Instructions to use trollek/SmolImagePromptHelper-135M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trollek/SmolImagePromptHelper-135M with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="trollek/SmolImagePromptHelper-135M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trollek/SmolImagePromptHelper-135M")
model = AutoModelForCausalLM.from_pretrained("trollek/SmolImagePromptHelper-135M", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trollek/SmolImagePromptHelper-135M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trollek/SmolImagePromptHelper-135M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trollek/SmolImagePromptHelper-135M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trollek/SmolImagePromptHelper-135M

SGLang

How to use trollek/SmolImagePromptHelper-135M with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "trollek/SmolImagePromptHelper-135M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trollek/SmolImagePromptHelper-135M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "trollek/SmolImagePromptHelper-135M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trollek/SmolImagePromptHelper-135M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trollek/SmolImagePromptHelper-135M with Docker Model Runner:
```
docker model run hf.co/trollek/SmolImagePromptHelper-135M
```

SmolImagePromptHelper-135M / README.md

trollek

Update README.md

ac35bc1 verified over 1 year ago

preview code

Raw History Blame Contribute Delete

2.58 kB

---
license: apache-2.0
datasets:
- trollek/ImagePromptHelper-v02
- Gustavosta/Stable-Diffusion-Prompts
- k-mktr/improved-flux-prompts
- Falah/image_generation_prompts_SDXL
- ChrisGoringe/flux_prompts
language:
- en
base_model:
- HuggingFaceTB/SmolLM2-135M
library_name: transformers
tags:
- llama-factory
- full
---
# Smol Image Prompt Helper

This is meant to be a drop-in replacement for [my last image prompt helper](https://huggingface.co/trollek/ImagePromptHelper-danube3-500M) but with a new trick and a much smaller size. 
It achieves the following results on the evaluation set:
- Loss: 1.0077

## Model description

Lets say you have a node in ComfyUI to parse JSON and send the appropriate prompt to the text encoders. Tadaaa:

```
You are an AI assistant tasked with expanding and formatting image prompts. You are given an input that you will need to write image prompts for different text encoders.
Always respond with the following format:
{
    "clip_l": "<keywords from image analysis>",
    "clip_g": "<simple descriptions of the image>",
    "t5xxl": "<complex semanticly rich description of the image>",
    "negative": "<contrasting keywords for what is not in the image>"
}
```

## Intended uses & limitations

Have a look at the dataset that I created \([ImagePromptHelper-v02](https://huggingface.co/datasets/trollek/ImagePromptHelper-v02) \(CC BY 4.0\)\) and you will see whaaaaat I've doooone.

## Training procedure

I continued the pretraining with SDXL and Flux prompts and then SFT'd it on my own dataset.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 1
- seed: 443
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.1631        | 0.3966 | 500  | 1.2816          |
| 1.019         | 0.7932 | 1000 | 1.1431          |
| 0.9857        | 1.1896 | 1500 | 1.0818          |
| 1.0436        | 1.5862 | 2000 | 1.0459          |
| 0.9918        | 1.9827 | 2500 | 1.0235          |
| 0.9287        | 2.3791 | 3000 | 1.0114          |
| 0.9205        | 2.7757 | 3500 | 1.0079          |


### Framework versions

- Transformers 4.50.0
- Pytorch 2.6.0+cu126
- Datasets 3.4.1
- Tokenizers 0.21.0

	---
	license: apache-2.0
	datasets:
	- trollek/ImagePromptHelper-v02
	- Gustavosta/Stable-Diffusion-Prompts
	- k-mktr/improved-flux-prompts
	- Falah/image_generation_prompts_SDXL
	- ChrisGoringe/flux_prompts
	language:
	- en
	base_model:
	- HuggingFaceTB/SmolLM2-135M
	library_name: transformers
	tags:
	- llama-factory
	- full
	---

	# Smol Image Prompt Helper

	This is meant to be a drop-in replacement for [my last image prompt helper](https://huggingface.co/trollek/ImagePromptHelper-danube3-500M) but with a new trick and a much smaller size.
	It achieves the following results on the evaluation set:
	- Loss: 1.0077

	## Model description

	Lets say you have a node in ComfyUI to parse JSON and send the appropriate prompt to the text encoders. Tadaaa:

	```
	You are an AI assistant tasked with expanding and formatting image prompts. You are given an input that you will need to write image prompts for different text encoders.
	Always respond with the following format:
	{
	"clip_l": "<keywords from image analysis>",
	"clip_g": "<simple descriptions of the image>",
	"t5xxl": "<complex semanticly rich description of the image>",
	"negative": "<contrasting keywords for what is not in the image>"
	}
	```

	## Intended uses & limitations

	Have a look at the dataset that I created \([ImagePromptHelper-v02](https://huggingface.co/datasets/trollek/ImagePromptHelper-v02) \(CC BY 4.0\)\) and you will see whaaaaat I've doooone.

	## Training procedure

	I continued the pretraining with SDXL and Flux prompts and then SFT'd it on my own dataset.

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 2e-05
	- train_batch_size: 8
	- eval_batch_size: 1
	- seed: 443
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 64
	- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_ratio: 0.05
	- num_epochs: 3

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 1.1631 \| 0.3966 \| 500 \| 1.2816 \|
	\| 1.019 \| 0.7932 \| 1000 \| 1.1431 \|
	\| 0.9857 \| 1.1896 \| 1500 \| 1.0818 \|
	\| 1.0436 \| 1.5862 \| 2000 \| 1.0459 \|
	\| 0.9918 \| 1.9827 \| 2500 \| 1.0235 \|
	\| 0.9287 \| 2.3791 \| 3000 \| 1.0114 \|
	\| 0.9205 \| 2.7757 \| 3500 \| 1.0079 \|


	### Framework versions

	- Transformers 4.50.0
	- Pytorch 2.6.0+cu126
	- Datasets 3.4.1
	- Tokenizers 0.21.0