Image-Text-to-Video
Diffusers
text-to-video
image-to-video
video-to-video
text-to-audio-video
multimodal
quantized
comfyui
int4
nvfp4
Instructions to use Abiray/Minimax-H3-nvfp4-INT4-INT8-Convrot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Abiray/Minimax-H3-nvfp4-INT4-INT8-Convrot with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Abiray/Minimax-H3-nvfp4-INT4-INT8-Convrot", 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
Can I Reuse the Comfy-Org Text Encoders and VAE?
#6
by nnn149 - opened
Do I need to re-download the qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors text encoder and the VAE models for this project?
I already have the versions from the official Comfy-Org repository. Although the filenames are identical, I noticed the SHA256 hashes are different.
Is it safe to reuse the Comfy-Org text_encoders and vae and only download the diffusion_models from this repository, or are the files actually different and required for compatibility?
Yeah you can, no issue in that.