search

Stability-AI / stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models
MIT License
38.33k stars 4.95k forks source link

txt2img.py doesn't work. #337

Open Michi-123 opened 10 months ago

Michi-123 commented 10 months ago

I ran txt2img.py on Google Colab. !python scripts/txt2img.py --prompt "prompt" --ckpt /content/trinart2_step60000.ckpt --config configs/stable-diffusion/v2-inference-v.yaml But it stop in the middle of process with the '^C'. Why is that?

Global seed set to 42 Loading model from /content/trinart2_step60000.ckpt Global Step: 60000 No module 'xformers'. Proceeding without it. /usr/local/lib/python3.10/dist-packages/pytorch_lightning/utilities/distributed.py:258: LightningDeprecationWarning: pytorch_lightning.utilities.distributed.rank_zero_only has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from pytorch_lightning.utilities instead. rank_zero_deprecation( LatentDiffusion: Running in v-prediction mode DiffusionWrapper has 865.91 M params. making attention of type 'vanilla' with 512 in_channels Working with z of shape (1, 4, 32, 32) = 4096 dimensions. making attention of type 'vanilla' with 512 in_channels open_clip_pytorch_model.bin: 100% 3.94G/3.94G [02:02<00:00, 32.1MB/s] ^C

batuannguyen commented 9 months ago

As my experience, it is caused due to RAM out of memory. Try to run in a device with larger RAM