Initial commit

.gitattributes

@@ -0,0 +1,63 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/unsloth_baking.png filter=lfs diff=lfs merge=lfs -text
+assets/unsloth_cartoon.png filter=lfs diff=lfs merge=lfs -text
+assets/unsloth_field.png filter=lfs diff=lfs merge=lfs -text
+assets/unsloth_headshot.png filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-7.0bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-7.5bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-2.63bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-3.0bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-3.5bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-4.0bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-4.33bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-4.66bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-5.0bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-UD-6.0bpw.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+qwen-image-2.1-F16.gguf filter=lfs diff=lfs merge=lfs -text
+assets/qwen21_pareto.png filter=lfs diff=lfs merge=lfs -text
+assets/qwen21_pareto_v2.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,216 @@
+---
+base_model: Qwen/Qwen-Image-2.1
+base_model_relation: quantized
+license: other
+license_name: qwen-research
+license_link: https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/LICENSE
+language:
+- en
+- zh
+pipeline_tag: text-to-image
+tags:
+- gguf
+- quantized
+- unsloth
+- qwen
+- image-generation
+widget:
+- text: a cartoon sloth mascot waving, flat vector illustration, bright colours
+  output:
+    url: assets/unsloth_cartoon.png
+- text: a sloth baking bread in a rustic kitchen, warm morning light, photorealistic
+  output:
+    url: assets/unsloth_baking.png
+---
+This is a GGUF quantized version of [Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1). <br>
+unsloth/Qwen-Image-2.1-GGUF uses [Unsloth Dynamic 2.0](https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs) methodology for SOTA performance.
+
+- Important layers are upcasted to higher precision, per tensor, from a measured sensitivity scan.
+- Run these with [stable-diffusion.cpp](https://github.com/unslothai/stable-diffusion.cpp). A GGUF is the denoiser only, so it needs the VAE and the Qwen3-VL text encoder alongside it.
+- VAE: [unsloth/Qwen-Image-2.1-FP8](https://huggingface.co/unsloth/Qwen-Image-2.1-FP8) `vae/qwen_image_2.1_vae_bf16.safetensors`. Text encoder: [unsloth/Qwen3-VL-8B-Instruct-GGUF](https://huggingface.co/unsloth/Qwen3-VL-8B-Instruct-GGUF) `Qwen3-VL-8B-Instruct-Q4_K_M.gguf`.
+
+```bash
+sd-cli --diffusion-model qwen-image-2.1-Q4_K_M.gguf \
+  --vae qwen_image_2.1_vae_bf16.safetensors \
+  --llm Qwen3-VL-8B-Instruct-Q4_K_M.gguf \
+  -p "a cartoon sloth mascot waving, flat vector illustration, bright colours" \
+  --steps 20 --cfg-scale 6.0 --sampling-method euler -W 1024 -H 1024 --diffusion-fa \
+  -o out.png
+```
+
+
+<div>
+  <div style="display: flex; gap: 5px; align-items: center; ">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://docs.unsloth.ai/">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+</div>
+
+### Samples
+
+Rendered with the Q4_K_M file, 1024x1024, 20 steps, cfg 6.0, euler.
+
+<table>
+  <tr>
+    <td><img src="assets/unsloth_cartoon.png" width="200"></td>
+    <td><img src="assets/unsloth_headshot.png" width="200"></td>
+  </tr>
+  <tr>
+    <td><img src="assets/unsloth_baking.png" width="200"></td>
+    <td><img src="assets/unsloth_field.png" width="200"></td>
+  </tr>
+</table>
+
+---
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/image2.1/logo.png" width="400"/>
+</p>
+<p align="center">
+    🤖 <a href="https://modelscope.cn/models/Qwen/Qwen-Image-2.1">ModelScope</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;🤗 <a href="https://huggingface.co/Qwen/Qwen-Image-2.1">HuggingFace</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;📑 <a href="https://qwen.ai/blog?id=qwen-image-2.1">Blog</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;🖥️ <a href="https://huggingface.co/spaces/Qwen/Qwen-Image-2.1">Demo</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;🫨 <a href="https://discord.gg/BEYSk3pkSu">Discord</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;💬 <a href="https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/assets/qr.png">WeChat</a>
+</p>
+
+## Introduction
+
+We are excited to open-source **Qwen-Image-2.1**, a unified text-to-image generation and image editing model in the Qwen family. With just **7B parameters in its visual generation component** (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.
+
+Four key improvements define this release:
+
+- **Compact and Efficient**: a lightweight architecture with mixed-granularity attention and prefix KV cache reuse delivers strong image quality at low computational cost.
+- **Native Transparency, Unified Creation and Editing**: generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photographs, all in one model.
+- **Versatile Editing**: support up to **10 reference images**, specify local edits via circles, painted annotations, or separate masks, and preserve identity for people and products.
+- **Realistic Textures and Refined Aesthetics**: improved typography, portrait lighting, and fine details for more visually compelling results.
+
+<p align="center">
+    <img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-01.png" width="100%"/>
+</p>
+
+For more details, see the [GitHub repo](https://github.com/QwenLM/Qwen-Image-2.1) and [Blog](https://qwen.ai/blog?id=qwen-image-2.1).
+
+## Quick Start
+
+### Installation
+
+```bash
+pip install torch>=2.4.0
+pip install transformers>=5.17
+pip install git+https://github.com/huggingface/diffusers
+pip install accelerate pillow
+```
+
+### Text-to-Image
+
+```python
+import torch
+from diffusers import QwenImage21Pipeline
+
+pipe = QwenImage21Pipeline.from_pretrained(
+    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
+).to("cuda")
+
+image = pipe(
+    prompt="A neon shop sign that reads \"QWEN IMAGE 2.1\", rainy night, reflections on wet pavement",
+    width=2048, height=2048,
+    num_inference_steps=40,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+
+image.save("t2i_example.png")
+```
+
+### Image Editing
+
+```python
+import torch
+from PIL import Image
+from diffusers import QwenImage21Pipeline
+
+pipe = QwenImage21Pipeline.from_pretrained(
+    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
+).to("cuda")
+
+input_image = Image.open("input.png")
+
+image = pipe(
+    prompt="Change the background to a sunset beach",
+    image=input_image,
+    num_inference_steps=40,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+
+image.save("edit_example.png")
+```
+
+### Transparent Image Generation (RGBA)
+
+Use the recommended prompt format for transparent images:
+
+```python
+image = pipe(
+    prompt="This is an RGBA image with transparency. A cute cartoon dragon sticker. The image has alpha channel and the background is transparent.",
+    width=2048, height=2048,
+    num_inference_steps=40,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+
+image.save("transparent_example.png")
+```
+
+### Supported Aspect Ratios
+
+```python
+aspect_ratios = {
+    "1:1":  (2048, 2048),
+    "4:3":  (2400, 1792),
+    "3:4":  (1792, 2400),
+    "3:2":  (2528, 1696),
+    "2:3":  (1696, 2528),
+    "16:9": (2752, 1536),
+    "9:16": (1536, 2752),
+}
+```
+
+### Memory Optimization
+
+```python
+pipe = QwenImage21Pipeline.from_pretrained(
+    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
+)
+pipe.enable_model_cpu_offload()
+```
+
+## Showcase
+
+<p align="center">
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-04.png" width="30%"/>
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-05.png" width="30%"/>
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-06.png" width="30%"/>
+</p>
+<p align="center"><em>Native transparent image generation</em></p>
+
+<p align="center">
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-15.png" width="100%"/>
+</p>
+<p align="center"><em>Group photograph generated from six portrait references</em></p>
+
+<p align="center">
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-43.png" width="48%"/>
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-44.png" width="48%"/>
+</p>
+<p align="center"><em>Text rendering</em></p>
+
+## License
+
+This model is licensed under the [Qwen Research License Agreement](https://huggingface.co/Qwen/Qwen-Image-2.1/blob/main/LICENSE).

