Hugging Face's logo

AbstractFramework
/
wan2.2-t2v-a14b-diffusers-bf16

Text-to-Video
Safetensors
MLX
Wan2.2
mlx-gen
mflux
apple-silicon
bf16
wan
video-generation
wan-a14b
Model card Files
xet
 Community
lpalbou commited on
Commit
2061f00
·
verified ·
1 Parent(s): f7de702

Add files using upload-large-folder tool

Browse files
Files changed (33) hide show
  1. README.md +35 -37
  2. transformer/0.safetensors +1 -1
  3. transformer/1.safetensors +1 -1
  4. transformer/10.safetensors +1 -1
  5. transformer/11.safetensors +1 -1
  6. transformer/12.safetensors +1 -1
  7. transformer/13.safetensors +1 -1
  8. transformer/2.safetensors +1 -1
  9. transformer/3.safetensors +1 -1
  10. transformer/4.safetensors +1 -1
  11. transformer/5.safetensors +1 -1
  12. transformer/6.safetensors +1 -1
  13. transformer/7.safetensors +1 -1
  14. transformer/8.safetensors +1 -1
  15. transformer/9.safetensors +1 -1
  16. transformer/model.safetensors.index.json +1 -1
  17. transformer_2/0.safetensors +1 -1
  18. transformer_2/1.safetensors +1 -1
  19. transformer_2/10.safetensors +1 -1
  20. transformer_2/11.safetensors +1 -1
  21. transformer_2/12.safetensors +1 -1
  22. transformer_2/13.safetensors +1 -1
  23. transformer_2/2.safetensors +1 -1
  24. transformer_2/3.safetensors +1 -1
  25. transformer_2/4.safetensors +1 -1
  26. transformer_2/5.safetensors +1 -1
  27. transformer_2/6.safetensors +1 -1
  28. transformer_2/7.safetensors +1 -1
  29. transformer_2/8.safetensors +1 -1
  30. transformer_2/9.safetensors +1 -1
  31. transformer_2/model.safetensors.index.json +1 -1
  32. vae/0.safetensors +1 -1
  33. vae/model.safetensors.index.json +1 -1
README.md CHANGED
@@ -8,57 +8,45 @@ tags:
8
  - mlx-gen
9
  - mflux
10
  - apple-silicon
 
11
  - wan
12
  - wan2.2
13
  - video-generation
14
  - text-to-video
15
- - image-to-video
16
  - wan-a14b
17
  ---
18
  # wan2.2-t2v-a14b-diffusers-bf16
19
 
20
- This repository contains MLX-Gen saved weights for `Wan-AI/Wan2.2-T2V-A14B-Diffusers`. The checkpoint is designed for local Apple Silicon inference with [`mlx-gen`](https://github.com/lpalbou/mlx-gen).
 
 
 
21
 
22
- It uses the mflux/MLX saved-weight layout. It is not a Diffusers or Transformers `from_pretrained()` checkpoint.
 
23
 
24
  ## Source Model
25
 
26
  Original model: [`Wan-AI/Wan2.2-T2V-A14B-Diffusers`](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers).
27
 
28
- ## License and Access
29
-
30
  This prepared derivative follows the Apache 2.0 license of the source model.
31
 
32
- ## Quantization
33
-
34
- This checkpoint stores MLX-Gen Wan2.2 A14B weights without an explicit quantization level.
35
-
36
- For Wan checkpoints, MLX-Gen loads transformer and VAE weights at BF16 runtime precision. The UMT5 text encoder is preserved from the source model. Wan supports text-to-video and selected image-to-video routes depending on the source model.
37
-
38
- ## Local Validation
39
 
40
- Validation used 384x224, 17 frames, 12 denoising steps, guidance 4, guidance-2 3, fps 8, and seed 4242 on Apple Silicon. The memory numbers cover the full run from model init through video save. MLX peak is the MLX allocator peak; physical peak is the Darwin process physical footprint, which better reflects Apple Silicon unified-memory pressure than RSS alone.
41
 
