<ul><li>The trigger word is 'gwm txxx'.</li><li>Supports generating high-resolution images now!<ul><li>1664×936, 16:9</li><li>1280×960, 4:3</li><li>1024×1024, 1:1</li><li>or other you like</li></ul></li><li>Better scenery and vehicle photography composition.</li><li>Better vehicle details.</li><li>The problem of word pollution is alleviated.</li><li>Recommended params<ul><li>Sampling method: DPM++ 2M SDE Karras</li><li>CFG Scale: 3~5</li><li>Checkpoint: <a target="_blank" rel="ugc" href="https://civarchive.com/models/133005?modelVersionId=240840">Juggernaut XL - V 7 + RunDiffusion | Stable Diffusion Checkpoint | Civitai </a>( Highly Recommended! )</li><li>Prompt:<ul><li>{your description}, ultra detail, Eye-level product film photography, depth of field, shot on 120mm, shot on Hasselblad, Cross Processing Color grading</li><li>{your description}, ultra detail, beautiful, hd, 8k, (photographic:1.5), magnificent, grandiose, macos wallpaper</li></ul></li><li>Negative prompt:<ul><li>collapse, scatter, out of frame, low-res, text, error, cropped, worst quality, low quality, jpeg artifacts, duplicate, wrong proportions, mutation, deformed, blurry, bad anatomy, bad proportions, username, watermark, signature, (low quality, worst quality:1.3)</li></ul></li></ul></li><li>Note: it may appear to collapse more frequently when generating an image resolution of 1664 × 936(or even bigger). We guess the resolution gap between training data and the test leads to this phenomenon(the largest size of our training input is 1360 × 768).</li><li>Any suggestion is appreciated！</li></ul>

Files with SHA256: fc07cea6e84e2db5b6956400225074033c1eb435f7c24f5e4fe77de40f351c86