jaidaken/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Refactor: move clip_preprocess to comfy.clip_model (#11586)

Browse Source
This commit is contained in:
comfyanonymous
2025-12-31 14:38:36 -08:00
committed by GitHub
parent 236b9e211d
commit d622a61874
2 changed files with 21 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
comfy/clip_model.py
View File

@@ -2,6 +2,25 @@ import torch
from comfy.ldm.modules.attention import optimized_attention_for_device
import comfy.ops
def clip_preprocess(image, size=224, mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711], crop=True):
image = image[:, :, :, :3] if image.shape[3] > 3 else image
mean = torch.tensor(mean, device=image.device, dtype=image.dtype)
std = torch.tensor(std, device=image.device, dtype=image.dtype)
image = image.movedim(-1, 1)
if not (image.shape[2] == size and image.shape[3] == size):
if crop:
scale = (size / min(image.shape[2], image.shape[3]))
scale_size = (round(scale * image.shape[2]), round(scale * image.shape[3]))
else:
scale_size = (size, size)
image = torch.nn.functional.interpolate(image, size=scale_size, mode="bicubic", antialias=True)
h = (image.shape[2] - size)//2
w = (image.shape[3] - size)//2
image = image[:,:,h:h+size,w:w+size]
image = torch.clip((255. * image), 0, 255).round() / 255.0
return (image - mean.view([3,1,1])) / std.view([3,1,1])
class CLIPAttention(torch.nn.Module):
def __init__(self, embed_dim, heads, dtype, device, operations):
super().__init__()