Text-to-Image
Diffusers
Safetensors
Cosmos
Cosmos3OmniDiffusersPipeline
cosmos3_omni
cosmos3
quantization
fp8
8-bit precision
modelopt
image-to-video
Instructions to use Reza2kn/Cosmos3-Nano-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Reza2kn/Cosmos3-Nano-FP8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Reza2kn/Cosmos3-Nano-FP8", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Cosmos
How to use Reza2kn/Cosmos3-Nano-FP8 with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
File size: 1,750 Bytes
489a947 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | {
"_class_name": "AutoencoderKLWan",
"_diffusers_version": "0.37.1",
"_name_or_path": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
"attn_scales": [],
"base_dim": 160,
"clip_output": false,
"decoder_base_dim": 256,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"in_channels": 12,
"is_residual": true,
"latents_mean": [
-0.2289,
-0.0052,
-0.1323,
-0.2339,
-0.2799,
0.0174,
0.1838,
0.1557,
-0.1382,
0.0542,
0.2813,
0.0891,
0.157,
-0.0098,
0.0375,
-0.1825,
-0.2246,
-0.1207,
-0.0698,
0.5109,
0.2665,
-0.2108,
-0.2158,
0.2502,
-0.2055,
-0.0322,
0.1109,
0.1567,
-0.0729,
0.0899,
-0.2799,
-0.123,
-0.0313,
-0.1649,
0.0117,
0.0723,
-0.2839,
-0.2083,
-0.052,
0.3748,
0.0152,
0.1957,
0.1433,
-0.2944,
0.3573,
-0.0548,
-0.1681,
-0.0667
],
"latents_std": [
0.4765,
1.0364,
0.4514,
1.1677,
0.5313,
0.499,
0.4818,
0.5013,
0.8158,
1.0344,
0.5894,
1.0901,
0.6885,
0.6165,
0.8454,
0.4978,
0.5759,
0.3523,
0.7135,
0.6804,
0.5833,
1.4146,
0.8986,
0.5659,
0.7069,
0.5338,
0.4889,
0.4917,
0.4069,
0.4999,
0.6866,
0.4093,
0.5709,
0.6065,
0.6415,
0.4944,
0.5726,
1.2042,
0.5458,
1.6887,
0.3971,
1.06,
0.3943,
0.5537,
0.5444,
0.4089,
0.7468,
0.7744
],
"num_res_blocks": 2,
"out_channels": 12,
"patch_size": 2,
"scale_factor_spatial": 16,
"scale_factor_temporal": 4,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 48
}
|