideoCrafter
- Stable Diffusion XL Long Weighted Prompt Pipeline
- 新增模型GPT-SoVITS HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from paddlemix.