42
- Bottom line:
43
 
44
- - The BF16 package reduces storage, not runtime memory. It is useful when you want a smaller, uploadable package with byte-identical output to the original source-cache run.
45
- - The mixed q8/BF16 package reduces both storage and runtime memory. Use it when memory footprint matters.
46
 
47
- | Layout | Disk | MLX Peak | Physical Peak | Time | Result |
48
- | --- | ---: | ---: | ---: | ---: | --- |
49
- | Original source snapshot | 118 GiB | 33.0 GiB | 48.9 GiB | 108.3 s | Baseline. |
50
- | This BF16 package | 64 GiB | 33.0 GiB | 45.1 GiB | 114.4 s | Storage only; output was byte-identical. |
51
- | Mixed q8/BF16 package | 40 GiB | 20.8 GiB | 31.8 GiB | 110.3 s | Storage and memory; side-by-side quality validation passed. |
52
 
53
- Compared with the original source snapshot, this BF16 package cuts disk usage by about 46% but does not materially reduce generation memory. The mixed q8/BF16 package cuts disk usage by about 66%, MLX peak memory by about 37%, and physical peak memory by about 35% in this validation run.
 
 
 
54
 
55
- ## Compatibility
56
-
57
- Requires `mlx-gen >= 0.18.8`.
58
-
59
- Generated with `mlx-gen 0.18.8`.
60
-
61
- Use the `mlxgen` command and Python import path for new MLX-Gen projects.
62
 
63
  ## Usage
64
 
@@ -70,20 +58,30 @@ mlxgen download --model AbstractFramework/wan2.2-t2v-a14b-diffusers-bf16
70
  mlxgen generate \
71
  --model AbstractFramework/wan2.2-t2v-a14b-diffusers-bf16 \
72
  --task text-to-video \
73
- --prompt "Your video prompt here" \
74
- --width 1280 \
75
- --height 720 \
76
- --frames 81 \
77
- --steps 40 \
78
  --guidance 4 \
79
  --guidance-2 3 \
80
- --fps 16 \
81
- --seed 42 \
 
 
82
  --output video.mp4
83
  ```
84
 
 
 
 
 
 
 
 
 
85
  ## Attribution
86
 
87
- MLX-Gen is based on [mflux](https://github.com/filipstrand/mflux) by Filip Strand and the original mflux contributors. This model card is generated by MLX-Gen so derived checkpoints keep that attribution visible.
88
 
89
  Prepared and contributed by [@lpalbou](https://huggingface.co/lpalbou).
 
8
  - mlx-gen
9
  - mflux
10
  - apple-silicon
11
+ - bf16
12
  - wan
13
  - wan2.2
14
  - video-generation
15
  - text-to-video
 
16
  - wan-a14b
17
  ---
18
  # wan2.2-t2v-a14b-diffusers-bf16
19
 
20
+ This repository contains BF16 MLX-Gen saved weights for
21
+ [`Wan-AI/Wan2.2-T2V-A14B-Diffusers`](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers).
