Jaret Burkett e72468b456 Added initial support for fine tuning and captioning with Qwen 3.8 27B

2026-10-18 12:25:28 -06:00

..

band_loss.svg

Added experimental band loss

2026-10-15 08:26:12 -06:00

blended_blur_noise.py

Various experiments and minor bug fixes for edge cases

2025-04-25 13:44:38 -06:00

comfy_quant_export.py

Phase 2

2026-08-27 15:37:13 -06:00

comfy_quant_import.py

Added initial support for fine tuning and captioning with Qwen 3.8 27B

2026-10-18 12:25:28 -06:00

convrot_quant.py

Added initial support for fine tuning and captioning with Qwen 3.8 27B

2026-10-18 12:25:28 -06:00

convrot_w4a8_quant.py

Added initial support for fine tuning and captioning with Qwen 3.8 27B

2026-10-18 12:25:28 -06:00

float8_quant.py

Phase 2

2026-08-27 15:37:13 -06:00

get_model.py

Phase 2

2026-08-27 18:18:31 -06:00

inverse_cfg.py

Small tweaks and fixes for specialized ip adapter training

2024-03-26 11:35:26 -06:00

ip_adapter_utils.py

Remove ip adapter submodule

2025-04-18 09:59:42 -06:00

losses.py

Added experimental band loss

2026-10-15 08:26:12 -06:00

mask.py

Added mask diffirential mask dialation for flex2. Handle video for the i2v adapter

2025-04-10 11:50:01 -06:00

mixed_precision.py

Fix issue with ltx caching

2026-08-30 11:01:52 -06:00

nvfp4_quant.py

Phase 2

2026-08-27 15:37:13 -06:00

orbit_quant.py

Fix casting issue with orbit quant

2026-07-10 10:23:38 -06:00

orbit_vq_quant.py

Added experimental orbit quant

2026-07-09 15:14:51 -06:00

ostris_quant.py

Phase 2

2026-08-27 15:37:13 -06:00

quantize.py

Stability improvements to model offloading. Added D-OPSD bleed loss as well.

2026-08-29 11:23:47 -06:00

qwen_vae_gradient_checkpointing.py

Fix issue with qwen image edit models.

2026-07-17 09:14:04 -06:00

shuffle.py

Various experiments and minor bug fixes for edge cases

2025-04-25 13:44:38 -06:00

streamed_safetensors.py

Load sage sheet and use it on training with 50% dropout so it generates sheet music and handles without it.

2026-09-14 17:01:36 -06:00

uintx_quant.py

Move uintx quantization to ostris quant with bit identical matching. Now we are not bound to an older version of torch ao.

2026-07-27 12:59:42 -06:00

unified_memory.py

Fixed issue on DGX spark that caused unnessary moves of models causing slow down on unified memory

2026-09-26 11:56:42 -06:00

vae.py

Various bug fixes

2025-04-29 09:30:33 -06:00