--- title: QwenImageEdit2511_LoRA canonical_url: "https://www.modelscope.cn/models/tori29umai/QwenImageEdit2511_LoRA" md_url: "https://www.modelscope.cn/models/tori29umai/QwenImageEdit2511_LoRA.md" repository: tori29umai/QwenImageEdit2511_LoRA last_updated: 2026-06-26 license: apache-2.0 pipeline_tag: image-to-image tasks: - image-to-image base_model: - Qwen/Qwen-Image-Edit base_model_relation: adapter parameters: 184.0M tensor_type: - BF16 library_name: - lora - safetensors - pytorch frameworks: - pytorch language: - ja - en supports_inference: img2img downloads: 133 stars: 2 tags: - lora - qwen-image-edit - image-to-image --- # QwenImageEdit2511_LoRA > QwenImageEdit2511_LoRA - tori29umai 在 ModelScope 开源的模型。QwenImageEdit2511 LoRA Collection tori29umai/QwenImageEdit2511_LoRA 是 ModelScope 魔搭社区上的 184.0M 参数image-to-image模型，采用 apache-2.0 许可，基于 Qwen/Qwen-Image-Edit 构建，并支持在线推理（img2img）。 - **Repository**: tori29umai/QwenImageEdit2511_LoRA - **License**: apache-2.0 - **Tasks**: image-to-image - **Parameters**: 184.0M - **Base model**: Qwen/Qwen-Image-Edit - **Online inference**: img2img - **Tags**: lora, qwen-image-edit, image-to-image - **Downloads**: 133 - **Stars**: 2 - **Last updated**: 2026-06-26 Source: https://www.modelscope.cn/models/tori29umai/QwenImageEdit2511_LoRA --- # QwenImageEdit2511 LoRA Collection **言語 / Language**: [日本語](#日本語) | [English](#english) --- ## 日本語 ### 概要 [Qwen-Image-Edit (2511 リビジョン)](https://huggingface.co/Qwen/Qwen-Image-Edit) 用に学習・派生させた LoRA のコレクションです。 キャラクター変換、オブジェクト抽出、画風変換、吹き出し除去などの自作 LoRA に加え、サードパーティの公開 LoRA を SVD で低ランク (`dim`) に再エンコードしたものを含みます。 ### 動作環境 - ベースモデル: Qwen-Image-Edit (2511 リビジョン) - 推論フレームワーク: ComfyUI / Diffusers など LoRA 対応のもの - 形式: kohya / musubi-tuner LoRA フォーマット (safetensors / bf16) ### 含まれる LoRA #### 自作 LoRA ##### `QIE2511_3Dpose2Chara_V14_dim1_1e-3-000120.safetensors` 3D ポーズ画像 (Image 2) を参照ポーズとし、Image 1 のキャラクターで完全に置き換える LoRA。Image 1 の絵柄・顔・髪型・衣装を保ったまま、Image 2 のポーズ・構図・表情を取り込みます。 プロンプト: ```text Use Image 2 as a reference for pose, composition, and facial expression, loosely following its pose, gesture, camera angle, framing, and expression, then replace the character entirely with the character from Image 1, applying the art style, facial features, hairstyle, and outfit design of Image 1, ensuring the final image looks like the character from Image 1 inspired by the pose and expression of Image 2. ``` ##### `QIE2511_3Dpose2Chara_faceless_V3_dim1_1e-3-000120.safetensors` 上記の "faceless" 版。完全にのっぺらぼう（目・鼻・口・眉なし）のキャラクターを生成します。 プロンプト: ```text Use Image 2 as a reference for pose and composition, following its pose, gesture, camera angle, and framing. Replace the character entirely with the character design from Image 1, applying only the hairstyle, outfit design, color palette, and overall art style of Image 1. The character should have a completely blank, featureless face (no eyes, nose, mouth, eyebrows, or facial details), creating a smooth faceless appearance. ``` ##### `QIE2511_ObjectExtraction_V10_dim1_1e-3-000120.safetensors` 単色のマスク（色は自由、原色がおすすめ）で覆われた領域を再構築し、白背景で出力する LoRA。元のオブジェクトの輪郭・比率・素材感を維持しつつ、マスクで隠れた部分を補完します。 プロンプト: ```text From picture1, extract only the main object itself and remove everything else. This means removing not just the background, but also any objects in the foreground that obscure or appear in front of the main object, all shadows the object casts onto surfaces, any ground shadows or reflections, and any surrounding artifacts or context. Keep the object's natural surface details, textures, and the shading that defines its form, but eliminate all external shadows, reflections, and foreground obstructions. The result should be a clean cutout of just the main object on a pure white background, looking as though it was photographed in complete isolation without any environmental lighting effects. ``` ##### `QIE2511_ObjectRemove_V3_dim1_1e-3-000030.safetensors` マスクされたオブジェクトを完全に削除し、周囲の背景の質感・色・模様を自然に延長して欠損部分を補完する LoRA。マスクされたオブジェクトの背後にある人物や物体などの要素は保持・復元し、完全に見えるようにします。最終結果は、マスクされたオブジェクトが最初から存在しなかったかのように見える必要があります。痕跡、輪郭、新しい物体は残さず、既存の背景のみを連続させます。 プロンプト: ```text Completely remove the masked object. Fill the area using only the background by extending surrounding textures, colors, and patterns. Preserve any elements behind the masked object, such as people or objects, ensuring they are fully visible. The result should look as if the masked object never existed. No traces, outlines, or new objects. Only continue the existing background. ``` ##### `QIE2511_image2rakugaki_V3_dim1_1e-3-000020.safetensors` 詳細な画像をフラットで抽象的な落書き調に変換する LoRA。線・細部を削除し、色と光のバランスで形を表現します。 