Skip to content

Prompt Enhance

Note

Different model types have different preferences on how to prompt them. For details, see Prompting model specific tips.

SD.Next includes built-in prompt enhancer that uses LLM to enhance your prompts:

  • Can be used to manually or automatically enhance prompts
    Automatic enhancement is done during normal generation without user intervention
  • Built-in presets for:
    Gemma-3, Qwen-2.5, Phi-4, Llama-3.2, SmolLM2, Dolphin-3
  • Support for custom system prompt
  • Support for custom models
  • Load any models hosted on huggingface
  • Supports models in huggingface format
  • Supports models in gguf format
  • Models are auto-downloaded on first use
  • Support quantization and offloading
  • Advanced options: max tokens, sampling, temperature, repetition penalty

Warning

If SD.Next detected censored output, it will print warning in the log file and return original prompt

[!NOTE] Any model hosted on huggingface in original format should work
as long as it implements standard transformers.AutoModelForCausalLM interface

[!NOTE] Not all model architecture are supported for gguf format
Typically gguf support is added slightly later than transformers support

[!TIP] Debug logging can be enabled using SD_LLM_DEBUG=true env variable

Custom models

Can be used to define any model that is not included in predefined list

Example: standard huggingface model

  • Model repo: nidum/Nidum-Gemma-3-4B-it-Uncensored

Example: gguf model hosted on huggingface

  • Model repo: meta-llama/Llama-3.2-1B-Instruct
    Link to original model repo on huggingface, required so that SD.Next can download components not present in gguf file such as tokenizer
  • Model GGUF: mradermacher/Llama-3.2-1B-Instruct-Uncensored-i1-GGUF
    Link to repo on huggingface that is hosting the gguf file(s)
  • Model type: llama
    Model type, required for SD.Next to know how to load the model
  • Model name: Llama-3.2-1B-Instruct-Uncensored.i1-Q4_0.gguf
    Name of the gguf file inside gguf repo

Supported GGUF model types: llama, mistral, qwen2, qwen2moe, falcon, tokenizer, phi3, bloom, t5, stablelm, gpt2, starcoder2, mamba, nemotron, gemma2 Supported Transformer model types is a superset of GGUF model types and includes model types such as latest gemma3
In case of unsupported model type, SD.Next will print currently supported model types in the log file