Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
2
10
Yulia Yakovleva
robolamp
Follow
edvin3i's profile picture
KennyVechov's profile picture
2 followers
Β·
2 following
robolamp
AI & ML interests
None yet
Recent Activity
reacted
to
MonsterMMORPG
's
post
with π
10 days ago
How to Extract LoRA from FLUX Fine Tuning / DreamBooth Training Full Tutorial and Comparison Between Fine Tuning vs Extraction vs LoRA Training Full article is here public post : https://www.patreon.com/posts/112335162 This was short on length so check out the full article - public post Conclusions as below Conclusions With same training dataset (15 images used), same number of steps (all compared trainings are 150 epoch thus 2250 steps), almost same training duration, Fine Tuning / DreamBooth training of FLUX yields the very best results So yes Fine Tuning is the much better than LoRA training itself Amazing resemblance, quality with least amount of overfitting issue Moreover, extracting a LoRA from Fine Tuned full checkpoint, yields way better results from LoRA training itself Extracting LoRA from full trained checkpoints were yielding way better results in SD 1.5 and SDXL as well Comparison of these 3 is made in Image 5 (check very top of the images to see) 640 Network Dimension (Rank) FP16 LoRA takes 6.1 GB disk space You can also try 128 Network Dimension (Rank) FP16 and different LoRA strengths during inference to make it closer to Fine Tuned model Moreover, you can try Resize LoRA feature of Kohya GUI but hopefully it will be my another research and article later Image Raw Links Image 1 : https://huggingface.co/MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests/resolve/main/Image_1.png Image 2 : https://huggingface.co/MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests/resolve/main/Image_2.jfif Image 3 : https://huggingface.co/MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests/resolve/main/Image_3.jfif Image 4 : https://huggingface.co/MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests/resolve/main/Image_4.jfif Image 5 : https://huggingface.co/MonsterMMORPG/FLUX-Fine-Tuning-Grid-Tests/resolve/main/Image_5.jpg
liked
a model
10 days ago
amd/SD2.1-Nitro
liked
a model
29 days ago
black-forest-labs/FLUX.1-dev
View all activity
Organizations
None yet
robolamp
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
liked
a model
10 days ago
amd/SD2.1-Nitro
Text-to-Image
β’
Updated
Nov 6
β’
53
β’
4
liked
a model
29 days ago
black-forest-labs/FLUX.1-dev
Text-to-Image
β’
Updated
Aug 16
β’
1.33M
β’
β’
7.43k
liked
a model
4 months ago
city96/FLUX.1-dev-gguf
Text-to-Image
β’
Updated
Aug 18
β’
158k
β’
756
liked
3 Spaces
6 months ago
Running
on
CPU Upgrade
69
π
Open LLM Leaderboard
Track, rank and evaluate open LLMs and chatbots
Running
on
CPU Upgrade
12k
π
Open LLM Leaderboard
Track, rank and evaluate open LLMs and chatbots
Running
105
ποΈ
Open-LLM performances are plateauing, letβs make the leaderboard steep again
liked
a model
9 months ago
SamLowe/roberta-base-go_emotions
Text Classification
β’
Updated
Oct 4, 2023
β’
991k
β’
β’
512
liked
a model
about 1 year ago
ostris/ikea-instructions-lora-sdxl
Text-to-Image
β’
Updated
Sep 29, 2023
β’
4.82k
β’
β’
229
liked
a Space
over 1 year ago
Running
on
Zero
146
π
Zeroscope V2
text-to-video
liked
a model
almost 2 years ago
stabilityai/stable-diffusion-2-1
Text-to-Image
β’
Updated
Jul 5, 2023
β’
1.07M
β’
3.91k