Go
Home
Pricing
FAQ
Install
Home
Pricing
FAQ
Install
Login
via GitHub
kohya-ss/sd-scripts
Pull Requests
Commits
Open
Closed
Improve resolution bucketing
#2352 opened 2026-05-10 17:32 by
Hirmuolio
feat: Add support for Safetensors format in caching strategies
#2290 opened 2026-03-22 12:19 by
kohya-ss
Make stable validation loss stable and deterministic for Flux when using uncached latents
#2238 opened 2025-11-12 20:16 by
mturnshek
Add fp8 scaling, fp8 scaled convolutions, and gradient checkpointing for Flux AutoEncoder
#2231 opened 2025-10-29 16:31 by
rockerBOO
Add BREAK for captions in strategy_sd
#2223 opened 2025-10-10 19:10 by
rockerBOO
Add non_blocking to loading and moving tensors
#2222 opened 2025-10-10 19:01 by
rockerBOO
CDC-FM (Carré du Champ Flow Matching) Implementation
#2221 opened 2025-10-09 22:25 by
rockerBOO
feat: torch compile within checkpointing and activation memory budget for Lumina 2
#2217 opened 2025-09-30 08:41 by
urlesistiana
Handle icc profiles and images with transparency
#2210 opened 2025-09-27 13:47 by
Hirmuolio
feat: add fp8 optimization for FLUX
#2208 opened 2025-09-25 13:12 by
kohya-ss
Chroma fix t5
#2203 opened 2025-09-20 17:45 by
johnr14
fix: Fix variable reference error in sd-scripts/library/flux_models.py on sd3 branch.
#2188 opened 2025-08-25 02:22 by
Holasyb918
Amazing Flux FFT quality on a 5090: (N)AdamW / Adan with fused backwards pass & CPU offloading
#2187 opened 2025-08-24 15:24 by
araleza
Add MGPO to Flux network
#2180 opened 2025-08-19 06:59 by
rockerBOO
Add support for DoRA and diffusions layer names
#2172 opened 2025-08-10 20:51 by
Reithan
Big image quality improvement! Kahan summation for Adafactor-optimized Flux FFT
#2159 opened 2025-07-23 14:06 by
araleza
Added warning for buckets without enough images to half fill a batch
#2141 opened 2025-07-01 20:45 by
araleza
train_network.py: add debugging print for tensor and gradient norms
#2136 opened 2025-06-28 14:43 by
ddpasa
Add IVON optimizer support
#2129 opened 2025-06-19 17:59 by
rockerBOO
Update tag_images_by_wd14_tagger.py
#2109 opened 2025-06-04 13:26 by
matan2244
Support Cogview4
#2097 opened 2025-05-26 02:04 by
sdbds
Randomized and Incremental Regularization Image Loading - Overhaul of Regularization Image Loading Logic
#2096 opened 2025-05-25 19:37 by
DKnight54
Add Partitioned VAE
#2080 opened 2025-05-08 23:37 by
rockerBOO
Add SDPABackend for SD and SDXL
#2061 opened 2025-04-22 17:52 by
rockerBOO
Added --blocks_to_swap_while_sampling, may allow faster sample image generation
#2056 opened 2025-04-20 10:48 by
araleza
Add AID Activation by Interval-wise Dropout
#2047 opened 2025-04-13 18:08 by
rockerBOO
Add LoRA dropout
#2046 opened 2025-04-13 06:43 by
rockerBOO
Add Flash, cuDNN, Efficient attention for Flux
#2045 opened 2025-04-12 03:23 by
rockerBOO
Add wavelet loss for networks
#2037 opened 2025-04-08 00:05 by
rockerBOO
Add parse blocks to allow setting values per block
#2032 opened 2025-04-05 23:12 by
rockerBOO
Older