プロンプト: ```text Convert a detailed image into a flat abstract style using large, smooth color areas. Remove all lines and details, letting shapes blend softly. Focus on color and light balance rather than form accuracy ``` ##### `QIE2511_FukidashiErase_V1_dim4_1e-3-000080_dim1.safetensors` マンガの手書き文字、吹き出し内のテキスト、および吹き出し自体の線を消去し、背景として自然に再描画する LoRA。キャラクターの線画・表情・ポーズはそのまま保持します。 プロンプト: ```text Remove the text and dialogue inside the speech bubbles of a manga illustration. Do not preserve the outlines of the speech bubbles; instead, redraw the area naturally as background. Do not alter the character's line art, facial expression, or pose in any way. ``` #### 派生 LoRA (dim 削減版) ##### `collage_qwenedit_lora_V1_dim1.safetensors` 元: [do9/collage_lora_qwenedit](https://huggingface.co/do9/collage_lora_qwenedit) を SVD で **dim=1** に削減したもの。 使い方・プロンプトは元リポジトリを参照してください。 ##### `Qwen-Image-Edit-2511-Object-Remover_dim1.safetensors` 元: [prithivMLmods/Qwen-Image-Edit-2511-Object-Remover](https://huggingface.co/prithivMLmods/Qwen-Image-Edit-2511-Object-Remover) を SVD で **dim=1** に削減したもの。 使い方・プロンプトは元リポジトリを参照してください。 ##### `QIE2511_Gaussian-Splash-Sharp_dim1.safetensors` 元: [dx8152/Qwen-Image-Edit-2511-Gaussian-Splash](https://huggingface.co/dx8152/Qwen-Image-Edit-2511-Gaussian-Splash) を SVD で **dim=1** に削減したもの。Gaussian-Splash-Sharp の dim1 版です。 ##### `QIE2511_Gaussian-Splash-Sharp_dim1.safetensors` Based on / source LoRA: [dx8152/Qwen-Image-Edit-2511-Gaussian-Splash](https://huggingface.co/dx8152/Qwen-Image-Edit-2511-Gaussian-Splash), SVD-reduced to **dim=1**. ##### `qwen-image-edit-2511-multiple-angles-lora_dim1.safetensors` 元: [fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA](https://huggingface.co/fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA) を SVD で **dim=1** に削減したもの。 使い方・プロンプトは元リポジトリを参照してください。 ##### `Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16_dim{1,4,8}.safetensors` 元: [lightx2v/Qwen-Image-Edit-2511-Lightning](https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning) を SVD でそれぞれ **dim=1 / 4 / 8** に削減した Lightning (4-step 加速) LoRA。 使い方は元リポジトリを参照してください。 ### dim 削減について 派生 LoRA はすべて SVD ベースのランク削減を行っており、`multiplier=1.0` で適用したときに元 LoRA の最良低ランク近似が再現されるよう調整しています。低 dim ほどメモリ・速度面で軽量になりますが、品質は元 LoRA より若干低下する場合があります。 ### ライセンス・クレジット - 自作 LoRA: Apache-2.0 (ベースモデルに準拠)。 - 派生 LoRA: 元リポジトリのライセンスに従ってください。 - ベースモデル: [Qwen/Qwen-Image-Edit](https://huggingface.co/Qwen/Qwen-Image-Edit) (Apache-2.0) --- ## English ### Overview A LoRA collection for [Qwen-Image-Edit (2511 revision)](https://huggingface.co/Qwen/Qwen-Image-Edit). It includes self-trained LoRAs for character transfer, object extraction, art-style conversion, and speech-bubble removal, plus SVD-based low-rank (`dim`) re-encodings of third-party public LoRAs. ### Requirements - Base model: Qwen-Image-Edit (2511 revision) - Inference framework: ComfyUI / Diffusers, or any LoRA-capable runtime - Format: kohya / musubi-tuner LoRA (safetensors / bf16) ### Included LoRAs #### Original LoRAs ##### `QIE2511_3Dpose2Chara_V14_dim1_1e-3-000120.safetensors` Uses a 3D pose image (Image 2) as a reference and fully replaces the character with the one in Image 1. Image 1's art style, facial features, hairstyle, and outfit are preserved while Image 2's pose, composition, and expression are inherited. Prompt: ```text Use Image 2 as a reference for pose, composition, and facial expression, loosely following its pose, gesture, camera angle, framing, and expression, then replace the character entirely with the character from Image 1, applying the art style, facial features, hairstyle, and outfit design of Image 1, ensuring the final image looks like the character from Image 1 inspired by the pose and expression of Image 2. ``` ##### `QIE2511_3Dpose2Chara_faceless_V3_dim1_1e-3-000120.safetensors` Faceless variant of the above — the generated character has a completely blank, featureless face (no eyes, nose, mouth, or eyebrows). Prompt: ```text Use Image 2 as a reference for pose and composition, following its pose, gesture, camera angle, and framing. Replace the character entirely with the character design from Image 1, applying only the hairstyle, outfit design, color palette, and overall art style of Image 1. The character should have a completely blank, featureless face (no eyes, nose, mouth, eyebrows, or facial details), creating a smooth faceless appearance. ``` ##### `QIE2511_ObjectExtraction_V10_dim1_1e-3-000120.safetensors` From picture1, extract only the main object itself and remove everything else. This means removing not just the background, but also any objects in the foreground that obscure or appear in front of the main object, all shadows the object casts onto surfaces, any ground shadows or reflections, and any surrounding artifacts or context. Keep the object's natural surface details, textures, and the shading that defines its form, but eliminate all external shadows, reflections, and foreground obstructions. The result should be a clean cutout of just the main object on a pure white background, looking as though it was photographed in complete isolation without any environmental lighting effects. Prompt: ```text Remove or reconstruct the areas covered by the semi-transparent pink mask Reconstruct any missing parts of the object that were hidden by the mask by inferring the original shape structure material texture color and design Preserve the object's outline proportions details and overall style consistency with strict accuracy Rebuild the object as a continuous structure without broken lines or distorted geometry Set the background to white ``` ##### `QIE2511_ObjectRemove_V3_dim1_1e-3-000030.safetensors` Completely removes the masked object and fills the missing area by naturally extending the surrounding background textures, colors, and patterns. Elements behind the masked object, such as people or objects, are preserved or restored so they remain fully visible. The result should look as if the masked object never existed, with no traces, outlines, or newly introduced objects. Only the existing background is continued. Prompt: ```text Completely remove the masked object. Fill the area using only the background by extending surrounding textures, colors, and patterns. Preserve any elements behind the masked object, such as people or objects, ensuring they are fully visible. The result should look as if the masked object never existed. No traces, outlines, or new objects. Only continue the existing background. ``` ##### `QIE2511_image2rakugaki_V3_dim1_1e-3-000020.safetensors` Converts a detailed image into a flat, abstract doodle-like style. Lines and fine detail are removed; shape is expressed through color and light balance. Prompt: ```text Convert a detailed image into a flat abstract style using large, smooth color areas. Remove all lines and details, letting shapes blend softly. Focus on color and light balance rather than form accuracy ``` ##### `QIE2511_FukidashiErase_V1_dim4_1e-3-000080_dim1.safetensors` Removes both the text inside manga speech bubbles AND the bubble outlines themselves, naturally redrawing the area as background. The character's line art, facial expression, and pose are preserved. Prompt: ```text Remove the text and dialogue inside the speech bubbles of a manga illustration. Do not preserve the outlines of the speech bubbles; instead, redraw the area naturally as background. Do not alter the character's line art, facial expression, or pose in any way. ``` #### Derivative LoRAs (rank-reduced) ##### `collage_qwenedit_lora_V1_dim1.safetensors` Source: [do9/collage_lora_qwenedit](https://huggingface.co/do9/collage_lora_qwenedit), SVD-reduced to **dim=1**. See the source repository for usage and prompt instructions. ##### `Qwen-Image-Edit-2511-Object-Remover_dim1.safetensors` Source: [prithivMLmods/Qwen-Image-Edit-2511-Object-Remover](https://huggingface.co/prithivMLmods/Qwen-Image-Edit-2511-Object-Remover), SVD-reduced to **dim=1**. See the source repository for usage and prompt instructions. ##### `qwen-image-edit-2511-multiple-angles-lora_dim1.safetensors` Source: [fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA](https://huggingface.co/fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA), SVD-reduced to **dim=1**. See the source repository for usage and prompt instructions. ##### `Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16_dim{1,4,8}.safetensors` Source: [lightx2v/Qwen-Image-Edit-2511-Lightning](https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning), SVD-reduced to **dim=1 / 4 / 8** respectively (Lightning 4-step acceleration LoRA). See the source repository for usage instructions. ### Notes on Dim Reduction All derivative LoRAs were rank-reduced via SVD, tuned so that applying them at `multiplier=1.0` reproduces the best low-rank approximation of the original. Lower-dim versions are lighter on memory and faster, but may show a slight quality drop compared to the original. ### License & Credits - Original LoRAs: Apache-2.0 (matching the base model). - Derivative LoRAs: follow the license of their source repositories. - Base model: [Qwen/Qwen-Image-Edit](https://huggingface.co/Qwen/Qwen-Image-Edit) (Apache-2.0).