Tencent/HunyuanDiT
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Jupyter NotebookNOASSERTION
Issues
- 0
- 0
Hunyuan-captioner报错
#210 opened by RENLINA123 - 0
图片生成是一张黑图,不论什么prompt生成的结果都是一张黑图
#209 opened by earnmonforfam - 2
请问支持图生图吗?
#192 opened by PromptExpert - 2
trt部署时,模型导出onnx失败
#184 opened by linuxmi - 1
这个有api接口文档吗
#208 opened by dhp666 - 0
RuntimeError: mat1 and mat2 must have the same dtype
#207 opened by jiang-gy - 0
是否有新的hunyuan要发布,flux.1很大也很强
#205 opened by JoshonSmith - 0
关于canny controlnet 训练问题
#204 opened by dkerjw1 - 0
Fine-tune on my own dataset
#203 opened by cuonghoang29 - 0
https://huggingface.co/spaces 的demo有错误
#202 opened by friendmine - 0
您好这个项目支持天数智芯的智铠,天垓系列GPU吗
#201 opened by AnnaYanami-8 - 4
[BUG]使用v1.2版本的权重和v1.2的distill权重进行推理生成的图片全黑
#160 opened by GenerallyCovetous - 0
- 1
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens:
#186 opened by liiux - 1
lora模型在哪里能下载?
#197 opened by Edward-keyes - 1
构建tensorrt engine报错
#159 opened by xinguo2 - 1
支持中文很好,有一点就是感觉封装太狠了,不就调个模型而已吗?
#196 opened by gg22mm - 0
- 0
the training details for hunyuan dit control net
#194 opened by icelighting - 0
xDiT supports parallel inference of HunyuanDiT
#191 opened by feifeibear - 0
图片生成质量请教
#190 opened by zhongmiyu99 - 1
请问controlnet微调之后的.pt文件怎么转换成.safetensors呢?我在转换过程中报错了
#161 opened by Whoo-jl - 1
About comfyui clone, and controlnet in comfy
#188 opened by YacratesWyh - 2
- 0
- 1
请问如何在GPU单卡28G上面跑起来?
#171 opened by LtFung - 0
ip adapter
#185 opened by JoshonSmith - 1
- 0
论文中的评测集有吗?
#183 opened by zhangyuxin0 - 0
- 0
what the infer mode is for?
#180 opened by lzran - 0
官方COMFYUI的CN节点和DIFFSUERS的PIP节点冲突怎么解决?
#179 opened by slash1224 - 0
TensorRT in comfyui?
#178 opened by nikolaiusa - 0
TRT模型分辨率16:9问题
#176 opened by rammiah - 0
如何在单节点多张GPU上进行微调训练?
#175 opened by skywalker-lt - 0
DiT-XL/2 参数启动失败
#174 opened by 15053285989 - 0
ComfyUI failing to load comfyui-hydit
#173 opened by a-l-e-x-d-s-9 - 0
caption_demo.py 支持并行打标
#172 opened by CanvaChen - 0
HunyuanCaptioner是在llava基础上微调过的吗?
#170 opened by CanvaChen - 1
DreamBoothSubset.__init__() missing 1 required positional argument: 'alpha_mask' error!!
#163 opened by ShoponSKP - 1
Tensor Size a (91) must match the size of tensor b (90) at non-singleton dimesion 3
#169 opened by vsatyamesc - 3
'tuple' object has no attribute 'pop'
#164 opened by benzhangdragonplus - 0
!!! Exception during processing!!!
#167 opened by SYBSYBFUFU00005 - 0
- 0
Error occurred when executing HYDiTTextEncoderLoader: PytorchStreamReader failed reading zip archive: failed finding central directory
#158 opened by liaceboy - 1
CLIP.encode_from_tokens() got an unexpected keyword argument 'return_dict'
#155 opened by mrducdat1993 - 0
- 2
- 0
HunyuanDiT Blocks个数是几个?28?40?
#153 opened by henbucuoshanghai