From 4e0972382164f1af0c5e6106134d843fc45b00a7 Mon Sep 17 00:00:00 2001 From: sakura1bgx Date: Fri, 7 Mar 2025 04:51:36 +0900 Subject: [PATCH] Update README.md - Merge to FlipStreamChat --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index b9aaaa8..4f0c66a 100644 --- a/README.md +++ b/README.md @@ -103,8 +103,7 @@ python -m pip install llama-cpp-python - **FlipStreamGate**: A node for consolidating input timing to ensure that inputs to the sampler do not occur sequentially. - **FlipStreamRembg**: A node for remove background. It depends on ComfyUI-Inspyrenet-Rembg. - **FlipStreamSegMask**: A node for segmentation masks. The target can contain multiple words separated by commas for segmentation. It will use the 'microsoft/Florence-2-large' model, which you can download using the DownloadAndLoadFlorence2Model node of ComfyUI-Florence2. Segmentation sometimes fails, so you may need to try some other random seeds. -- **FlipStreamLoadChatModel**: Loads an LLM (Large Language Model) for chat. It only supports *.gguf files in the models/LLM folder and uses llama-cpp-python. -- **FlipStreamChat**: Obtains chat responses from the chat model. +- **FlipStreamChat**: Loads an LLM (Large Language Model) and obtains chat responses. It only supports *.gguf files in the models/LLM folder and uses llama-cpp-python. - **FlipStreamBatchPrompt**: A node for simple batch prompting. Use the following format for the input prompt of this node. The 'pre text' and 'append text' sections apply to all frames. The separator `----` should consist of four hyphens, and each line of 'frame text' applies evenly to the number of frames specified in 'frames'. For example, if 'frames' is 8 and there are 2 'frame text' lines, they will be applied starting from frames 0 and 4. ``` pre text,