v8.0：增强了写实风格v8.0: Enhanced the photorealistic style3.0所有示例图片都是ComfyUI默认工作流直出没有放大和修正参数为：3.0 All sample images are ComfyUI default workflows straight out without enlargement and correctionThe parameters are:分辨率：1024 x 1536采样器：EulerSteps: 25, CFG scale: 5,832 x 1216采样方法 (Sampler)：Euler a迭代步数 (Steps)：28CFG：7.5masterpiece, best quality, very aesthetic, latest,worst quality, low quality, jpeg artifacts, 3d, multiple views, 4koma, bad anatomy, bad hands, text,<h3 id="4illustriousxllora-l4fgzk5zp">使用了4个illustriousXL模型进行融合并融入了自己训练的Lora</h3><h3 id="-y7h5cnr6o">合并的模型分别是：</h3><h3 id="four-illustriousxl-models-were-used-to-fuse-and-incorporate-lora-which-was-trained-by-itself-rmgqrhpfa">Four illustriousXL models were used to fuse and incorporate Lora, which was trained by itself</h3><h3 id="the-merged-models-are:-vfmd3rnze">The merged models are:</h3><h1 id="illustrious-xl-a2pfumlpj"><a target="_blank" rel="ugc" href="https://civarchive.com/models/795765?modelVersionId=889818">Illustrious-XL</a></h1><h1 id="pasanctuary-(sdxl-illustriousxl)-6yxfx7miv"><a target="_blank" rel="ugc" href="https://civarchive.com/models/835578/pasanctuary-sdxl-illustriousxl?modelVersionId=934850">PaSanctuary (SDXL, IllustriousXL)</a></h1><h1 id="illustrious-xl-smoothft-hrvs538nu"><a target="_blank" rel="ugc" href="https://civarchive.com/models/811067/illustrious-xl-smoothft?modelVersionId=907264">Illustrious-XL SmoothFT</a></h1><h1 id="illustrious_pencil-xl-5n3kr9fba"><a target="_blank" rel="ugc" href="https://civarchive.com/models/838773/illustriouspencil-xl?modelVersionId=951879">illustrious_pencil-XL</a></h1>

illustriousXL_MMMix

illustriousxlMmmix_v65.safetensors

v6.5

v8.0

v7.0

v6.0

v5.0

v4.0

v3.0

v2.0

v1.0

REPRINTCheck version detail section for description

illustriousXL_MMMix
Pruned Model fp16 (6.46 GB)

3.0 All sample images are ComfyUI default workflows straight out without enlargement and correction

The parameters are:
1040 x 1520
Euler a
Steps: 30, CFG scale: 8,
masterpiece, best quality, very aesthetic, latest,
worst quality, low quality, jpeg artifacts, 3d, multiple views, 4koma, bad anatomy, bad hands, text,

Four illustriousXL models were used to fuse and incorporate Lora, which was trained by itself

The merged models are:
Illustrious-XL
PaSanctuary (SDXL, IllustriousXL)
Illustrious-XL SmoothFT
illustrious_pencil-XL


illustriousXL MMMix

V6.5

Files with SHA256: c93e847288cfcf9e3d9108f65ab9b5d762d648ca14dea6ce7d4eaf5ea003addc