modelscope / modelscope/DiffSynth-Studio
qwen-image-edit-2511部署推理和lora微调
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
qwen-image-edit-2511部署在服务器上推理。任务大概是给视频生成个性化封面，上游已经通过视频理解模型从视频中抽出了三张高相关视频帧作为参考图，以及输出了视频内容文本分析和三张参考图文本分析，再加上一些固定的生图尺寸、内容、质量要求等。送入到qwen-image-edit-2511进行推理，当前部署到本地的模型和demo以及线上产品的效果差距也太大了........后期打算用banana产一批好图进行微调，不知道能不能改善一下呢
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files, tests, or entry points are named. Start by reviewing the qwen-image-edit-2511 local deployment and demo, then compare their inference inputs and outputs with the online product using the stated video frames, analyses, and generation requirements. Done would require a reproducible server inference setup and evidence that LoRA fine-tuning improves the personalized cover results.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100