Instructions to use prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8")
model = AutoModelForMultimodalLM.from_pretrained("prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8

SGLang

How to use prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8 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 "prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8" \
    --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": "prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8",
		"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 "prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8" \
        --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": "prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8 with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Qwen-Image-2.1-PE-T2I-FP8
```

prithivMLmods commited on 5 days ago

Commit

6f49d7d

verified ·

1 Parent(s): 7eb8cdd

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -21,6 +21,9 @@ pipeline_tag: text-generation
 > **Qwen-Image-2.1-PE-T2I-FP8** is an **FP8 dynamic-quantized** build of [Qwen/Qwen-Image-2.1-PE-T2I](https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I), the text-to-image **prompt rewriting model** for [Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1). The base model is a fine-tuned **Qwen3.5-VL 9B** that turns a brief image request in any language into a detailed English prompt plus a recommended aspect ratio. This checkpoint was compressed with **[llm-compressor](https://github.com/vllm-project/llm-compressor)** using the **FP8_DYNAMIC** scheme, stored in the **compressed-tensors** format, and is intended to be served with **[vLLM](https://github.com/vllm-project/vllm)**. The **Linear** layers are quantized to **FP8** weights with dynamic per-token FP8 activations, which lowers weight memory and improves serving throughput relative to the BF16 original. The **lm_head**, **embedding layers**, **vision modules**, and **linear attention** layers are excluded and kept in their original precision. No calibration data is required, because activation scales are computed at runtime.
 ## Quantization Details
 | Property | Value |

 > **Qwen-Image-2.1-PE-T2I-FP8** is an **FP8 dynamic-quantized** build of [Qwen/Qwen-Image-2.1-PE-T2I](https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I), the text-to-image **prompt rewriting model** for [Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1). The base model is a fine-tuned **Qwen3.5-VL 9B** that turns a brief image request in any language into a detailed English prompt plus a recommended aspect ratio. This checkpoint was compressed with **[llm-compressor](https://github.com/vllm-project/llm-compressor)** using the **FP8_DYNAMIC** scheme, stored in the **compressed-tensors** format, and is intended to be served with **[vLLM](https://github.com/vllm-project/vllm)**. The **Linear** layers are quantized to **FP8** weights with dynamic per-token FP8 activations, which lowers weight memory and improves serving throughput relative to the BF16 original. The **lm_head**, **embedding layers**, **vision modules**, and **linear attention** layers are excluded and kept in their original precision. No calibration data is required, because activation scales are computed at runtime.
+> [!NOTE]
+System Prompt — https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I/blob/main/system_prompt.txt
 ## Quantization Details
 | Property | Value |