左边是不使用 Lora 的效果,默认就是欧美人的形象,右边是使用了 Lora 的效果,默认是偏向亚洲人脸的。 提示词:A memorable movie photo taken by Antoine Verney Carron captures a young Asian woman with charming curves, making her a masterpiece. Shot on Fujicolor C200 film using side lighting and a 50...
Search or jump to... Search code, repositories, users, issues, pull requests... Provide feedback We read every piece of feedback, and take your input very seriously. Include my email address so I can be contacted Cancel Submit feedback Saved searches Use saved searches to filter your...
1、a model with dark skin wearing white boots and an off shoulder black rose print dress walks on the runway, full body shot from head to toe, high heels, long legs, clean background, show photography, soft light, gray concrete floor, black roses, black choker necklace, white leather glo...
Fill and back colors must be perfectly white and black (#FFFFFF, #000000) for the source_qr. The canvas can be bigger than the QR code, but on the source_qr, there should be no pixels the same color as the module color outside of the QR exterior. Inputs source_qr - The original...
white = ((image[..., 0] >= 1-threshold_r) & (image[..., 1] >= 1-threshold_g) & (image[..., 2] >= 1-threshold_b)).float() return (red, green, blue, cyan, magenta, yellow, black, white,) class TransitionMask: @classmethod def INPUT_TYPES(s): return { "requ...
"Standard": "lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, disfigured, username, watermark, signature, backgound out of focus, black and white,...
The blackpoint and whitepoint options in some nodes have been changed to slider adjustment for a more intuitive display. Include MaskEdgeUltraDetailV2, SegmentAnythingUltraV2, RmBgUltraV2,PersonMaskUltraV2,BiRefNetUltra, SegformerB2ClothesUltra, BlendIfMask and Levels. ImageScaleRestoreV2 and ImageSca...
"Standard": "lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, disfigured, username, watermark, signature, backgound out of focus, black and white,...
color='white', fontsize=12, bbox=dict(facecolor=facecolor, alpha=0.5) ) if fill_mask: mask_tensor = F.to_tensor(mask_layer) mask_tensor = mask_tensor.unsqueeze(0).permute(0, 2, 3, 1).cpu().float() mask_tensor = mask_tensor.mean(dim=0, keepdim=True) ...
A woman is posing for a photo. She has blonde hair and is wearing bunny ears. She is also wearing white stockings and a white t-shirt. She also has black shorts. She appears to be sitting on her knees. Behind her is a long table with two cups on it., ...