Hunyuan 3D v2.1 text to 3D asset workflow

text-to-3d-asset-api.json

Figure 1 -

Szükéseges modell:

ComfyUI/models/checkpoints
[hunyuan_3d_v2.1.safetensors]
(https://huggingface.co/Comfy-Org/hunyuan3D_2.1_repackaged/resolve/main/hunyuan_3d_v2.1.safetensors)

img.ozeki.hu esetén: 

ComfyUI/models/diffusion_models/

qwen_text2image_model.safetensors

wget https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors

video.ozeki.hu esetén: 

ComfyUI/models/diffusion_models/

qwen_text2image_model.safetensors

hf download Qwen/Qwen-Image --include 'transformer/*' --local-dir ./

Ezzel a kóddal kell egyesíteni a safetensor fileokat:

nano combine.py 
from safetensors.torch import load_file, save_file
import torch
import glob
import os

# Fájlok listája
split_files = sorted(glob.glob("diffusion_pytorch_model-*.safetensors"))

# Összevonás
combined_state_dict = {}
for file in split_files:
    state_dict = load_file(file)
    combined_state_dict.update(state_dict)

# Mentés egyetlen fájlba
output_file = "qwen_text2image_model.safetensors"
save_file(combined_state_dict, output_file)
print(f"Összevonva: {output_file}")

ComfyUI/models/vae/

qwen_image_vae.safetensors

wget https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors

ComfyUI/models/text_encoders/

qwen_text_encoder.safetensors

wget  https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors

Szükséges custom node:

ComfyUI-RMBG 

cd /home/user/comfy/ComfyUI/custom_nodes

git clone https://github.com/1038lab/ComfyUI-RMBG

cd /home/user/comfy/ComfyUI/custom_nodes/ComfyUI-RMBG

python -m pip install -r requirements.txt

A folyamat után után újra kell indítani a comfyui-t.

A node az első indulásnál letölti a szükséges modellt.

More information