22
+ It is designed for local Apple Silicon inference with
23
+ [`mlx-gen`](https://github.com/lpalbou/mlx-gen).
24
 
25
+ It uses the mflux/MLX saved-weight layout. It is not a Diffusers or Transformers
26
+ `from_pretrained()` checkpoint.
27
 
28
  ## Source Model
29
 
30
  Original model: [`Wan-AI/Wan2.2-T2V-A14B-Diffusers`](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers).
31
 
 
 
32
  This prepared derivative follows the Apache 2.0 license of the source model.
33
 
34
+ ## Precision
 
 
 
 
 
 
35
 
36
+ This package stores the Wan A14B T2V transformer and VAE weights for MLX-Gen BF16 runtime use. The UMT5 text encoder, scheduler metadata, tokenizer files, and model index are included in the prepared folder.
37
 
38
+ ## Validation
39
 
40
+ Measured on 2026-06-04 with `mlx-gen 0.18.9` on Apple Silicon. The upstream Diffusers source snapshot measured about 118 GiB in the local Hugging Face cache before preparing these packages. The table below reports prepared-package generation from model init through MP4 save and post-save video-health validation.
 
41
 
42
+ Validation profile: `384x224`, 33 frames, 12 denoising steps, guidance `4`, guidance-2 `3`, 8 fps, seed `4242`, `--low-ram`.
 
 
 
 
43
 
44
+ | Package | Disk | Full-Process Physical Peak | Max RSS | MLX Peak | Total Time | Video Health |
45
+ |---|---:|---:|---:|---:|---:|---|
46
+ | This BF16 package | 64.3 GiB | 33.0 GiB | 31.8 GiB | 27.7 GiB | 152.7 s | 33/33 frames, 384x224, 8 fps, temporal delta 1.3 |
47
+ | Mixed q8/BF16 package | 39.7 GiB | 20.7 GiB | 19.5 GiB | 15.5 GiB | 154.8 s | 33/33 frames, 384x224, 8 fps, temporal delta 1.4 |
48
 
49
+ Physical peak is Darwin `ri_phys_footprint` sampled for the full process. The validation is intentionally small and repeatable; it is not a claim that every full-size `1280x720`, 81-frame, 40-step job has the same memory or timing profile.
 
 
 
 
 
 
50
 
51
  ## Usage
52
 
 
58
  mlxgen generate \
59
  --model AbstractFramework/wan2.2-t2v-a14b-diffusers-bf16 \
60
  --task text-to-video \
61
+ --prompt "A cinematic scene of a scientist working on agentic AI through the night, monitors glowing, papers shifting in a slow dolly shot." \
62
+ --width 384 \
63
+ --height 224 \
64
+ --frames 33 \
65
+ --steps 12 \
66
  --guidance 4 \
67
  --guidance-2 3 \
68
+ --fps 8 \
69
+ --seed 4242 \
70
+ --low-ram \
71
+ --metadata \
72
  --output video.mp4
73
  ```
74
 
