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
huggingfaceformat - Supports models in
ggufformat - 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 ingguffile such as tokenizer - Model GGUF:
mradermacher/Llama-3.2-1B-Instruct-Uncensored-i1-GGUF
Link to repo on huggingface that is hosting thegguffile(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 thegguffile 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