This extension integrates a/MV-Adapter into ComfyUI, allowing users to generate multi-view consistent images from text prompts or single images directly within the ComfyUI interface.
This extension integrates MV-Adapter into ComfyUI, allowing users to generate multi-view consistent images from text prompts or single images directly within the ComfyUI interface.
ComfyUI/custom_nodes/
directory.pip install -r requirements.txt
.We provide the example workflows in workflows
directory.
Note that our code depends on diffusers, and will automatically download the model weights from huggingface to the hf cache path at the first time. The ckpt_name
in the node corresponds to the model name in huggingface, such as stabilityai/stable-diffusion-xl-base-1.0
.
We also provide the nodes Ldm**Loader
to support loading text-to-image models in ldm
format. Please see the workflow files with the suffix _ldm.json
.
If your GPU resources are limited, we recommend using the following configuration:
upcast_fp32
to False
.enable_vae_slicing
in the Diffusers Model Makeup node to True
.However, since SDXL is used as the base model, it still requires about 13G to 14G GPU memory.
With SDXL or other base models
workflows/t2mv_sdxl_diffusers.json
for loading diffusers-format modelsworkflows/t2mv_sdxl_ldm.json
for loading ldm-format modelsWith LoRA
workflows/t2mv_sdxl_ldm_lora.json
for loading ldm-format models with LoRA for text-to-multi-view generation
With SDXL or other base models
workflows/i2mv_sdxl_diffusers.json
for loading diffusers-format modelsworkflows/i2mv_sdxl_ldm.json
for loading ldm-format modelsWith LoRA
workflows/i2mv_sdxl_ldm_lora.json
for loading ldm-format models with LoRA for image-to-multi-view generation