You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Since we passed the `--push_to_hub` flag, it will automatically create a model repo under your huggingface account based on `$HUB_MODEL_ID`. By the end of training, the final checkpoint will be automatically stored on the hub. You can find an example model repo [here](https://huggingface.co/YiYiXu/fill-circle-controlnet).
Copy file name to clipboardExpand all lines: examples/controlnet/README_flux.md
+4-2Lines changed: 4 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -58,7 +58,8 @@ When running `accelerate config`, if we specify torch compile mode to True there
58
58
## Custom Datasets
59
59
60
60
We support dataset formats:
61
-
The original dataset is hosted in the [ControlNet repo](https://huggingface.co/lllyasviel/ControlNet/blob/main/training/fill50k.zip). We re-uploaded it to be compatible with `datasets`[here](https://huggingface.co/datasets/fusing/fill50k). Note that `datasets` handles dataloading within the training script. To use our example, add `--dataset_name=fusing/fill50k \` to the script and remove line `--jsonl_for_train` mentioned below.
61
+
The original dataset is hosted in the [ControlNet repo](https://huggingface.co/lllyasviel/ControlNet/blob/main/training/fill50k.zip). We re-uploaded it to be compatible with `datasets`[here](https://huggingface.co/datasets/fusing/fill50k). Note that `datasets` handles dataloading within the training script. To use our example, add `--dataset_name=fusing/fill50k \
62
+
--trust_remote_code \` to the script and remove line `--jsonl_for_train` mentioned below.
62
63
63
64
64
65
We also support importing data from jsonl(xxx.jsonl),using `--jsonl_for_train` to enable it, here is a brief example of jsonl files:
@@ -84,7 +85,8 @@ we can define the num_layers, num_single_layers, which determines the size of th
0 commit comments