shileims
shileims
Running "pip install sptag", the following error: Could not find a version that satisfies the requirement sptag (from versions: ) No matching distribution found for sptag. Any solution is appreciated,...
## Summary import oneflow as torch "RuntimeError: This package is a placeholder. Please install oneflow following the instructions" ## Code to reproduce bug import oneflow as torch ## System Information...
Hi @thedarkzeno and @patil-suraj Thanks for your excellent work on dream booth inpainting. My question is that how to perform fp16 dreambooth inpainting fine-tuning?
### 🐛 Describe the bug Hi colossalai, I am trying to use colossalai to fine-tune stable diffusion. In the code, optimizer is defined as GeminiAdamOptimizer. I used the following code...
Hi, Thanks for your really great work. I am trying to finetune the model and use the same mask generation strategy on the places dataset. But I found the intermediate-generation...
Hi Author, Thanks for your great work! I want to ask what parameters I need to change for training 512x512 input image? Thanks
### 🐛 Describe the bug The error happens in booster.backward(loss, optimizer), I used GeminiPlugin ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -6) local_rank: 0 (pid: 2044) of binary: /opt/conda/envs/pytorch/bin/python ### Environment linux, cuda11.7 torch1.13.1
Hi Author, Thanks for your great work. I would like to know How to perform inference without inputting prompt? Thanks
Hi author, Thanks for this excellent work. I would like to ask any plan for supporting SDXL-1.0? It will be very useful. Thanks
Hi Author, I found that if I used teddy.ckpt and herburn.ckpt to get multiconcept results. The image results don't include any teddy. 