Instructions to use heboya8/text2video-test-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use heboya8/text2video-test-2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("heboya8/text2video-test-2", 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
Delete checkpoint-28040
Browse files- checkpoint-28040/lora/full_weights/28040_lora_text_to_video_unet.safetensors +0 -3
- checkpoint-28040/model_index.json +0 -25
- checkpoint-28040/scheduler/scheduler_config.json +0 -20
- checkpoint-28040/text_encoder/config.json +0 -25
- checkpoint-28040/text_encoder/model.safetensors +0 -3
- checkpoint-28040/tokenizer/merges.txt +0 -0
- checkpoint-28040/tokenizer/special_tokens_map.json +0 -24
- checkpoint-28040/tokenizer/tokenizer_config.json +0 -33
- checkpoint-28040/tokenizer/vocab.json +0 -0
- checkpoint-28040/unet/config.json +0 -34
- checkpoint-28040/unet/diffusion_pytorch_model.safetensors +0 -3
- checkpoint-28040/vae/config.json +0 -32
- checkpoint-28040/vae/diffusion_pytorch_model.safetensors +0 -3
checkpoint-28040/lora/full_weights/28040_lora_text_to_video_unet.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9bbcbf73561f6bc5d0a17ea6a2081feed2d1304e87602d8c502d9a5c4bd85576
|
| 3 |
-
size 16
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/model_index.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "TextToVideoSDPipeline",
|
| 3 |
-
"_diffusers_version": "0.20.0",
|
| 4 |
-
"_name_or_path": "/kaggle/input/my-text2video-1-7b",
|
| 5 |
-
"scheduler": [
|
| 6 |
-
"diffusers",
|
| 7 |
-
"DDIMScheduler"
|
| 8 |
-
],
|
| 9 |
-
"text_encoder": [
|
| 10 |
-
"transformers",
|
| 11 |
-
"CLIPTextModel"
|
| 12 |
-
],
|
| 13 |
-
"tokenizer": [
|
| 14 |
-
"transformers",
|
| 15 |
-
"CLIPTokenizer"
|
| 16 |
-
],
|
| 17 |
-
"unet": [
|
| 18 |
-
"models.unet_3d_condition",
|
| 19 |
-
"UNet3DConditionModel"
|
| 20 |
-
],
|
| 21 |
-
"vae": [
|
| 22 |
-
"diffusers",
|
| 23 |
-
"AutoencoderKL"
|
| 24 |
-
]
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/scheduler/scheduler_config.json
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "DDIMScheduler",
|
| 3 |
-
"_diffusers_version": "0.20.0",
|
| 4 |
-
"beta_end": 0.012,
|
| 5 |
-
"beta_schedule": "scaled_linear",
|
| 6 |
-
"beta_start": 0.00085,
|
| 7 |
-
"clip_sample": false,
|
| 8 |
-
"clip_sample_range": 1.0,
|
| 9 |
-
"dynamic_thresholding_ratio": 0.995,
|
| 10 |
-
"num_train_timesteps": 1000,
|
| 11 |
-
"prediction_type": "epsilon",
|
| 12 |
-
"rescale_betas_zero_snr": false,
|
| 13 |
-
"sample_max_value": 1.0,
|
| 14 |
-
"set_alpha_to_one": false,
|
| 15 |
-
"skip_prk_steps": true,
|
| 16 |
-
"steps_offset": 1,
|
| 17 |
-
"thresholding": false,
|
| 18 |
-
"timestep_spacing": "leading",
|
| 19 |
-
"trained_betas": null
|
| 20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/text_encoder/config.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/kaggle/input/my-text2video-1-7b",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"CLIPTextModel"
|
| 5 |
-
],
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 0,
|
| 8 |
-
"dropout": 0.0,
|
| 9 |
-
"eos_token_id": 2,
|
| 10 |
-
"hidden_act": "gelu",
|
| 11 |
-
"hidden_size": 1024,
|
| 12 |
-
"initializer_factor": 1.0,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 4096,
|
| 15 |
-
"layer_norm_eps": 1e-05,
|
| 16 |
-
"max_position_embeddings": 77,
|
| 17 |
-
"model_type": "clip_text_model",
|
| 18 |
-
"num_attention_heads": 16,
|
| 19 |
-
"num_hidden_layers": 23,
|
| 20 |
-
"pad_token_id": 1,
|
| 21 |
-
"projection_dim": 512,
|
| 22 |
-
"torch_dtype": "float32",
|
| 23 |
-
"transformers_version": "4.30.0",
|
| 24 |
-
"vocab_size": 49408
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/text_encoder/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7ec178e5f07ed24deb82bf41fdfde9392c0471755d5bf8d0576b21d7c6dafd46
|
| 3 |
-
size 1361597016
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/tokenizer/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-28040/tokenizer/special_tokens_map.json
DELETED
