damian0815
/

pashahlis-val-test-1e-6-ep30

Text-to-Image

Diffusers

StableDiffusionPipeline

Inference Endpoints

Model card Files Files and versions Community

damian0815 commited on Feb 26, 2023

Commit

ea70c43

•

1 Parent(s): ed8bcd4

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ It's available in [InvokeAI](https://github.com/invoke-ai) by adding the diffuse
 Training an SD model is subjective. Picking when to stop is a trade-off between an evaluation about how well the model reproduces the training data the way you want it to, vs how flexibly it is able to apply the new training data to novel outputs.
 There are some [generated image samples](grates) from each epoch to look at (generated with my python tool [grate](https://pypi.org/project/sdgrate/)).
-For example, [this one (warning: huuuge image, 20,000x10,000 pixels): ![grid of images](pashahlis-val-test_as-received_lr1e-6-768x768-thumbnail.jpg)](grates/pashahlis-val-test_as-received_lr1e-6-768x768.jpg).
 I'm satisfied that the training quality roughly follows the shape of the validation graph, but you might want to look at this image closely to verify for yourself that the best model is probably somewhere between epoch 30 and epoch 40.
 * Notice how at epochs 30 and 40 the `ancient temple` prompt produces a variety of different temples with different seeds. By epoch 50 some weird artefacts are starting to creep in, with the results becoming progressively more monotonous and, especially beginning epoch 80, increasingly bizarre.
@@ -34,7 +34,7 @@ I'm satisfied that the training quality roughly follows the shape of the validat
 ## try them yourself
-If you want to try them out for yourself, other epochs are available at [damian0815/pashahlis-val-test-1e-6-ep40](https://huggingface.io/damian0815/pashahlis-val-test-1e-6-ep40), [damian0815/pashahlis-val-test-1e-6-ep80](https://huggingface.io/damian0815/pashahlis-val-test-1e-6-ep80), [damian0815/pashahlis-val-test-1e-6-ep110](https://huggingface.io/damian0815/pashahlis-val-test-1e-6-ep110),

 Training an SD model is subjective. Picking when to stop is a trade-off between an evaluation about how well the model reproduces the training data the way you want it to, vs how flexibly it is able to apply the new training data to novel outputs.
 There are some [generated image samples](grates) from each epoch to look at (generated with my python tool [grate](https://pypi.org/project/sdgrate/)).
+For example, [this one (warning: huuuge image, 20,000x10,000 pixels): ![grid of images](pashahlis-val-test_as-received_lr1e-6-768x768-thumbnail.jpg)](grates/pashahlis-val-test_as-received_lr1e-6-768x768.jpg)
 I'm satisfied that the training quality roughly follows the shape of the validation graph, but you might want to look at this image closely to verify for yourself that the best model is probably somewhere between epoch 30 and epoch 40.
 * Notice how at epochs 30 and 40 the `ancient temple` prompt produces a variety of different temples with different seeds. By epoch 50 some weird artefacts are starting to creep in, with the results becoming progressively more monotonous and, especially beginning epoch 80, increasingly bizarre.
 ## try them yourself
+If you want to try them out for yourself, other epochs are available at [damian0815/pashahlis-val-test-1e-6-ep40](https://huggingface.co/damian0815/pashahlis-val-test-1e-6-ep40), [damian0815/pashahlis-val-test-1e-6-ep80](https://huggingface.co/damian0815/pashahlis-val-test-1e-6-ep80), [damian0815/pashahlis-val-test-1e-6-ep110](https://huggingface.co/damian0815/pashahlis-val-test-1e-6-ep110).