Downloads · 30 days
23K
22% of all-time downloads
Abiray/Qwen-Image-2.1-viggle-4-steps-turbo-GGUF
Qwen-Image-2.1-viggle-4-steps-turbo-GGUF is a text-to-image model from Abiray. Use it when you need an image from a text prompt. The card lists the license as other.
This repository contains optimized community GGUF quantizations of Viggle/Qwen-Image-2.1-viggle-turbo, an official 4-step distilled student model of Qwen-Image-2.1 trained by Viggle using Distribution Matching Distill…
Downloads · 30 days
23K
22% of all-time downloads
All-time downloads
106K
Public
Repo size
29.9 GB
Likes
27
Trending 1
Click a slice to open those files.
.gguf29.9 GB · 100%
From the Hugging Face model README
This repository contains optimized community GGUF quantizations of Viggle/Qwen-Image-2.1-viggle-turbo, an official 4-step distilled student model of Qwen-Image-2.1 trained by Viggle using Distribution Matching Distillation (DMD).
These files were converted directly from the official full transformer weights (transformer/diffusion_pytorch_model.safetensors), allowing you to run near-instant 4-step image generation and image editing natively inside ComfyUI without needing to stack external LoRAs.
Because this model is distilled with DMD, it requires specific inference parameters. Using standard diffusion parameters will degrade image quality or cause visual burn artifacts:
| Parameter | Value | Note |
|---|---|---|
| Steps | 4 or 8 steps | Do not increase to 25 or 40. |
| CFG (Guidance Scale) | 1.0 | Must remain at 1.0 (trained without classifier-free guidance). |
| Negative Prompt | Empty (Blank) | Leave blank; CFG 1.0 ignores negative prompts. |
| Sampler | euler | Standard Euler sampler. |
| Scheduler | simple (or FlowMatch Euler) | Matches the distilled flow-matching trajectory. |
| Denoise | 1.0 | For standard text-to-image generation. |
All quants preserve high-precision FP32 attention normalization layers (norm_k, norm_q, text_norm) to eliminate NaN errors and color banding, alongside native BF16 patch input embeddings (img_in.weight). The _M tiers retain 6-bit precision (Q6_K) on critical attention value projections (attn.to_v.weight) and native BF16 on text conditioning input layers (txt_in).
| Filename | Quant Type | File Size | Recommended VRAM | Description |
|---|---|---|---|---|
qwen_image_2.1_turbo_Q8_0.gguf | Q8_0 | 7.59 GB | 16 GB+ | Near-lossless 8-bit master quant. |
qwen_image_2.1_turbo_Q6_K.gguf | Q6_K | 5.88 GB | 12 GB - 16 GB | High-detail tier with 6-bit attention. |
qwen_image_2.1_turbo_Q5_K_M.gguf | Q5_K_M | 5.01 GB | 10 GB - 12 GB | Best quality-to-size balance (6-bit to_v heads). |
qwen_image_2.1_turbo_Q4_K_M.gguf | Q4_K_M | 4.19 GB | 8 GB - 12 GB | Recommended for most GPUs (RTX 3060/4060, Tesla T4). |
qwen_image_2.1_turbo_Q4_K_S.gguf | Q4_K_S | 4.06 GB | 8 GB | Slightly smaller 4-bit footprint. |
qwen_image_2.1_turbo_Q3_K_M.gguf | Q3_K_M | 3.19 GB | 6 GB - 8 GB | Ultra-low VRAM tier. |
Ensure your ComfyUI and custom nodes are updated:
qwen_image architecture recognition)pip install -U "gguf>=0.13.0"Troubleshooting Note: If you encounter
ValueError: This model is not currently supported - (Unknown model architecture!), update your installation viagit pullin both yourComfyUIroot andComfyUI/custom_nodes/ComfyUI-GGUFdirectories, then restart the server.
Place your downloaded models into the standard ComfyUI directories: ComfyUI/ ├── models/ │ ├── diffusion_models/ │ │ └── qwen_image_2.1_turbo_Q4_K_M.gguf │ ├── text_encoders/ │ │ └── qwen3vl_8b_int8_convrot.safetensors (or fp8_scaled / w4a8) │ └── vae/ │ └── qwen_image_2.1_vae_bf16.safetensors
Supporting text encoder and VAE weights can be downloaded from Comfy-Org:
UnetLoaderGGUF to load the selected Turbo GGUF file.CLIPLoader set to type qwen_image) and VAE (VAELoader).TextEncodeQwenImage21.KSampler to:
steps: 4cfg: 1.0sampler_name: eulerscheduler: simpledenoise: 1.0Qwen-Image-2.1 natively handles instruction-based image editing directly:
Load Image node.image_1 input slot on the TextEncodeQwenImage21 node.vae input slot on TextEncodeQwenImage21.steps: 4 and cfg: 1.0.Viggle — Viggle/Qwen-Image-2.1-viggle-turbo
city96/ComfyUI-GGUF and llama.cpp.