huggingface / huggingface/diffusers

InstructPix2Pix training script for SD3

未关闭
#9,101 22 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
stale
主要语言
Python
星标
34.5k
派生
7.3k
平均合并
3 天 3 小时
30 天内合并 PR
91

描述

**Is your feature request related to a problem? Please describe.**
It would be awesome to see a training script for InstructPix2Pix based on Stable Diffusion 3 such as [this](https://github.com/huggingface/diffusers/blob/main/examples/instruct_pix2pix/train_instruct_pix2pix_sdxl.py).

**Describe the solution you'd like.**
A training script for IP2P based on SD3.

**Describe alternatives you've considered.**
None

**Additional context.**
None

贡献指南

打开贡献指南

调研方向

Start by reading examples/instruct_pix2pix/train_instruct_pix2pix_sdxl.py, which is provided as the reference implementation. Determine how its InstructPix2Pix training flow should correspond to Stable Diffusion 3, then add the requested SD3-based training script and verify that it supports IP2P training.

由索引模型根据 Issue 内容生成。

评估

技术栈
python, pytorch
领域
ai, machine-learning
Issue 类型
功能
难度
5/5
预计耗时
一周以上
活跃度
停滞
描述清晰度
基本清楚
新手友好度
35/100

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。