SD3.5 Large + Google FLAN

CHECKPOINT
Reprint


Updated:

Full Checkpoint with improved TE do not load additional CLIP/TE

SD3.5 Large with FLAN improved TE

  • The Full BF16 model runs at an amazing speed even on my 8GB card. It was built with Triple Clip using the 42GB Google FLAN T5xxl 12B parameter model (Converted to BF16), CLIP-G and improved CLIP-L

  • The Full FP16 model runs at half the speed of the BF16 version, on my card but may have better accuracy.

  • Do not use negatives above 0.2 timestamp - If you do not understand this line load any image as a workflow. (The same instructions as base SD 3.5)

  • If you have a 8GB card I suggest the Medium Model with FLAN it is still about several times faster then the BF16 FLAN model on my RTX 3050 (1.5 seconds per IT vs 5-6 Seconds Per IT for the 26GB model)

Works in Comfy-UI without any modification just load checkpoint and go.

Per the Apache 2.0 license FLAN is attributed to Google

My IT's per Second on an old 3050 8GB RTX

SD 3.5 Large (Triple CLIP FP8)

13.5GB = 6-8 Seconds Per IT

22GB Hybrid = 6-8 Seconds Per IT

26GB (BF16 FULL) = 5-6 Seconds per IT (BF16 seems to be faster for 1bit less precision but wider range I think it is worth it)

26GB (FP16 FULL) = 8-16 Seconds per IT (FP16 seem to have erratic IT/s compared to BF16)

The model deployment is abnormal, please re-upload/contact customer service.

Version Detail

SD 3.5 Large
100000
100

Project Permissions

Model reprinted from : https://civitai.com/models/882666/sd35-large-google-flan?modelVersionId=1003031

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

No posts yet