Use Stable Cascade's Stage C to understand prompt words and compose images, and use SDXL to add image details.

Stable Cascade Stage C: https://civitai.com/models/316681/invictusredmond-stable-cascade-stage-c-finetune-generalist-model

(ComfyUI/models/unet)

Stable Cascade text encoder: https://huggingface.co/stabilityai/stable-cascade/tree/main/text_encoder

(ComfyUI/models/clip)

Previewer VAE: https://huggingface.co/stabilityai/stable-cascade/blob/main/previewer.safetensors

(ComfyUI/models/vae)

SDXL lightning: https://civitai.com/models/112902?modelVersionId=354657

(ComfyUI/models/checkpoints)

checkpoint: https://civitai.com/models/215418?modelVersionId=273102

(ComfyUI/models/checkpoints)

instantid node: https://github.com/cubiq/ComfyUI_InstantID

(ComfyUI/custom_nodes/)

instantid model: https://huggingface.co/InstantX/InstantID/resolve/main/ip-adapter.bin?download=true

The main model can be downloaded from HuggingFace and should be placed into the ComfyUI/models/instantid directory. (Note that the model is called ip_adapter as it is based on the IPAdapter models).

(ComfyUI/models/instantid)

antelopev2 model: https://huggingface.co/MonsterMMORPG/tools/resolve/main/antelopev2.zip

(ComfyUI/models/insightface/models/antelopev2)

controlnet model:  https://huggingface.co/InstantX/InstantID/resolve/main/ControlNetModel/diffusion_pytorch_model.safetensors?download=true

(ComfyUI/models/controlnet)