Image-Text-to-Video
Diffusers
Safetensors
MiniMax H3
modular-diffusers
ref2va
fl2va
Merge
synchronized-audio-video
experimental
Instructions to use diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024", 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
Upload modular_model_index.json with huggingface_hub
Browse files- modular_model_index.json +131 -0
modular_model_index.json
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "MiniMaxH3ModularPipeline",
|
| 3 |
+
"_diffusers_version": "0.40.0.dev0",
|
| 4 |
+
"_blocks_class_name": "MiniMaxH3Blocks",
|
| 5 |
+
"text_encoder": [
|
| 6 |
+
"transformers",
|
| 7 |
+
"Qwen3VLForConditionalGeneration",
|
| 8 |
+
{
|
| 9 |
+
"type_hint": [
|
| 10 |
+
"transformers",
|
| 11 |
+
"Qwen3VLForConditionalGeneration"
|
| 12 |
+
],
|
| 13 |
+
"pretrained_model_name_or_path": "multimodalart/MiniMax-H3-Pruned",
|
| 14 |
+
"subfolder": "text_encoder",
|
| 15 |
+
"variant": null,
|
| 16 |
+
"revision": null
|
| 17 |
+
}
|
| 18 |
+
],
|
| 19 |
+
"tokenizer": [
|
| 20 |
+
"transformers",
|
| 21 |
+
"Qwen2TokenizerFast",
|
| 22 |
+
{
|
| 23 |
+
"type_hint": [
|
| 24 |
+
"transformers",
|
| 25 |
+
"Qwen2TokenizerFast"
|
| 26 |
+
],
|
| 27 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 28 |
+
"subfolder": "tokenizer",
|
| 29 |
+
"variant": null,
|
| 30 |
+
"revision": null
|
| 31 |
+
}
|
| 32 |
+
],
|
| 33 |
+
"processor": [
|
| 34 |
+
"transformers",
|
| 35 |
+
"Qwen3VLProcessor",
|
| 36 |
+
{
|
| 37 |
+
"type_hint": [
|
| 38 |
+
"transformers",
|
| 39 |
+
"Qwen3VLProcessor"
|
| 40 |
+
],
|
| 41 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 42 |
+
"subfolder": "processor",
|
| 43 |
+
"variant": null,
|
| 44 |
+
"revision": null
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"vae": [
|
| 48 |
+
"diffusers",
|
| 49 |
+
"AutoencoderKLMiniMaxH3",
|
| 50 |
+
{
|
| 51 |
+
"type_hint": [
|
| 52 |
+
"diffusers",
|
| 53 |
+
"AutoencoderKLMiniMaxH3"
|
| 54 |
+
],
|
| 55 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 56 |
+
"subfolder": "vae",
|
| 57 |
+
"variant": null,
|
| 58 |
+
"revision": null
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"audio_vae": [
|
| 62 |
+
"diffusers",
|
| 63 |
+
"AutoencoderKLMiniMaxH3Audio",
|
| 64 |
+
{
|
| 65 |
+
"type_hint": [
|
| 66 |
+
"diffusers",
|
| 67 |
+
"AutoencoderKLMiniMaxH3Audio"
|
| 68 |
+
],
|
| 69 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 70 |
+
"subfolder": "audio_vae",
|
| 71 |
+
"variant": null,
|
| 72 |
+
"revision": null
|
| 73 |
+
}
|
| 74 |
+
],
|
| 75 |
+
"transformer": [
|
| 76 |
+
"diffusers",
|
| 77 |
+
"AutoModel",
|
| 78 |
+
{
|
| 79 |
+
"type_hint": [
|
| 80 |
+
"diffusers",
|
| 81 |
+
"AutoModel"
|
| 82 |
+
],
|
| 83 |
+
"pretrained_model_name_or_path": "diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024",
|
| 84 |
+
"subfolder": "transformer",
|
| 85 |
+
"variant": null,
|
| 86 |
+
"revision": null
|
| 87 |
+
}
|
| 88 |
+
],
|
| 89 |
+
"transformer_ref": [
|
| 90 |
+
"diffusers",
|
| 91 |
+
"AutoModel",
|
| 92 |
+
{
|
| 93 |
+
"type_hint": [
|
| 94 |
+
"diffusers",
|
| 95 |
+
"AutoModel"
|
| 96 |
+
],
|
| 97 |
+
"pretrained_model_name_or_path": "diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024",
|
| 98 |
+
"subfolder": "transformer",
|
| 99 |
+
"variant": null,
|
| 100 |
+
"revision": null
|
| 101 |
+
}
|
| 102 |
+
],
|
| 103 |
+
"scheduler": [
|
| 104 |
+
"diffusers",
|
| 105 |
+
"MiniMaxH3Scheduler",
|
| 106 |
+
{
|
| 107 |
+
"type_hint": [
|
| 108 |
+
"diffusers",
|
| 109 |
+
"MiniMaxH3Scheduler"
|
| 110 |
+
],
|
| 111 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 112 |
+
"subfolder": "scheduler",
|
| 113 |
+
"variant": null,
|
| 114 |
+
"revision": null
|
| 115 |
+
}
|
| 116 |
+
],
|
| 117 |
+
"audio_scheduler": [
|
| 118 |
+
"diffusers",
|
| 119 |
+
"MiniMaxH3Scheduler",
|
| 120 |
+
{
|
| 121 |
+
"type_hint": [
|
| 122 |
+
"diffusers",
|
| 123 |
+
"MiniMaxH3Scheduler"
|
| 124 |
+
],
|
| 125 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 126 |
+
"subfolder": "audio_scheduler",
|
| 127 |
+
"variant": null,
|
| 128 |
+
"revision": null
|
| 129 |
+
}
|
| 130 |
+
]
|
| 131 |
+
}
|