Search Results
8/8/2025, 12:26:35 PM
8/8/2025, 12:20:05 PM
Well I did some moar testing on this FP32 CLIP.
Seems to have potential imo. There is also another FP32 Illustrious CLIP floating around that I want to get around to testing.
Not shown here, I have tested another FP16 CLIP, which seems to have exhibited behavior more similar to the FP16 CLIP inside the model(don't have a huge experiment sample size for that, admittedly).
While whatever "restoration" this guy did also has a significant effect on quality most probably, I believe that the text encoder benefits from FP32 precision. Further evidenced by the change seen here when loading FP32 CLIP as FP16>>106187649. (Conversely, the image also changes when you load the FP16 CLIP as FP32, not necessarily for the better or worse though)
Seems to have potential imo. There is also another FP32 Illustrious CLIP floating around that I want to get around to testing.
Not shown here, I have tested another FP16 CLIP, which seems to have exhibited behavior more similar to the FP16 CLIP inside the model(don't have a huge experiment sample size for that, admittedly).
While whatever "restoration" this guy did also has a significant effect on quality most probably, I believe that the text encoder benefits from FP32 precision. Further evidenced by the change seen here when loading FP32 CLIP as FP16>>106187649. (Conversely, the image also changes when you load the FP16 CLIP as FP32, not necessarily for the better or worse though)
Page 1