a4bbe167ce
Added reference token attention isolation (kv_cache) for Krea2 edit training. Same training cost with significant inference speed up. 2x inference speedup.
2026-07-09 12:00:55 -06:00
6233efe1bb
Fix sampling issue on zimage turbo and krea2 turbo models
2026-07-08 12:34:39 -06:00
7bceec3b07
Apply a loss mask for first frame conditioning for wan and ltx
2026-07-07 09:05:53 -06:00
bd93a312bc
Load more types of comfy ui style quants for ltx2
2026-07-07 09:04:51 -06:00
b1e1a834d4
Added support to train Krea2 as an edit model
2026-07-04 09:12:39 -06:00
7ee1f98f6d
Allow loading and saving z_image in comfy safetensors format.
2026-06-28 07:15:49 -06:00
f8667f0334
Save Krea2 even if quantized
2026-06-28 06:03:37 -06:00
4a99ddabad
Fix breaking change with diffusers qwen image
2026-06-26 10:04:35 -06:00
5f04ae7ad5
Rework merge_network_on_save to handle dequantization on merging and saving for much more efficient full finetuning.
2026-06-25 13:19:38 -06:00
7a089fd0d7
Add support for training directly on Krea2 Turbo with a training adapter
2026-06-23 20:32:02 -06:00
a803611ec1
Enable tiling on vae when decoding with low_vram flag on krea2
2026-06-23 18:38:52 -06:00
724e67d634
Set krea 2 to use new lokr format
2026-06-23 13:31:50 -06:00
e20b42e84a
Add offloading support for krea2
2026-06-23 10:43:36 -06:00
99be3d96a2
Add support for Krea2 ( #906 )
...
* Add support for krea2
* Update repo pointer to actual repo
2026-06-23 09:18:14 -06:00
60c1ac6a50
Add support for Boogu Image and Boogu Image Edit
2026-06-18 15:05:49 -06:00
e886745051
Added additional information on addine new models and some additional gotchas
2026-06-18 15:04:50 -06:00
ad49d4ef25
Update example to cover some common issues
2026-06-18 07:54:37 -06:00
92814f9e6d
Apply ideogram dynamic shifting to sampling
2026-06-16 18:52:16 -06:00
178eb5fbbe
Add unconditional lora support so Ideogram 4 inference will more closely resemble the full pipeline results. I pushed a finetuned unconditional lora to the hub as an adapter.
2026-06-16 13:27:43 -06:00
f6c0104f25
Handle unconditional conditioning for ideogram 4 more in line with example code.
2026-06-16 10:23:08 -06:00
86b19589a0
Update the Ideogram 4 prompt generation/parsing/ui to handle the updated format notes better.
2026-06-16 09:44:38 -06:00
fcccc0fbd2
Add gradient checkpointing to ideogram4 vae
2026-06-15 10:00:40 -06:00
c0d600b5d6
Allow using flash backend for ideogram
2026-06-13 15:17:20 -06:00
c8cd78b1a4
Allow nested transformer block names for quantization, lora targeting, quantizing
2026-06-13 14:33:16 -06:00
6c3b82696e
Add support for PRX Pixel T2I
2026-06-13 09:47:53 -06:00
a01c83073a
Added an example model with docs so people and agents can add models easier.
2026-06-13 08:17:06 -06:00
35588726de
Fixed issue where a buffer was stuck on cpu when offloading ideogram4
2026-06-07 13:31:03 -06:00
8968e41234
Set ideogram to use new loke saving format
2026-06-07 09:49:57 -06:00
6a8d9333b6
Improved the prompt handeling of ideogram4 model. Now used advanced prompts class to store them smaller and allow longer prompts
2026-06-04 13:00:23 -06:00
63b3181262
Added experimental support for Ideogram 4
2026-06-04 09:03:00 -06:00
5e84bf0d0b
Fixed issue with hidream-01 that could cause a weird nan state. Took forever to track down as it was 1 in 10 starts.
2026-05-28 12:48:24 -06:00
ef57c1077c
Change z image divisibility
2026-05-28 09:09:36 -06:00
7354def271
Added decode latent method to qwen image model
2026-05-25 10:02:09 -06:00
fbac1cb7f5
Dont force flash attention on hidream 01. Causes random issues and is slower.
2026-05-24 16:05:22 -06:00
644a6f9246
Fix device casting for zimage in some instances
2026-05-23 10:37:33 -06:00
c6ecc03ccd
Fixed saving full model of z_image l2p for finetuning
2026-05-23 07:36:24 -06:00
6102370df9
Add support for ZImage L2P
2026-05-22 14:58:28 -06:00
e03c6e4dc9
Fix potential inconsistency with different attention mentods in hidream01
2026-05-13 09:08:11 -06:00
fc4d6ebf39
Add support for fine-tuning Hidream O1 ( #831 )
...
* Initial support for hidream. Lora keys likely need work
* Fix saving for hidream-o1
* Remove dependence on flash attention for hidream o1
* Fix gradient checkpointing for hidream o1
* A lot of fixes for hidream. Handle loading and saving as comfy model.
* Omit layers not used in comfy. Fix issue with lora loading keys in comfy
* Version bumpo
2026-05-12 11:15:16 -06:00
e9ab387dfd
Fixed issue with qwen image edit models when using multiple control images when not caching text embeddings.
2026-04-30 11:59:12 +00:00
deb409085a
Made it possible to use the flux 2 small decoder VAE when setting the vae_path manually for flux2 models
2026-04-30 05:42:31 -06:00
7ccec8ec2c
Add checkpointing and a proper decode for flux 2 VAEs so they can be used with DFE
2026-04-30 04:27:13 -06:00
7c4f18ce51
Fix ernie unpatchify
2026-04-17 12:03:39 -06:00
8cb9649382
Add decode latent to ernie pipe
2026-04-17 12:01:09 -06:00
ab1ee4df34
Hotfix some issues with Wan models caused by diffusers and transformers updates
2026-04-16 20:53:50 +00:00
afb62b1fa5
Add support for Nucleus-Image
2026-04-16 13:09:10 -06:00
dd7074a21f
Fix issue with layer offloading on ernie
2026-04-14 19:19:02 -06:00
3e0c904054
Add support for Baidu's ERNIE-Image ( #793 )
...
* Add support for ERNIE Image
* change float64 to float32
* Version bump
* Update ERNIE defaults
2026-04-14 09:45:12 -06:00
233e292256
Added some experimental low step things for zeta
2026-04-13 09:37:34 -06:00
9ca58e9aa2
Fixed offload and quantize order of ltx 2.3 text encoder.
2026-04-07 15:11:50 -06:00
Jaret Burkett