75
+ ## Compatibility
76
+
77
+ Requires `mlx-gen >= 0.18.9`.
78
+
79
+ Generated with `mlx-gen 0.18.9`.
80
+
81
+ Use the `mlxgen` command and Python import path for new MLX-Gen projects.
82
+
83
  ## Attribution
84
 
85
+ MLX-Gen is based on [mflux](https://github.com/filipstrand/mflux) by Filip Strand and the original mflux contributors.
86
 
87
  Prepared and contributed by [@lpalbou](https://huggingface.co/lpalbou).
transformer/0.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8592d59e9676607b8eb0c38933dbcb235fdc0ee0c1242d37832c27a75ef4a34
3
  size 2133612608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077956a53e075dd11f00fc2f0b2945e88d4750fa33156856e1dcf661b99d3fea
3
  size 2133612608
transformer/1.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0fcab2eb45022106ff9ba43f5b13905f0d09687c3e03dc3f60fe505c984b3df
3
  size 2108374015
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d004b2dae04565f9e6bff136cd4e8ee1cf276b84d101773bde2ceafeee2ae6
3
  size 2108374015
transformer/10.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7507d64c01fee8c90458a89c1d95c1afff640ab2e90227cafc16825234bdec3b
3
  size 2108374118
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9357ebc9ab1a5f4a07ac119945b47fd0988ec6c25aca208d47847a4225d86b52
3
  size 2108374118
transformer/11.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95693b4f3ac40e49b9584f35f6cd9e6a55d3fe96f1d46fb26677e1b6c98f2922
3
  size 2108374136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1323c2e22d6f53a577d5743caf5143ae76ad430b4502d4b1af9d474523fcf8b3
3
  size 2108374136
transformer/12.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ab0aa26925765164de15f1aff1bfe0250e408a5abe11e56fd2d864576bfba43
3
  size 2108374144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07c337852a24596291facdf927a9b0409734c1da6bfdc97b3013a78275685bd8
3
  size 2108374144
transformer/13.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f883ffc9c191fdf824e750fa3dcb57371d004f8ffb94739e0436d348f88462f0
3
  size 1144042059
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b0a3b4542e42ebd5b8aed67735640cbec05bad466e7811daecde08b80e9772
3
  size 1144042059
transformer/2.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c9ee2bdb54b966ebfb68e925bf5cce21fdcba040875773a5f1a606adddca4f3
3
  size 2108374047
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3560d3937a75539f682ccfd93943fc7c3dc7e571fce81f1f845b294e271e5ba
3
  size 2108374047
transformer/3.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3648b256dfb7f64f2a52d1c4a5ebffbb16bf0eec32e8571f39bf1c4c5ac6b34a
3
  size 2108374050
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e2f5e5243fd55f2747839044e1ea3c5a605d3365f1dd10cb284d5a457632c6
3
  size 2108374050
transformer/4.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b60946ee25b3bedf4c7e44d11116c11a249588f665e068b9508b6e75fb992113
3
  size 2108374118
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0517b2b5bdc07717b50bad5d76437355f23a1f4a783f9d0ee5d52fb11bca5ae
3
  size 2108374118
transformer/5.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63076b71bcb08f67ea277b5366a3d463fe70ed9300107fa9a0f977ac902e69e2
3
  size 2108374122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4abb152a6668c9e33dcf422635c6d059a98ca154e4ff70646f43bd232d609de3
3
  size 2108374122
transformer/6.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c016697d3eafc3080d3ce7655988198cc873cefed55850c13b1ac035fc3d9a99
3
  size 2108374116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36b0e4c706703d57fbe1f913866108372f95ef81644bed3add740487392a717
3
  size 2108374116
transformer/7.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1f0ffac68af2e13b13c948dd4e30213694cb79f9676aacd8cf2b54a1b928514
3
  size 2108374100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:730b11f1d1cf7b12c1dcef4d58d16449a127a2dbe06a75500973a8aa4ff7b9b4
3
  size 2108374100
transformer/8.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdfbb4fd751a3c59a52731166ca1a1973bf2e13961f4ce1ff14d96168c95d1c2
3
  size 2108374098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3ddbe5a34b0c4b6f3127d17e7e431fd61fbd77debe0b90b67d4c44ddf03158
3
  size 2108374098
transformer/9.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e070c34410540922c62209cc3a130629a643a8838674db12622e12182e54d4d2
3
  size 2108374110
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b6614e809490569bebf3f1374cb491f5bf08452453d787c4371460138f13ec
3
  size 2108374110
transformer/model.safetensors.index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "metadata": {
3
  "quantization_level": "None",
4
- "mflux_version": "0.18.8"
5
  },
6
  "weight_map": {
7
  "rope.freqs_cos": "0.safetensors",
 
