DiffSynth-Studio

DiffSynth-Studio copied to clipboard

有加入z-image模型的计划吗 可以说一说估计的时间吗

sugelamyd123

H100 GPU - FP8 inference acceleration

1

Thanks for the great work ! I followed the Qwen-Image inference example in below link (recommended for faster inference) for comparing FP8 vs bfloat16: [./accelerate/Qwen-Image-FP8.py](https://github.com/modelscope/DiffSynth-Studio/blob/833ba1e1fa5d36826d5b21d6628baa17ac1e6f4d/examples/qwen_image/accelerate/Qwen-Image-FP8.py) But for FP8 (torch.float8_e4m3fn), the...

anandharaju

[feature request] add pre-calculating latent / text encoder outputs

2

precalculating the text encoder embeddings can improve vram usage by only loading the text encoders when the dataset needs to be preprocessed, this also can apply to the vae, so...

yoinked-h

Wan2.2 T2V 14B， 训练vae 部分，cache_x 和 x 维度不匹配

4

maidang-zc

在使用qwen-image -edit 进行lora微调的时候，csv 和json有区别么？还是都能使用，只要image,prompt,edit_image能对上就可以

stillbetter

When will Flux2 training be supported?

5

gxd1994

qwen-image-edit lora训练 是否有显存优化手段

4

使用单机8卡49GA6000，按照repo中的lora去训练，已经启动了 --use_gradient_checkpointing --use_gradient_checkpointing_offload --enable_fp8_training，降低了lora_rank，zero_stage2/3都试过，全都在**accelerator.prepare步骤爆显存** 求各位指导： 1. 是否是deepspeed配置没起作用？配置方式见下图（--config_file） 2. 是否有其他方法能够优化显存？

pljj315

Can the training of Z-Image-Turbo be included?

1

Can the training of Z-Image-Turbo be included?

JiahongWu1995

按照Wan2.1的推理手册运行出现问题

1

按照手册指导的通过运行以下代码可以快速加载 [Wan-AI/Wan2.1-T2V-1.3B](https://www.modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B) 模型并进行推理 import torch from diffsynth import save_video from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig pipe = WanVideoPipeline.from_pretrained( torch_dtype=torch.bfloat16, device="cuda", model_configs=[ ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"), ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"), ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"), ],...

sugelamyd123

Facing issue while running Wan14B on Mutli GPU

2

Hi Team, Thanks for your work but I am not able to run the 14B model using the step given. I have 8 gpu with 24GB ram. Cmd used: `torchrun...

Akshaysharma29