black images with Z-Image-Turbo-fp16.safetensors & Z-Image-Turbo.safetensors in ComfyUI
the fp8 scaled also generates black images
The same, all black pictures.
The bf16 model works fine from:
https://comfyanonymous.github.io/ComfyUI_examples/z_image/#basic-example-workflow
Comparing that to the fp16 model silveroxides created it appears that the model layers are named differently compared to the comfy models.
These layers:
all_x_embedder.2-1
all_final_layer.2-1
Should be named:
x_embedder.2-1
final_layer.2-1
-- edit --
No it's more than that. Comfy is also combining the qkv weights into a single larger array. There's probably more stuff that I'm not aware of, but for sure there is a format issue happening.
The bf16 model works fine from:
https://comfyanonymous.github.io/ComfyUI_examples/z_image/#basic-example-workflowComparing that to the fp16 model silveroxides created it appears that the model layers are named differently compared to the comfy models.
These layers:
all_x_embedder.2-1
all_final_layer.2-1Should be named:
x_embedder.2-1
final_layer.2-1-- edit --
No it's more than that. Comfy is also combining the qkv weights into a single larger array. There's probably more stuff that I'm not aware of, but for sure there is a format issue happening.
ohh, but fp16 works a little more fast on my 5090 in comparison with bf16, need solution :/