---
base_model:
- Qwen/Qwen3.8-27B
base_model_relation: finetune
license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- transformers
- safetensors
- qwen3.8
- conversational
- comfyui
- fine-tuned
- sft
- unsloth
- vision-language
- mtp
---

# 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

```text
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:

```bash
pip install --upgrade transformers accelerate safetensors
```

```python
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

```text
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

```text
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

```text
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

```text
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](https://huggingface.co/Qwen/Qwen3.8-27B) and is distributed under the [Apache License 2.0](https://www.apache.org/licenses/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](https://unsloth.ai/).

## Citation

```bibtex
@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

- [Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B)
- [Unsloth](https://unsloth.ai/)
- [Transformers](https://huggingface.co/docs/transformers/)