Sign In

SD 3.5 Medium + Google FLAN

112

2.7k

31

Updated: Nov 9, 2024

base modelgoogleflan3.5

Verified:

SafeTensor

Type

Checkpoint Merge

Stats

2,042

0

Reviews

Published

Oct 29, 2024

Base Model

SD 3.5 Medium

Training

Steps: 100,000
Epochs: 100

Hash

AutoV2
41934CB384
SDXL Training Contest Participant
Felldude's Avatar

Felldude

This Stability AI Model is licensed under the Stability AI Community License, Copyright (c) Stability AI Ltd. All Rights Reserved.

Powered by Stability AI

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

SD 3.5 Medium + Google FLAN

  • Update your Comfy UI before using(10/29/2024)

  • FP16 merge with Google FLAN (From FP32)

  • SGM Uniform with Dpmpp_2M at 40 Steps or Euler Normal/Simple at 20 steps working well

  • 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)

  • I posted a FP8 version but even with a 8GB card I do not see an improvement in speed so I still recommend the FP16 (NF4 support in Forge would be great)

In my testing on a low VRAM card this model runs several times faster then the Large Model

Per the Apache 2.0 license FLAN is attributed to Google