PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.
PythonApache-2.0
Pinned issues
Issues
- 25
PaddleMIX 快乐开源活动 (2024 Q4)
#787 opened by luyao-cv - 2
使用文本生成音频时遇到TypeError: set_default_dtype only supports [float16, float32, float64, bfloat16] , but received paddle.float32
#708 opened by lyyilin - 1
项目有讨论群吗,想加入
#818 opened by hujianming8163 - 4
请问是否支持arm架构的昇腾910b
#798 opened by feria-tu - 4
自制数据训练clip模型报错
#804 opened by ericosmic - 4
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name'
#811 opened by ZhijunLStudio - 2
PaddleMIX单机单卡训练stable diffusion无法读取环境变量
#809 opened by fxy1699 - 1
- 4
【PaddleMIX 热身打卡】跑通 Stable-Diffusion 训练报错
#806 opened by fxy1699 - 1
【Hackathon 7th】Fundable project 4. 前沿扩散模型飞桨复现
#793 opened by yangguohao - 5
# PaddleMIX 快乐开源活动 (2024 Q3)
#644 opened by LokeZhou - 0
- 0
《飞桨PaddleMIX开发大赛等你来战!》
#732 opened by lyuwenyu - 0
ppdiffusersv0.29.0-release
#761 opened by westfish - 3
PaddleMIX训练stable_diffusion出错
#710 opened by zty-king - 0
SFT Qwen-VL 使用给的示例模板和命令行报错
#717 opened by overloadedHenry - 6
PPDiffusers 0.24.1 Open-Sora 生成视频结果乱码 绿屏问题
#707 opened by whisky-12 - 1
啥时候把cogvideox模型加入进去
#701 opened by lrjxgl - 1
关于ppdiffusers 是否支持 FLUX.1的类型模型的咨询和建议
#697 opened by whisky-12 - 6
PaddleMIX 2.0版本发布,欢迎开发者使用反馈
#645 opened by jerrywgz - 2
关于ppdiffusers是否支持LayerDiffuse 去除背景组件的支持提问
#679 opened by whisky-12 - 6
微调模型之后出现乱码
#634 opened by yimuu - 0
PaddleMIX 开发者任务RFC模板
#688 opened by lyuwenyu - 2
DataCoplit
#652 opened by paulpaul91 - 1
CUDNN_STATUS_NOT_INITIALIZED 错误
#678 opened by flymorn - 2
- 2
_dygraph_tracer()._has_grad is False, inplace multiply_grad is not yet supported.
#662 opened by imheng - 4
无法安装paddlenlp2.7.2
#673 opened by masaladi - 7
llava的静态图推理V100和A100。
#661 opened by wojiaoshihua - 1
LlaVA预训练模型没找到
#665 opened by scutfrank - 0
推理性能提升建议
#666 opened by wojiaoshihua - 2
在NPU上进行LLaVA1.6微调训练时遇到问题
#659 opened by yimuu - 2
sft训练,设定10epoch,但是一个epoch后就自动停止了,没有设置max_steps
#578 opened by zouhan6806504 - 1
sft全量微调多卡报错
#577 opened by fangfangssj - 4
- 1
llava微调数据集的格式
#610 opened by yimuu - 2
- 2
A import error and how i solve this problem?
#590 opened by ChYHENG123 - 1
Not implemented function in paddle.audio.functional
#603 opened by ChocoWu - 1
PaddleMix 怎么更改 多模态模型的Vision encoder呢?
#583 opened by ApolloRay - 1
sft训练需要合并权重吗?
#585 opened by 258863 - 1
请问有支持 internvl 2B 4B 之类模型推理的计划吗,谢谢
#575 opened by sanbuphy - 0
与PaddleNLP2.8在V100上的兼容性
#607 opened by wojiaoshihua - 1
ImportError
#580 opened by 1196228233 - 0
【Feature】Add ComfyUI support
#588 opened by CrazyBoyM - 0
How to train VLLM model in int8 format ?
#582 opened by ApolloRay - 0
Lora训练时遇到的问题
#555 opened by 1196228233 - 0
AssertionError: <None> should be a PretrainedModel class, but <<class 'NoneType'>>
#571 opened by dddlli - 1
【NVIDIA】当--use_ema True时,DiT单卡训练失败
#563 opened by yumin066 - 2
有哪些diffusion模型支持推理加速?
#556 opened by Worromots