Text-to-Video
Diffusers
Safetensors
MiniMaxH3ModularPipeline
video-generation
audio
fastvideo
bf16
pruned
Instructions to use FastVideo/FastVideo-FastH3-Trim-8-Step with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/FastVideo-FastH3-Trim-8-Step with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/FastVideo-FastH3-Trim-8-Step", 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
Download text_encoder/config.json from FastVideo/FastVideo-FastH3-Trim-8-Step: direct link, hf CLI and curl.
- Browser
- Download file 1.93 kB
-
https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step/resolve/main/text_encoder/config.json
- Command line
-
hf download hf://FastVideo/FastVideo-FastH3-Trim-8-Step/text_encoder/config.json
-
curl -L -o config.json https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step/resolve/main/text_encoder/config.json
1.93 kB
| { | |
| "architectures": [ | |
| "Qwen3VLForConditionalGeneration" | |
| ], | |
| "image_token_id": 151655, | |
| "model_type": "qwen3_vl", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 25600, | |
| "max_position_embeddings": 262144, | |
| "model_type": "qwen3_vl_text", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "use_cache": true, | |
| "vocab_size": 151936 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.0.dev0", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [ | |
| 8, | |
| 16, | |
| 24 | |
| ], | |
| "depth": 27, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "qwen3_vl", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 5120, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "num_hidden_layers_override": 50, | |
| "quantization_config": { | |
| "quant_method": "nvfp4", | |
| "activation_scheme": "dynamic", | |
| "fmt": "e2m1", | |
| "group_size": 16, | |
| "scale_fmt": "e4m3", | |
| "scale_layout": "128x4", | |
| "modules_to_not_convert": [ | |
| "model.visual", | |
| "lm_head" | |
| ], | |
| "producer": { | |
| "converter": "convert_minimax_h3_text_encoder_nvfp4.py", | |
| "flashinfer": "0.7.1rc2", | |
| "kept_language_layers": 50 | |
| } | |
| } | |
| } |