Trained using twenty 512x512 paintings by Hals, all of which are portraits, mostly of one single individual. There is definitely a lack of diversity there.This is Epoch 10, the rest can be found here: tensor. art/models/806925772804811440/Frans-Hals-V2-NoCapD6A6cos5-2024-12-14-00:54:26-Ep-10FLUX.1 - dev-fp8Trigger: fraha1 paintingRepeat: 20 Epoch 10 (* 20 10 20)=4000 total stepsUnet LR: 0.0005 Scheduler: cosine Optimizer: AdamWNetwork Dim: 6 Alpha: 3Epoch Loss1 0.3742 0.3573 0.3484 0.3435 0.3376 0.3247 0.3108 0.3089 0.30010 0.285 <- lowest
Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Idle
Unknown content type
Related Models
Discover similar models you might be interested in
Sausage Dishes - White Sausage-Dev v1.0
Most Important Places - Thank You Special - Thank You Special v1
Sanai Mahbub Viral Style - v1.0
Ferrari SF90 XX Stradale - 2024 - v1.0 FLUX
Sergey Kolesov - V1
Thomas Blackshear - V1
Mgrt03 - V1
Ashley Wood - V1
fantasy-tree - v1.0
Ringbrothers Octavia - 2025 - v1.0 FLUX
Flux Waifu Enhancer - v1.0
Taste of Taiwan - Oyster Thin Noodles v1.0