Instructions to use MAMBA4L/Libero_action_conditioned_svd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MAMBA4L/Libero_action_conditioned_svd with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MAMBA4L/Libero_action_conditioned_svd", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add action conditioned SVD checkpoint
Browse files
checkpoint-152000/action_proj.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be8a7f83d27a023c3637d9f188acc8035ea48ed13cfffeda60ebea7e7b571d3b
|
| 3 |
+
size 4233328
|
checkpoint-152000/action_type_embed.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc9f6c7ca52530dafd1098e895eba437c97a4e5fce423705ef4d5182d68b9b88
|
| 3 |
+
size 5390
|
checkpoint-152000/temporal_pos_emb.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59d954716d5e88d8843e6ee764cada5d21219fd6d7deeaa0e555a64d1a94c346
|
| 3 |
+
size 132361
|
checkpoint-152000/unet/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNetSpatioTemporalConditionModel",
|
| 3 |
+
"_diffusers_version": "0.25.1",
|
| 4 |
+
"_name_or_path": "/mnt/kevin/vlm_models/svd",
|
| 5 |
+
"addition_time_embed_dim": 256,
|
| 6 |
+
"block_out_channels": [
|
| 7 |
+
320,
|
| 8 |
+
640,
|
| 9 |
+
1280,
|
| 10 |
+
1280
|
| 11 |
+
],
|
| 12 |
+
"cross_attention_dim": 1024,
|
| 13 |
+
"down_block_types": [
|
| 14 |
+
"CrossAttnDownBlockSpatioTemporal",
|
| 15 |
+
"CrossAttnDownBlockSpatioTemporal",
|
| 16 |
+
"CrossAttnDownBlockSpatioTemporal",
|
| 17 |
+
"DownBlockSpatioTemporal"
|
| 18 |
+
],
|
| 19 |
+
"in_channels": 8,
|
| 20 |
+
"layers_per_block": 2,
|
| 21 |
+
"num_attention_heads": [
|
| 22 |
+
5,
|
| 23 |
+
10,
|
| 24 |
+
20,
|
| 25 |
+
20
|
| 26 |
+
],
|
| 27 |
+
"num_frames": 14,
|
| 28 |
+
"out_channels": 4,
|
| 29 |
+
"projection_class_embeddings_input_dim": 768,
|
| 30 |
+
"sample_size": 96,
|
| 31 |
+
"transformer_layers_per_block": 1,
|
| 32 |
+
"up_block_types": [
|
| 33 |
+
"UpBlockSpatioTemporal",
|
| 34 |
+
"CrossAttnUpBlockSpatioTemporal",
|
| 35 |
+
"CrossAttnUpBlockSpatioTemporal",
|
| 36 |
+
"CrossAttnUpBlockSpatioTemporal"
|
| 37 |
+
]
|
| 38 |
+
}
|
checkpoint-152000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cca3fa9a8071464a18384a1d2af7beae27ca508f33da399a65c65685f2856b0
|
| 3 |
+
size 6098682464
|
checkpoint-152000/view_type_embed.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17528406ac75ee00059bcf180bcd5267d0d114d447defbb24e3ee2faa81fa359
|
| 3 |
+
size 9476
|