RandNMR73
9ee229bb68
test timestep fix
2025-10-02 09:57:56 +00:00
RandNMR73
a274a90c88
obey min num frames requirement in self forcing test
2025-10-02 09:35:31 +00:00
RandNMR73
be01fbe536
self-forcing script fix
2025-10-02 09:23:03 +00:00
RandNMR73
22d6f0cb8d
retry self forcing test again
2025-10-02 09:09:17 +00:00
RandNMR73
b835c0cf5d
retry self forcing test
2025-10-02 08:55:46 +00:00
RandNMR73
c8fce0c21c
try self forcing test fix
2025-10-02 08:43:58 +00:00
RandNMR73
1037f81960
training pipeline fix
2025-10-02 08:19:04 +00:00
RandNMR73
9717ffe017
.
2025-10-02 05:39:23 +00:00
RandNMR73
fb64178611
fix fake score optimizer 2
2025-10-02 05:31:36 +00:00
RandNMR73
ee736ecb48
fix required configs in distillation pipelines
2025-10-02 05:23:45 +00:00
SolitaryThinker
c0c77c7e03
increase lora test threshold
2025-10-02 05:18:42 +00:00
SolitaryThinker
793ce61c30
fixes and reverts
2025-10-02 05:17:26 +00:00
SolitaryThinker
cbaaabf360
fix encoder
2025-10-02 05:10:50 +00:00
SolitaryThinker
add1463b0b
fix encoder test
2025-10-02 04:57:39 +00:00
RandNMR73
6fb1bdb0a0
fix distillation scripts
2025-10-02 04:53:18 +00:00
RandNMR73
d2e091150a
revert
2025-10-02 04:31:59 +00:00
RandNMR73
920184403f
encoder_hidden_states fix
2025-10-02 03:52:07 +00:00
RandNMR73
d016119f2e
fix wan 2.2 self forcing script
2025-10-02 03:42:50 +00:00
SolitaryThinker
066118dada
fix shape
2025-10-02 03:10:29 +00:00
RandNMR73
a547fc1005
clean up
2025-10-02 01:11:58 +00:00
RandNMR73
f27e28ad87
fix datatype?
2025-10-01 21:26:44 +00:00
RandNMR73
2b8e695721
remove deprecated tests
2025-10-01 20:32:28 +00:00
RandNMR73
6d28a05a1c
.
2025-10-01 09:28:26 +00:00
RandNMR73
b55a78be3c
.
2025-10-01 09:25:22 +00:00
RandNMR73
f468651f4e
.
2025-10-01 09:16:32 +00:00
RandNMR73
6b0f456d6f
self-forcing test
2025-10-01 09:07:15 +00:00
RandNMR73
63eeef039d
remove training script
2025-10-01 08:01:23 +00:00
RandNMR73
133533adb4
clean
2025-10-01 07:58:50 +00:00
RandNMR73
abdd8c851d
clean up
2025-10-01 05:57:01 +00:00
RandNMR73 and gemini-code-assist[bot]
d03eacc1c6
Update wan2.2_train.sh
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-09-30 22:22:00 -07:00
RandNMR73 and gemini-code-assist[bot]
03747310c6
Update examples/distill/SFWan2.2-A14B/distill_dmd.sh
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-09-30 22:21:46 -07:00
RandNMR73
a444862561
cleanup + torch.compile training support
2025-09-27 01:40:57 +00:00
RandNMR73
e9802cc5f2
make EMA consistent + clean up SF pipeline
2025-09-26 23:28:10 +00:00
RandNMR73
6ff7686a9d
make EMA and training utils MoE compatible
2025-09-26 20:49:07 +00:00
RandNMR73
92d3ce1612
training works with gradient checkpointing but config has issues
2025-09-26 11:48:07 +00:00
RandNMR73
2b9d8e91b5
gradient checkpointing bug
2025-09-26 08:49:34 +00:00
SolitaryThinker
b666de819a
add init from safetensor for transformer_2
2025-09-26 07:48:59 +00:00
RandNMR73
2df82f0ee4
training not broken
2025-09-26 04:05:14 +00:00
RandNMR73
4f45b6e515
fix hang
2025-09-25 21:01:13 +00:00
SolitaryThinker
4c11512cde
debug
2025-09-25 04:11:51 +00:00
SolitaryThinker
32a820c735
fix val
2025-09-24 04:44:22 +00:00
SolitaryThinker
d6165981b4
offload dit in training
2025-09-24 00:51:41 +00:00
SolitaryThinker
db2e2d79ca
fix rebase
2025-09-23 22:26:20 +00:00
RandNMR73
aabf1fe135
inference works after changes added
...
new branch
Stop backprop through kv_cache
Enable timestep warping & using SelfForcing scheduler
checkpoint
text preprocessing ready
fix rotary embedding
Change Wan DiT to have 0 numerical diff with SF's Wan
wan2.2 training doesn't crash
training hangs
2025-09-23 22:20:29 +00:00
William Lin
404cbf4f3c
[self-forcing] [6/n] Add Ode Init training ( #811 )
2025-09-22 17:58:19 -07:00
William Lin
958ffec844
[bugfix] Update learning rates for sparse distillation recipe ( #812 )
2025-09-22 12:07:03 -07:00
31f000d1cc
[self-forcing] [5/n] Add Self-Forcing distillation pipeline ( #808 )
...
Co-authored-by: RandNMR73 <notomatthew31@gmail.com >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-09-20 19:32:10 -07:00
Yongqi Chen
cd32b3e02f
Update example files and readme ( #809 )
2025-09-20 18:15:59 -07:00
Zhang Peiyuan
bf27908095
Update WeChat Link
2025-09-20 14:16:20 -07:00
William Lin
c5f9ea53b2
[self-forcing] [4/n] Preprocessing for collecting ODE trajectory ( #788 )
2025-09-15 17:54:42 -07:00
RandNMR73