FLUX.1: make FLUX lifelike/realistic - Efficient Negative Prompt with SD1.5 Upscale
5.0
0 reviews
Description
In my opinion, the SD1.5 upscale makes the images look much more lifelike :-)
Pay attention to the EMBEDDINGS I used in the upscaler ;-)
Source Worklow:
FLUX.1: Efficient Negative Prompt
thanx to data it for the source
Node Diagram
Discussion
TypeError: separated_sample() got an unexpected keyword argument 'scheduler_func'
what is yout model flux ? this is always error
Error occurred when executing UNETLoader:
'conv_in.weight'
File "/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/ComfyUI/execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/ComfyUI/nodes.py", line 814, in load_unet
model = comfy.sd.load_unet(unet_path)
File "/ComfyUI/comfy/sd.py", line 552, in load_unet
model = load_unet_state_dict(sd)
File "/ComfyUI/comfy/sd.py", line 525, in load_unet_state_dict
model_config = model_detection.model_config_from_diffusers_unet(sd)
File "/ComfyUI/comfy/model_detection.py", line 380, in model_config_from_diffusers_unet
unet_config = unet_config_from_diffusers_unet(state_dict)
File "/ComfyUI/comfy/model_detection.py", line 262, in unet_config_from_diffusers_unet
match["model_channels"] = state_dict["conv_in.weight"].shape[0]
you can use org flux-dev1 or flux-dev1-fp8
Node Details
Primitive Nodes (1)
ImpactNegativeConditioningPlaceholder (1)
Custom Nodes (24)
ComfyUI
- EmptyLatentImage (1)
- UpscaleModelLoader (1)
- VAEDecode (1)
- DualCLIPLoader (1)
- VAELoader (1)
- SaveImage (2)
- PreviewImage (1)
- CLIPTextEncode (2)
- SD_4XUpscale_Conditioning (1)
- UNETLoader (1)
- ToBasicPipe (1)
- EditBasicPipe (1)
- FromBasicPipe_v2 (1)
- PreviewBridgeLatent (1)
- ImpactKSamplerAdvancedBasicPipe (2)
- Efficient Loader (1)
- FaceRestoreCFWithModel (1)
- FaceRestoreModelLoader (1)
- GetImageSizeAndCount (1)
- DynamicThresholdingFull (1)
- UltimateSDUpscale (1)
Model Details
Checkpoints (0)
LoRAs (0)