特困生 发表于 2026-2-28 21:01:26

meiyouruguo 发表于 2026-2-28 20:53
偶尔会发生, 模型有时候不识别提示词

好的，收到

coolkyanyi 发表于 2026-3-12 10:19:37

存符石，能貸款嗎？哈哈

woshihaha 发表于 2026-3-14 18:17:32

jandown 发表于 2026-1-13 10:15
建议加个香蕉的api，比开源的qwen-edit 效果要好很多

香蕉收费啊

z445726864 发表于 2026-3-16 13:23:57

零食不够，发帖慢慢攒

o4andv1 发表于 2026-3-16 17:14:35

最低多少G显存用

meiyouruguo 发表于 2026-3-16 17:25:23

o4andv1 发表于 2026-3-16 17:14
最低多少G显存用

12G勉强可以,16G推荐

z445726864 发表于 2026-3-16 20:34:02

meiyouruguo 发表于 2026-3-16 17:25
12G勉强可以,16G推荐

我507012G49张差不多个把小时。。效果不错

o4andv1 发表于 2026-3-25 12:14:16

Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Requested to load WanVAE
loaded completely; 7449.00 MB usable, 242.03 MB loaded, full load: True
Found quantization metadata version 1
Using MixedPrecisionOps for text encoder
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load QwenImageTEModel_
loaded completely; 9581.80 MB usable, 7910.28 MB loaded, full load: True
Requested to load WanVAE
Unloaded partially: 3633.28 MB freed, 4277.00 MB remains loaded, 453.25 MB buffer reserved, lowvram patches: 0
loaded completely; 3104.87 MB usable, 242.03 MB loaded, full load: True
loaded completely; 9320.65 MB usable, 7910.28 MB loaded, full load: True
model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
model_type FLUX
got prompt


处理出错

ryan1944 发表于 2026-3-26 01:05:30

很棒的素材生成工具:handshake

mukdswzdkum 发表于 2026-3-26 17:43:34

处理出错,恳请大佬帮解~感谢您
页: 1 2 3 4 [5]
查看完整版本: DFL多角度素材生成工具