Llava models are not consistent in response even after following specified prompt template

[mathav95raj]

Model : llava-llama-3-8b-v1_1-int4.gguf
Clip : llava-llama-3-8b-v1_1-mmproj-f16.gguf

According to [docs](https://llmfarm.tech/docs/prompt_format , I set up the prompt template as follows,
[system](You are a helpful, respectful and honest assistant.)

User: {prompt} Describe this image

Assistant:

If I upload the image and type this prompt, I get garbage response. If I do the same after I start with only a text input followed by the image, I get response. Even in the latter, if we upload subsequent images, the response is still of the older one.

[guinmoon]

Hello. Could you please send me prompt options screenshot. It looks like you have an empty first line.