You can read my guide to using this workflow: link

In general, you're missing the “RV-Tools” node, which is not detected by ComfyUI manager. You can find it in “Custom node manager”.

To do this outpainting, this workflow first creates a first image with SDXL and then creates a new one with FLUX. The result is really nice.

The upscaler adds detail and corrects joins between the original image and the new one quite well.

The easiest way to install all the files needed for workflow use is to use one of my installation scripts or my manager.

To install the missing nodes, I created a script : ComfyUI missing nodes auto installer - v2.0 | Flux Other | Civitai

Resources you need:

SDXL (any SDXL with vae in)

SD XL - v1.0 VAE fix | Stable Diffusion XL Checkpoint | Civitai
"sd_xl_base_1.0_0.9vae.safetensors" in ComfyUI\models\checkpoints

ControlNet Outpaint

diffusion_pytorch_model_promax.safetensors · UmeAiRT/FLUX-auto_installer at main
"diffusion_pytorch_model_promax.safetensors" in ComfyUI\models\controlnet

Flux.1

Kijai/flux-fp8 at main (huggingface.co)
"flux1-dev-fp8" in ComfyUI\models\unet

black-forest-labs/FLUX.1-dev at main (huggingface.co)
"ae" in \ComfyUI\models\vae

comfyanonymous/flux_text_encoders at main (huggingface.co)
"t5xxl_fp8_e4m3fn" in \ComfyUI\models\clip
"clip_l" in \ComfyUI\models\clip

For GGUF

I recommend :
24 gb Vram: Q8_0 + T5_Q8 or FP8
16 gb Vram: Q5_K_S + T5_Q5_K_M or T5_Q3_K_L
<12 gb Vram: Q4_K_S + T5_Q3_K_L

GGUF_Model
city96/FLUX.1-dev-gguf at main (huggingface.co)
"flux1-dev-Q8_0.gguf" in ComfyUI\models\unet

GGUF_clip
city96/t5-v1_1-xxl-encoder-gguf at main (huggingface.co)
"t5-v1_1-xxl-encoder-Q8_0.gguf" in \ComfyUI\models\clip

Better flux text encoder
ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors · zer0int/CLIP-GmP-ViT-L-14 at main (huggingface.co)
"ViT-L-14-GmP-ft-TE-only-HF-format.safetensors" in \ComfyUI\models\clip

Upscaler

ESRGAN/4x_NMKD-Siax_200k.pth · uwg/upscaler at main (huggingface.co)
"4x_NMKD-Siax_200k.pth" in \ComfyUI\models\upscale_models