1
  {
2
  "metadata": {
3
  "quantization_level": "None",
4
+ "mflux_version": "0.18.9"
5
  },
6
  "weight_map": {
7
  "rope.freqs_cos": "0.safetensors",
transformer_2/0.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:286f392ee2e582ee44a916b7327dbc8164c2218b8160df88269b07eb07760bce
3
  size 2133612608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ee806421dff604405109dbdbe6031f2274f5bd63195223248d9f8a46517e92
3
  size 2133612608
transformer_2/1.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6415eb24222566e0ca2bdff6520dc149d0c67c6dac215be39ff91044a69f096a
3
  size 2108374015
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb55633aaeb23464271c3194c0d22305ea3ea89d912f94710c818d349194f158
3
  size 2108374015
transformer_2/10.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:345a2816ee2388fb7d1351f061e7ef664e0c6ddf335a69c278fe321c1556ae9d
3
  size 2108374118
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b781cf8b59bfeb370f686a3797149f2d6fff4bf6cd576f907ad4326697c5ab
3
  size 2108374118
transformer_2/11.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f18188349ec6880187dfbc18c25d030165dd1bd6e8696e0e396a90ec1c596e71
3
  size 2108374136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f437bf8290390686b7cce92f18ff9e3055ed191fa1fda5523d9946dc04d97013
3
  size 2108374136
transformer_2/12.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:787fc300cc0209472c9d986786ae2c19613f8faf36a730b97acd73e59db0099b
3
  size 2108374144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe482282a1df0993823f3ff791e3dc0b6b3fc5b6f865164f438a676977a306a
3
  size 2108374144
transformer_2/13.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81900d4a3841f60be43912fcb19906e937963cbf2e4f0793a0e132d1610e3e90
3
  size 1144042059
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b45445e960045d5ca33dd3f0cc008641e325195593f4ec451ffaaa9b4445700
3
  size 1144042059
transformer_2/2.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4955037639c64a4746a922adc383c7eaa99a24375385fef4a98760646819cce7
3
  size 2108374047
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e11c8e7cadae434eb2fbf515d86758c9a8e5222459139ee7f3d29055cec60bcb
3
  size 2108374047
transformer_2/3.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9f3dea2cdba8922032db31d7d0e8e1b25f2c0004d90f918be1e4cfe4db18573
3
  size 2108374050
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1abc8a6e026c1d2739357fbb978f48599b6d8a4d0afaa22fb505996bf2b0e807
3
  size 2108374050
transformer_2/4.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea172191d9006d89428b718ca35171c03bc847cc134c7d1fc88539a3dec7b5ce
3
  size 2108374118
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a43ede6ddb32632e1757fdbbfe8cd427eafa887e906a059b0a4b4e02acb5c0
3
  size 2108374118
transformer_2/5.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e48404ec4833171703a708f37d9e1f70007a916c5ee935bd77295351c974a184
3
  size 2108374122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e658e5e452711172c04180e11d47e475ae469d5fcf7dd9a8825f657ad1707617
3
  size 2108374122
transformer_2/6.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0eb5345ceea74c7a4c77d3bda4f548f54b0eb8742e482db56d6ad0ed0c363f23
3
  size 2108374116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cebfd35a90752a78ba0e10159526d4be76d0dd364aa9510b7613ff5037054a
3
  size 2108374116
transformer_2/7.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d87b1e83064c4d7b1014171d366f21eb6472e3e48f41df85757753b01a501691
3
  size 2108374100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d73d1cbb1accd7cdc27fa3ba7fc8be70d10a44afe0599f424dcd8332fde73c7
3
  size 2108374100
transformer_2/8.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eeaf3d6fc20a273d9eee2e65eb70cda5d4e3e4d3e3a42c106c167f9f9bf03c3c
3
  size 2108374098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b1b5339b411967518dffda3dfdf07ba480bd42258198f925b773613f61d0db2
3
  size 2108374098
transformer_2/9.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8a7f6862473ea1cf7175d6baea11c3530ceae18c71ba4015bfa5e5867d9d25b
3
  size 2108374110
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a23cc157564677f0464d7f60fffe9f4432cf3d9cf991ed499b01a9509928f6
3
  size 2108374110
transformer_2/model.safetensors.index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "metadata": {
3
  "quantization_level": "None",
4
- "mflux_version": "0.18.8"
5
  },
6
  "weight_map": {
7
  "rope.freqs_cos": "0.safetensors",
 
1
  {
2
  "metadata": {
3
  "quantization_level": "None",
4
+ "mflux_version": "0.18.9"
5
  },
6
  "weight_map": {
7
  "rope.freqs_cos": "0.safetensors",
vae/0.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:626e078e91c46ef98d8f3dd4b90dc8b9d3e7ff48357f48f973fee272b3bdeb63
3
  size 253807820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3d43fd7e6e6370daf762a357d4fab09f34118d0b9f9dc383f322fffe0db0411
3
  size 253807820
vae/model.safetensors.index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "metadata": {
3
  "quantization_level": "None",
4
- "mflux_version": "0.18.8"
5
  },
6
  "weight_map": {
7
  "encoder.conv_in.conv3d.weight": "0.safetensors",
 
1
  {
2
  "metadata": {
3
  "quantization_level": "None",
4
+ "mflux_version": "0.18.9"
5
  },
6
  "weight_map": {
7
  "encoder.conv_in.conv3d.weight": "0.safetensors",