Instructions to use Rom3rk/Qwen3.8-27B-ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rom3rk/Qwen3.8-27B-ComfyUI with Transformers:

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

pipe = pipeline("image-text-to-text", model="Rom3rk/Qwen3.8-27B-ComfyUI")
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("Rom3rk/Qwen3.8-27B-ComfyUI")
model = AutoModelForMultimodalLM.from_pretrained("Rom3rk/Qwen3.8-27B-ComfyUI", 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 Rom3rk/Qwen3.8-27B-ComfyUI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rom3rk/Qwen3.8-27B-ComfyUI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rom3rk/Qwen3.8-27B-ComfyUI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Rom3rk/Qwen3.8-27B-ComfyUI

SGLang

How to use Rom3rk/Qwen3.8-27B-ComfyUI 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 "Rom3rk/Qwen3.8-27B-ComfyUI" \
    --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": "Rom3rk/Qwen3.8-27B-ComfyUI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Rom3rk/Qwen3.8-27B-ComfyUI" \
        --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": "Rom3rk/Qwen3.8-27B-ComfyUI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Rom3rk/Qwen3.8-27B-ComfyUI with Docker Model Runner:
```
docker model run hf.co/Rom3rk/Qwen3.8-27B-ComfyUI
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3.8-27B-ComfyUI

Qwen3.8-27B-ComfyUI is a fine-tuned Qwen3.8-27B model specialized for generating, editing, repairing, auditing, and explaining ComfyUI frontend/UI workflow JSON.

Overview

ComfyUI request
    -> interpret workflow intent and constraints
    -> generate, edit, repair, audit, or explain
    -> return workflow JSON or a conversational answer

Capabilities

Generate ComfyUI UI workflows from natural-language requests
Edit existing workflows while preserving requested components
Repair invalid, incomplete, or disconnected workflows
Audit workflow structure, nodes, inputs, and links
Explain workflow behavior and node interactions
Provide raw workflow JSON or conversational ComfyUI assistance

Quick Start

Install the required libraries:

pip install --upgrade transformers accelerate safetensors

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

MODEL_ID = "Rom3rk/Qwen3.8-27B-ComfyUI"
ENABLE_THINKING = False

processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForImageTextToText.from_pretrained(
    MODEL_ID,
    dtype=torch.bfloat16,
    device_map="auto",
).eval()

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": (
                    "Create a ComfyUI UI workflow for an SDXL image-to-image "
                    "pipeline with a ControlNet depth branch and return the "
                    "complete loadable UI workflow JSON."
                ),
            }
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    enable_thinking=ENABLE_THINKING,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.inference_mode():
    generated_ids = model.generate(
        **inputs,
        max_new_tokens=4096,
        do_sample=True,
        temperature=0.7,
        top_p=0.8,
        top_k=20,
    )

new_tokens = generated_ids[:, inputs.input_ids.shape[1]:]
response = processor.batch_decode(
    new_tokens,
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False,
)[0]

print(response)

The model uses Qwen's native chat template. Set ENABLE_THINKING according to the task and inference runtime rather than replacing the template.

Usage Examples

Workflow Generation

Create a ComfyUI UI workflow for an SDXL image-to-image pipeline with a ControlNet depth branch, a two-stage sampler, and a final image-save node. Return the complete loadable UI workflow JSON.

Workflow Editing

Modify the following ComfyUI UI workflow to add a second ControlNet branch. Preserve the existing model, sampler settings, node positions, and unrelated links.

Workflow Repair

Repair the invalid links and missing required inputs in this ComfyUI UI workflow. Keep all valid nodes and settings unchanged, and return the corrected workflow JSON.

Workflow Audit

Audit this ComfyUI UI workflow for invalid endpoints, disconnected nodes, incompatible inputs, redundant components, and settings that conflict with the requested generation pipeline.

Recommended Sampling Settings

Mode	Temperature	Top-p	Top-k	Presence penalty
Thinking	1.0	0.95	20	0.0
Non-thinking	0.7	0.80	20	1.5

These settings follow the recommendations published for Qwen3.8. Availability and parameter names may vary by inference runtime.

Questions and Feedback

For questions, bug reports, workflow compatibility issues, or general feedback, please open a Discussion from this repository's Community tab.

When reporting a workflow issue, please include:

Inference runtime and version
ComfyUI version
Relevant custom nodes
The original prompt
The generated workflow JSON or raw model output

License and Attribution

This model is a modified derivative of Qwen/Qwen3.8-27B and is distributed under the Apache License 2.0. See the repository's LICENSE file for the full license text.

Qwen3.8 was developed by the Qwen Team. Model fine-tuning and merging used Unsloth.

Citation

@misc{qwen38,
  title  = {{Qwen3.8-Max}: A New Bar for Coding and Cowork},
  author = {{Qwen Team}},
  month  = {August},
  year   = {2026},
  url    = {https://qwen.ai/blog?id=qwen3.8}
}

References

Downloads last month: -

Safetensors

Model size

28B params

Tensor type

BF16

Model tree for Rom3rk/Qwen3.8-27B-ComfyUI

Base model

Qwen/Qwen3.8-27B

Finetuned

(217)

this model

Quantizations

2 models