Upload folder using huggingface_hub
Browse files- README.md +7 -3
- audio_vae/config.json +1 -1
- model_index.json +12 -1
- scheduler/scheduler_config.json +3 -3
- transformer/config.json +2 -2
- transformer/diffusion_pytorch_model.safetensors +2 -2
README.md
CHANGED
|
@@ -1,3 +1,7 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Kandinsky 6 Diffusers export
|
| 2 |
+
|
| 3 |
+
This bundle references K6 classes from an installed patched Diffusers package; the generated Python modules are intentionally not copied into this directory.
|
| 4 |
+
|
| 5 |
+
Install the patched checkout before loading it.
|
| 6 |
+
|
| 7 |
+
Pipeline class: `Kandinsky6TI2VAPipeline` from the installed patched package.
|
audio_vae/config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "MMAudioVAE",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"downsample_factor": 1024,
|
| 5 |
"mode": "44k",
|
| 6 |
"sample_rate": 44100,
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "MMAudioVAE",
|
| 3 |
+
"_diffusers_version": "0.40.0.dev0",
|
| 4 |
"downsample_factor": 1024,
|
| 5 |
"mode": "44k",
|
| 6 |
"sample_rate": 44100,
|
model_index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "Kandinsky6TI2VAPipeline",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"transformer": [
|
| 5 |
"diffusers",
|
| 6 |
"Kandinsky6Transformer3DModel"
|
|
@@ -29,6 +29,17 @@
|
|
| 29 |
"transformers",
|
| 30 |
"CLIPTokenizer"
|
| 31 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"audio_vae": [
|
| 33 |
"diffusers",
|
| 34 |
"MMAudioVAE"
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "Kandinsky6TI2VAPipeline",
|
| 3 |
+
"_diffusers_version": "0.40.0.dev0",
|
| 4 |
"transformer": [
|
| 5 |
"diffusers",
|
| 6 |
"Kandinsky6Transformer3DModel"
|
|
|
|
| 29 |
"transformers",
|
| 30 |
"CLIPTokenizer"
|
| 31 |
],
|
| 32 |
+
"_kandinsky6": {
|
| 33 |
+
"format_version": 1,
|
| 34 |
+
"source_checkpoint": "merged_bf16.safetensors",
|
| 35 |
+
"video_vae_implementation": "diffusers",
|
| 36 |
+
"uses_patched_diffusers": true,
|
| 37 |
+
"processor": "tokenizer",
|
| 38 |
+
"text_encoder_assets": {
|
| 39 |
+
"qwen": "text_encoder",
|
| 40 |
+
"clip": "text_encoder_2"
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
"audio_vae": [
|
| 44 |
"diffusers",
|
| 45 |
"MMAudioVAE"
|
scheduler/scheduler_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "PiflowScheduler",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"base_image_seq_len": 256,
|
| 5 |
"base_shift": 0.5,
|
| 6 |
"eps": 1e-06,
|
|
@@ -8,8 +8,8 @@
|
|
| 8 |
"invert_sigmas": false,
|
| 9 |
"max_image_seq_len": 4096,
|
| 10 |
"max_shift": 1.15,
|
| 11 |
-
"n_grid":
|
| 12 |
-
"nfe":
|
| 13 |
"num_policy_substeps": 128,
|
| 14 |
"num_train_timesteps": 1000,
|
| 15 |
"shift": 5.0,
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "PiflowScheduler",
|
| 3 |
+
"_diffusers_version": "0.40.0.dev0",
|
| 4 |
"base_image_seq_len": 256,
|
| 5 |
"base_shift": 0.5,
|
| 6 |
"eps": 1e-06,
|
|
|
|
| 8 |
"invert_sigmas": false,
|
| 9 |
"max_image_seq_len": 4096,
|
| 10 |
"max_shift": 1.15,
|
| 11 |
+
"n_grid": 10,
|
| 12 |
+
"nfe": null,
|
| 13 |
"num_policy_substeps": 128,
|
| 14 |
"num_train_timesteps": 1000,
|
| 15 |
"shift": 5.0,
|
transformer/config.json
CHANGED
|
@@ -24,8 +24,8 @@
|
|
| 24 |
"model_dim_a": 2048,
|
| 25 |
"num_text_blocks": 4,
|
| 26 |
"num_visual_blocks": 60,
|
| 27 |
-
"out_audio_dim":
|
| 28 |
-
"out_visual_dim":
|
| 29 |
"patch_size": [
|
| 30 |
1,
|
| 31 |
2,
|
|
|
|
| 24 |
"model_dim_a": 2048,
|
| 25 |
"num_text_blocks": 4,
|
| 26 |
"num_visual_blocks": 60,
|
| 27 |
+
"out_audio_dim": 400,
|
| 28 |
+
"out_visual_dim": 160,
|
| 29 |
"patch_size": [
|
| 30 |
1,
|
| 31 |
2,
|
transformer/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cddcd748cabd276ac9263221f5ff0d5fd1d938f071d6506fc0654b6f47b1083b
|
| 3 |
+
size 60344968640
|