From d034b389e3164c79669e803812712c55eb3d5624 Mon Sep 17 00:00:00 2001 From: Zeke Sikelianos Date: Thu, 19 Sep 2024 07:38:12 -0700 Subject: [PATCH 1/3] summarize features in README --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/README.md b/README.md index dc25a67..b156592 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,13 @@ It's live at [replicate.com/ostris/flux-dev-lora-trainer](https://replicate.com/ It also includes code for running inference with a fine-tuned model. +## Features + +- Automatic image captioning during training +- LoRA inference +- Optionally uploads fine-tuned weights to Hugging Face after training +- Automated test suite with [cog-safe-push](https://github.com/replicate/cog-safe-push) for continuous deployment + ## Getting Started If you're looking to create your own fine-tuned model on Replicate, you don't need to do anything with this codebase. From 605d628240bbb54bed7d3bb4256bdea5527d5601 Mon Sep 17 00:00:00 2001 From: Zeke Sikelianos Date: Thu, 19 Sep 2024 09:05:08 -0700 Subject: [PATCH 2/3] Update README.md Co-authored-by: fofr --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b156592..1c427a9 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,7 @@ It also includes code for running inference with a fine-tuned model. ## Features - Automatic image captioning during training -- LoRA inference +- Image generation using the LoRA (inference) - Optionally uploads fine-tuned weights to Hugging Face after training - Automated test suite with [cog-safe-push](https://github.com/replicate/cog-safe-push) for continuous deployment From 2ea00ab5160cafbe411b55d1f297180b20d22af1 Mon Sep 17 00:00:00 2001 From: Zeke Sikelianos Date: Thu, 19 Sep 2024 09:05:23 -0700 Subject: [PATCH 3/3] Update README.md Co-authored-by: fofr --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 1c427a9..75fa8ef 100644 --- a/README.md +++ b/README.md @@ -12,6 +12,7 @@ It also includes code for running inference with a fine-tuned model. - Image generation using the LoRA (inference) - Optionally uploads fine-tuned weights to Hugging Face after training - Automated test suite with [cog-safe-push](https://github.com/replicate/cog-safe-push) for continuous deployment +- Weights and biases integration ## Getting Started