qwen-image-2.1-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa239e5ddb28d4641942231396d7171da41ad305ea401dd92a7d6410bde798d
+size 14230275808

qwen-image-2.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053e2cf11059e9f5091c03853025b18bc64d18fff4426b1a17da09ed29cc09c9
+size 2466137824

qwen-image-2.1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f688e47c32c033aa8d059c6b7e27d668b2cef0f1dd3d667f97f544954d541238
+size 3168290528

qwen-image-2.1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71af4723442d004b469425ddbdbbf5e4f5f6068c2544cd82d9bb49791b54be3
+size 2724742880

qwen-image-2.1-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef42f3a1b0ccf30be0a068341d383beeea86173e6aa1aa1a33749b337e55e0a9
+size 3612493536

qwen-image-2.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631d532e7ca71e8d90a87c71d3699761a812039d22e3370e87498d87754660fe
+size 4199565024

qwen-image-2.1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328a2b2203ceb45a7f14515fb902c5ec28e9df901d43f49020b4fd251234587f
+size 3906356960

qwen-image-2.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b53321654dd3bf0aa8dd6bb821fdcb1c9053ca735070e359a23cbb9f97268ce
+size 5390223072

qwen-image-2.1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9399e07005c929d2cba313d73f0658e7893219825f29dc609130b75803ea75
+size 4501948128

qwen-image-2.1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ead1ee665e8ebc5fec517d287a167f5c6a7e985acbf3b1b93143437a04616ac
+size 6271551200

qwen-image-2.1-Q6_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9410ad28f20018e7f2f300a06eed7e48db144286d02f0a6d4208d4dbd266691b
+size 6718506720

qwen-image-2.1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ed4b2ffd56cbe9c3df1e4a4098045256484ebe94ba5a7e4338d35ec046baa5
+size 7640860384