Viggle/Qwen-Image-2.1-viggle-turbo — new model trending #30 on Hugging Face

v0.2.1 is the step-700 checkpoint of the run whose step-600 checkpoint shipped as v0.2 on 2026-09-23: 100 more

training steps, same recipe, same 6-step schedule. Against v0.2 it is a little sharper (Laplacian sharpness 0.0199

vs 0.0187) and marginally more diverse (0.98× vs 0.97× the base model), with the same 0% composition drift. The v0.2

files (`Qwen-Image-2.1-viggle-turbo-v0.2-5step-lora-r256.safetensors`, the r128 cut, `peft_v0.2/`) stay in the repository unchanged;

sample them with the same 6-step nodes (the `5step` in their name is the schedule they launched with, see

[Rules that matter](#rules-that-matter)).

What changed against v0.1, measured on our held-out set of 96 user requests (text-to-image and editing) against the

40-step base model with its official prompt enhancement:

| | v0.1 LoRA r64 | v0.1 full fine-tune | **v0.2.1 LoRA r256, 6 steps** | v0.2 LoRA r256, 6 steps | (v0.2 at 5 steps) | (v0.2 at 4 steps) |

|---|---|---|---|---|---|---|

| sample diversity, × base model ¹ | 0.75 | 0.72 | **0.98** | 0.97 | 0.93 | 0.89 |

| composition drift vs base model ² | −0.019 | −0.033 | **+0.000** | −0.001 | +0.000 | +0.002 |

| prompts whose layout differs from the base model ³ | — | — | **0%** | 0% | 4% | — |

¹ mean intra-prompt DINOv2 patch distance over 8 seeds per prompt, 32 prompts, as a ratio to the 40-step base model

(1.00 = as diverse as the base). v0.1 collapsed seeds onto near-identical layouts; v0.2 keeps the base model's spread.

² mean horizontal drift of the image centroid relative to the base model's output for the same prompt and seed, in

image widths; 0 means the student places its subjects where the base model does.

³ share of the 96 prompts where the student's composition visibly differs from the base model's for the same seed

(centroid drift above 0.05 image widths). In practice v0.2 and v0.2.1 follow the prompt

and the reference images noticeably more faithfully than v0.1 — fewer dropped or merged instructions, less ghosting

of duplicated subjects — and match the base model's sharpness where the v0.1 LoRA was softer.

The v0.2 files and the v0.1 artifacts (`transformer/` full fine-tune and the r64 LoRA, both 4-step) stay in the

repository unchanged for reproducibility; there is no reason to prefer them.

> **Known limits.** Complicated edits (multi-reference composition, face swaps, identity-preserving edits, instructions

> with several constraints) can still fall short of the 40-step base model. We will keep updating this repository as

> the distillation improves.

## What's inside

```

Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors # v0.2.1 LoRA (rank 256, alpha 256), diffusers key format, bf16 <- use this

peft_v0.2.1/ # the same v0.2.1 adapter in peft key format, F32 as trained

Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r128.safetensors # v0.2.1 LoRA truncated to rank 128 (alpha 128), diffusers key format, bf16

comfyui/ # ComfyUI custom nodes (viggle_turbo.py), text-to-image and edit workflows, example inputs

scheduler/scheduler_config.json # base scheduler config with shift_terminal: null

Qwen-Image-2.1-viggle-turbo-v0.2-5step-lora-r256.safetensors # v0.2 LoRA (step 600 of the same run), kept for reference

Qwen-Image-2.1-viggle-turbo-v0.2-5step-lora-r128.safetensors # v0.2 LoRA truncated to rank 128, kept for reference

peft_v0.2/ # v0.2 adapter in peft key format, F32

Qwen-Image-2.1-viggle-turbo-4step-lora-r64.safetensors # v0.1 LoRA (rank 64), 4-step, kept for reference

peft/ # v0.1 adapter in peft key format, F32

transformer/ # v0.1 full fine-tuned transformer (bf16), 4-step, kept for reference

LICENSE, NOTICE, README.md

```

Shipped checkpoint: v0.2.1 is the step-700 EMA student (v0.2 was step 600) of a LoRA run (rank 256 on the attention, image-MLP, modulation and

timestep-embedder projections) that adds SenseFlow-style intra-segment guidance (the student's velocity over each of its

segments is regressed on the teacher's) and prompt-enhanced teacher targets to the DMD objective;

it was trained on the 4-step schedule and is sampled with the first (highest-noise) segment cut into three (6 steps),

which removes the detail loss, ghosting and composition drift of the plain 4-step rollout (5 steps, the segment cut in

two, was the launch schedule; 6 is strictly better on every metric we track, with the same weights). The LoRA is never merged into the transformer — merging into

bf16 is lossy, loading it at runtime is exact. Text encoder, VAE and processor are not redistributed; they load from the base repo.

## Install

```bash

pip install -U torch "transformers>=5.17,<6" accelerate safetensors peft pillow

pip install "git+https://github.com/huggingface/diffusers.git@80c7ed262aeffbeb43ef13ae04baeb9b84515a69"

```

`QwenImage21Pipeline` is not in a released `diffusers` yet, hence the pinned git install. `peft` is required.

## Usage

### Load the v0.2.1 LoRA

```python

import torch

from diffusers import QwenImage21Pipeline, FlowMatchEulerDiscreteScheduler

pipe = QwenImage21Pipeline.from_pretrained("Qwen/Qwen-Image-2.1", dtype=torch.bfloat16)

pipe.load_lora_weights(

"Viggle/Qwen-Image-2.1-viggle-turbo",

weight_name="Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-lora-r256.safetensors",

)

pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(

"Viggle/Qwen-Image-2.1-viggle-turbo", subfolder="scheduler"

)

pipe.to("cuda")

STEPS, SIGMAS = 6, [1.0, 0.9375, 0.875, 0.75, 0.5, 0.25] # the v0.2.1 schedule; pass both to every call

```

<details>

<summary>v0.1 students (4-step, for reference)</summary>

```python

# v0.1 full fine-tuned transformer

from diffusers import QwenImage21Transformer2DModel

transformer = QwenImage21Transformer2DModel.from_pretrained(

"Viggle/Qwen-Image-2.1-viggle-turbo", subfolder="transformer", torch_dtype=torch.bfloat16

)

pipe = QwenImage21Pipeline.from_pretrained("Qwen/Qwen-Image-2.1", transformer=transformer, dtype=torch.bfloat16)

# v0.1 LoRA

pipe.load_lora_weights("Viggle/Qwen-Image-2.1-viggle-turbo", weight_name="Qwen-Image-2.1-viggle-turbo-4step-lora-r64.safetensors")

# both: the shipped scheduler as above, then num_inference_steps=4 and no sigmas= argument

```

Never stack two students (a LoRA on top of the fine-tuned transformer, or both LoRAs).

</details>

### Text to image

```python

image = pipe(

prompt="A studio portrait of an old fisherman mending a net, warm rim light, 85mm.",

height=1024,

width=1024,

num_inference_steps=STEPS,

sigmas=SIGMAS,

true_cfg_scale=1.0, # no CFG (also the default)

generator=torch.Generator("cuda").manual_seed(0),

Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo