You can use the online workflow below. If the results are good, you can then try setting it up and running it locally.<a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/1961068767721754626/?inviteCode=rh-v1013">👉 Click Here For Online WorkFlow</a>As a fan benefit, you’ll receive 1,000 points upon registration, plus 100 points for daily logins. Enjoy a smooth experience with an RTX 4090 and 48GB of VRAM.<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/e1ILfaxSZBE?rel=1" start="0"></iframe></div><h3 id="model-description">Model Description</h3>This is the upgraded version of Kontext Reality Transform, trained on the Qwen Image Edit model, with better results than the original Kontext version! In this version, you can try switching prompts to change the scene of the original image. See the recommended prompts for details. And don't forget the Qwen Image's Chinese characters support.<h3 id="recommended-settings">Recommended Settings</h3><ul><li>Sampler: Euler</li><li>LoRA Weight: 1</li><li>CFG: 1.0 (Using the <span style="background-color:rgb(255, 255, 255);color:rgb(37, 38, 43);font-family:&quot;Source Sans Pro&quot;, ui-sans-serif, system-ui, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;, &quot;Noto Color Emoji&quot;;font-size:medium">Qwen-Image-Lightning-8steps-V1.1 , acceleration LoRA weight 1.0)</li><li>Steps: 8</li><li>Recommended to use high-resolution upscale: 1.5× scale. Denoising set to 0.4. Beta scheduler is recommended, with 8 steps, CFG 1.0, using the <span style="background-color:rgb(255, 255, 255);color:rgb(37, 38, 43);font-family:&quot;Source Sans Pro&quot;, ui-sans-serif, system-ui, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;, &quot;Noto Color Emoji&quot;;font-size:medium">Qwen-Image-Lightning-8steps-V1.1, acceleration LoRA weight 0.5.</li></ul><h3 id="recommended-prompt">Recommended Prompt</h3>Trigger Word：transform into realistic photographyOther Prompts：<ol><li>transform into realistic photography, The background is set next to an everyday shopping street.</li><li>transform into realistic photography, change the background to a Japanese anime comiket convention, with a sparse crowd of japanese otaku and various japanese male and female cosplayers walking towards various directions in the background.They are wearing various anime costumes from different manga and anime,they are unware of the viewer, the lighting is natural indoor lighting without flashlight</li><li>(Use your imagination)</li></ol><h3>模型介绍</h3>这是此前发布的Kontext Reality Transform的升级版本，基于Qwen Image Edit模型训练，效果比Kontext版更好！此版本可以尝试切换提示词来更改原图的场景，详见提示词推荐。同时不要忘了Qwen Image系列的中文支持。<h3>推荐设置</h3><ul><li>采样器: Euler</li><li>LoRA 权重: 1</li><li>CFG: 1.0 （使用 <span style="background-color:rgb(255, 255, 255);color:rgb(37, 38, 43);font-family:&quot;Source Sans Pro&quot;, ui-sans-serif, system-ui, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;, &quot;Noto Color Emoji&quot;;font-size:medium">Qwen-Image-Lightning-8steps-V1.1 , 加速LoRA权重1.0)</li><li>步数: 8</li><li>推荐使用高清放大: 1.5倍. 降噪 0.4. Beta 调度器, 8步, CFG 1.0, 使用 <span style="background-color:rgb(255, 255, 255);color:rgb(37, 38, 43);font-family:&quot;Source Sans Pro&quot;, ui-sans-serif, system-ui, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;, &quot;Noto Color Emoji&quot;;font-size:medium">Qwen-Image-Lightning-8steps-V1.1, 加速LoRA权重0.5</li></ul><h3>推荐提示词</h3>触发词：transform into realistic photography其他提示词：<ol><li>transform into realistic photography, The background is set next to an everyday shopping street.</li><li>transform into realistic photography, change the background to a Japanese anime comiket convention, with a sparse crowd of japanese otaku and various japanese male and female cosplayers walking towards various directions in the background.They are wearing various anime costumes from different manga and anime,they are unware of the viewer, the lighting is natural indoor lighting without flashlight</li><li>(发挥你的想象)</li></ol>

Qwen Edit Reality Transform By Aldniki

aldniki_qwen_reality_transform_v01.safetensors

v1.0

HideYou can use the online workflow below. If the results are good, you can then try setting it up and running it locally.<a href="https://www.runninghub.ai/post/1961068767721754626/?inviteCode=rh-v1013" rel="ugc noopener noreferrer nofollow" target="_blank">👉 Click Here For Online WorkFlow</a>As a fan benefit, you’ll receive 1,000 points upon registration, plus 100 points for daily logins. Enjoy a smooth experience with an RTX 4090 and 48GB of VRAM.Model DescriptionThis is the upgraded version of Kontext Reality Transform, trained on the Qwen Image Edit model, with better results than the original Kontext version! In this version, you can try switching prompts to change the scene of the original image. See the recommended prompts for details. And don't forget the Qwen Image's Chinese characters support.Recommended Settings<ul><li>Sampler: Euler</li><li>LoRA Weight: 1</li><li>CFG: 1.0 (Using the Qwen-Image-Lightning-8steps-V1.1 , acceleration LoRA weight 1.0)</li><li>Steps: 8</li><li>Recommended to use high-resolution upscale:&nbsp;1.5× scale. Denoising set to 0.4. Beta scheduler is recommended, with 8 steps, CFG 1.0, using the Qwen-Image-Lightning-8steps-V1.1, acceleration LoRA weight 0.5.</li></ul>Recommended PromptTrigger Word：transform into realistic photographyOther Prompts：<ol><li>transform into realistic photography, The background is set next to an everyday shopping street.</li><li>transform into realistic photography, change the background to a Japanese anime comiket convention, with a sparse crowd of japanese otaku and various japanese male and female cosplayers walking towards various directions in the background.They are wearing various anime costumes from different manga and anime,they are unware of the viewer, the lighting is natural indoor lighting without flashlight</li><li>(Use your imagination)</li></ol>模型介绍这是此前发布的Kontext Reality Transform的升级版本，基于Qwen Image Edit模型训练，效果比Kontext版更好！此版本可以尝试切换提示词来更改原图的场景，详见提示词推荐。同时不要忘了Qwen Image系列的中文支持。推荐设置<ul><li>采样器: Euler</li><li>LoRA 权重: 1</li><li>CFG: 1.0 （使用 Qwen-Image-Lightning-8steps-V1.1 , 加速LoRA权重1.0)</li><li>步数: 8</li><li>推荐使用高清放大: 1.5倍. 降噪 0.4. Beta 调度器, 8步, CFG 1.0, 使用 Qwen-Image-Lightning-8steps-V1.1, 加速LoRA权重0.5</li></ul>推荐提示词触发词：transform into realistic photography其他提示词：<ol><li>transform into realistic photography, The background is set next to an everyday shopping street.</li><li>transform into realistic photography, change the background to a Japanese anime comiket convention, with a sparse crowd of japanese otaku and various japanese male and female cosplayers walking towards various directions in the background.They are wearing various anime costumes from different manga and anime,they are unware of the viewer, the lighting is natural indoor lighting without flashlight</li><li>(发挥你的想象)</li></ol>

Files with SHA256: f9d7c2c1e4b5edfbfacf5841eaf117bd933558dd44072a76a3eb0029abd2d7ed