Resources you need:
📂Files :
Clip_vision : sigclip_vision_patch14_384.safetensors
in ComfyUI/models/clip_vision
REDUX : flux1-redux-dev.safetensors
in ComfyUI/models/style_models
PuLID : pulid_flux_v0.9.0.safetensors
in ComfyUI\models\pulid
📂Files for "base" version :
Model : flux1-dev-fp8.safetensors
in ComfyUI\models\diffusion_models
CLIP : t5xxl_fp8_e4m3fn.safetensors and clip_l.safetensors
in ComfyUI\models\clip
VAE : ae.safetensors
in ComfyUI\models\vae
📂Files for GGUF version :
Recommendation :
24 gb Vram: Q8_0
16 gb Vram: Q5_K_S
<12 gb Vram: Q4_K_S
GGUF_Model : flux1-dev-QX_0.gguf
in ComfyUI\models\unet
GGUF_clip : t5-v1_1-xxl-encoder-QX_0.gguf
in ComfyUI\models\clip
Text encoder : ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors
in ComfyUI\models\clip
VAE : ae.safetensors
in ComfyUI\models\vae
ANY upscale model :
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in ComfyUI\models\upscale_models
📦Custom Nodes :
Description
Bug fix and 2k update
FAQ
Comments (3)
It seems like Pulid is not working with the new comfyui update 0.27, for those haveing issues rollback to comfy 0.26, "git checkout v0.2.6" on comfy folder.
So I am running into loading any LoRAs. I can generate just fine without loras using comfy 0.26.
When clicking the lora_name field I can see all my loras (screenshot) but I can not load them. After selection one the field will remain at [object Object] and no loras is being used in generation.
The Lora-Auto-Trigger seems to detect them:
[Lora-Auto-Trigger] calculating lora hash
[Lora-Auto-Trigger] requesting infos
[Lora-Auto-Trigger] tags found!
Data saved to ./loras_tags.json
I do not get any error logs when trying to select a lora. Anyone have an idea what the issue is?
Hello, thanks for sharing. It seems that the nodes associated with ComfyUI-PuLID-Flux-Enhanced are not loading. From what I understand, this is due to the recent version of comfyui. Is there a solution without having to go back to Comfy version 0.26? The fix link on your page doesn't work (404).