a72154405e
Text Processing Engine is Finished
...
100% reproduce all previous results, including TI embeddings, LoRAs in CLIP, emphasize settings, BREAK, timestep swap scheduling, AB mixture, advanced uncond, etc
Backend is 85% finished
2024-08-04 18:42:51 -07:00
2791203d5b
move file
2024-08-04 13:49:58 -07:00
1e23bf07ca
add transformer encode
2024-08-04 13:45:32 -07:00
8c118df739
emphasis
2024-08-04 13:19:32 -07:00
cb9b155645
add embedding layer impl
2024-08-04 13:10:08 -07:00
21c8608373
Implement A1111 Text Processing from Scratch
...
Thanks god
2024-08-04 12:43:31 -07:00
2e4adf19b6
Create emphasis.py
2024-08-04 12:21:57 -07:00
42ef31f106
textual inversion from scratch
2024-08-04 12:07:11 -07:00
2d30eeedfd
upload files and models
...
Update clip.py
i
Update base.py
i
2024-08-03 17:46:26 -07:00
6dd8cd8820
force config intergrity
2024-08-03 17:09:09 -07:00
be3f0a0039
remove legacy config
2024-08-03 17:04:56 -07:00
fb3052350b
rework model loader
2024-08-03 17:01:40 -07:00
430482d1a0
fix cast
2024-08-03 16:08:22 -07:00
c901890164
ling
2024-08-03 15:46:42 -07:00
3ecdcee5a8
add sampler
2024-08-03 15:46:27 -07:00
c7b1789892
Update sub_quadratic_attention.py
2024-08-03 15:19:45 -07:00
8a01b2c5db
move to new backend - part 1
2024-08-03 14:59:46 -07:00
07b2d2ccac
clipvision, ipadapter, and misc
...
backend is 75% finished
2024-08-03 14:18:16 -07:00
bb5083f3c2
rework sample function
2024-08-03 13:27:23 -07:00
e81788e3b8
add huggingface mappings
2024-08-02 22:56:04 -07:00
31d26adba3
add latent_spaces
2024-08-02 22:40:30 -07:00
e722991752
control rework
2024-08-02 22:17:27 -07:00
1f56acf3e7
use trange
2024-08-02 15:09:04 -07:00
6ed95d66e5
rework several component patcher
...
backend is 65% finished
2024-08-02 14:56:57 -07:00
91543adb90
resolve #926
2024-08-02 13:55:11 -07:00
d1b8a2676d
rework lora and patching system
...
and dora etc - backend rework is 60% finished
And I also removed the webui’s extremely annoying lora filter from model versions.
2024-08-02 13:45:26 -07:00
2104e12dab
Update unet.py
2024-08-02 04:22:05 -07:00
40476bb8b3
Update unet.py
2024-08-02 04:20:18 -07:00
76e0d17af3
tune attn params
2024-08-02 04:18:47 -07:00
3dd084d55b
more attention types
2024-08-02 03:37:21 -07:00
318219bc9d
move file
2024-08-02 03:37:20 -07:00
61ca3bc34f
fix lora
2024-08-01 23:29:27 -07:00
f6981339b0
predictor is a better name
2024-08-01 21:29:34 -07:00
bc9977a305
UNet from Scratch
...
Now backend rewrite is about 50% finished.
Estimated finish is in 72 hours.
After that, many newer features will land.
2024-08-01 21:19:41 -07:00
fec51bf2dd
ling
2024-08-01 13:07:42 -07:00
4d1be42975
Intergrate CLIP
2024-08-01 12:27:20 -07:00
af0b04cc16
store huggingface vars in VAE
2024-07-31 21:40:18 -07:00
3079b81547
make attn func name more technically correct
2024-07-31 21:35:19 -07:00
3fb9d5a85c
fix vae output layer weight cannot cast
2024-07-31 21:20:56 -07:00
0d079a846d
Intergrate Native AutoEncoderKL
2024-07-31 21:10:19 -07:00
f052fabd4d
make model guess a function that can be patched
2024-07-30 17:26:49 -06:00
c8156fcf41
rework model loader and configs
2024-07-30 13:27:26 -06:00
40dd61ba6c
improve vae key mapping
2024-07-30 09:23:58 -06:00
3289ccb53f
add vae configs
2024-07-30 08:55:22 -06:00
dc62b0d2d7
begin to use new vae impl
2024-07-30 08:43:14 -06:00
9a48c9eff3
rename state_dict method to make it clear
2024-07-30 08:05:36 -06:00
9cb69baf9f
Implement VAE for new backend
2024-07-29 22:26:32 -06:00
3bc9402de9
ling
2024-07-29 11:48:55 -06:00
68b672493a
implement attention for new backend
2024-07-29 11:46:16 -06:00
99fcb35506
rename
2024-07-29 11:29:29 -06:00
layerdiffusion