|
@@ -1,24 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<|startoftext|>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": true,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": "!",
|
| 17 |
-
"unk_token": {
|
| 18 |
-
"content": "<|endoftext|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": true,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/tokenizer/tokenizer_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": {
|
| 4 |
-
"__type": "AddedToken",
|
| 5 |
-
"content": "<|startoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": true,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false
|
| 10 |
-
},
|
| 11 |
-
"clean_up_tokenization_spaces": true,
|
| 12 |
-
"do_lower_case": true,
|
| 13 |
-
"eos_token": {
|
| 14 |
-
"__type": "AddedToken",
|
| 15 |
-
"content": "<|endoftext|>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": true,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false
|
| 20 |
-
},
|
| 21 |
-
"errors": "replace",
|
| 22 |
-
"model_max_length": 77,
|
| 23 |
-
"pad_token": "<|endoftext|>",
|
| 24 |
-
"tokenizer_class": "CLIPTokenizer",
|
| 25 |
-
"unk_token": {
|
| 26 |
-
"__type": "AddedToken",
|
| 27 |
-
"content": "<|endoftext|>",
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"normalized": true,
|
| 30 |
-
"rstrip": false,
|
| 31 |
-
"single_word": false
|
| 32 |
-
}
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/tokenizer/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-28040/unet/config.json
DELETED
|
@@ -1,34 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "UNet3DConditionModel",
|
| 3 |
-
"_diffusers_version": "0.20.0",
|
| 4 |
-
"_name_or_path": "/kaggle/input/my-text2video-1-7b",
|
| 5 |
-
"act_fn": "silu",
|
| 6 |
-
"attention_head_dim": 64,
|
| 7 |
-
"block_out_channels": [
|
| 8 |
-
320,
|
| 9 |
-
640,
|
| 10 |
-
1280,
|
| 11 |
-
1280
|
| 12 |
-
],
|
| 13 |
-
"cross_attention_dim": 1024,
|
| 14 |
-
"down_block_types": [
|
| 15 |
-
"CrossAttnDownBlock3D",
|
| 16 |
-
"CrossAttnDownBlock3D",
|
| 17 |
-
"CrossAttnDownBlock3D",
|
| 18 |
-
"DownBlock3D"
|
| 19 |
-
],
|
| 20 |
-
"downsample_padding": 1,
|
| 21 |
-
"in_channels": 4,
|
| 22 |
-
"layers_per_block": 2,
|
| 23 |
-
"mid_block_scale_factor": 1,
|
| 24 |
-
"norm_eps": 1e-05,
|
| 25 |
-
"norm_num_groups": 32,
|
| 26 |
-
"out_channels": 4,
|
| 27 |
-
"sample_size": 32,
|
| 28 |
-
"up_block_types": [
|
| 29 |
-
"UpBlock3D",
|
| 30 |
-
"CrossAttnUpBlock3D",
|
| 31 |
-
"CrossAttnUpBlock3D",
|
| 32 |
-
"CrossAttnUpBlock3D"
|
| 33 |
-
]
|
| 34 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/unet/diffusion_pytorch_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:479eaa570a8ba1d39b53ded7d96f82454fb8248e90318b4ed15611792c212769
|
| 3 |
-
size 5645118400
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/vae/config.json
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "AutoencoderKL",
|
| 3 |
-
"_diffusers_version": "0.20.0",
|
| 4 |
-
"_name_or_path": "/kaggle/input/my-text2video-1-7b",
|
| 5 |
-
"act_fn": "silu",
|
| 6 |
-
"block_out_channels": [
|
| 7 |
-
128,
|
| 8 |
-
256,
|
| 9 |
-
512,
|
| 10 |
-
512
|
| 11 |
-
],
|
| 12 |
-
"down_block_types": [
|
| 13 |
-
"DownEncoderBlock2D",
|
| 14 |
-
"DownEncoderBlock2D",
|
| 15 |
-
"DownEncoderBlock2D",
|
| 16 |
-
"DownEncoderBlock2D"
|
| 17 |
-
],
|
| 18 |
-
"force_upcast": true,
|
| 19 |
-
"in_channels": 3,
|
| 20 |
-
"latent_channels": 4,
|
| 21 |
-
"layers_per_block": 2,
|
| 22 |
-
"norm_num_groups": 32,
|
| 23 |
-
"out_channels": 3,
|
| 24 |
-
"sample_size": 512,
|
| 25 |
-
"scaling_factor": 0.18215,
|
| 26 |
-
"up_block_types": [
|
| 27 |
-
"UpDecoderBlock2D",
|
| 28 |
-
"UpDecoderBlock2D",
|
| 29 |
-
"UpDecoderBlock2D",
|
| 30 |
-
"UpDecoderBlock2D"
|
| 31 |
-
]
|
| 32 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-28040/vae/diffusion_pytorch_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fc436097e5cbb105c44df4403ae84acf7e81de1f64acfedc334888e9a8eea223
|
| 3 |
-
size 334643268
|
|
|
|
|
|
|
|
|
|
|
|