size mismatch for model.embed_tokens.weight: copying a param with shape torch.Size([151936, 4096]) from checkpoint, the shape in current model is torch.Size([128256, 4096]).
klein_9b with Qwen_3_8b on Mac desktop, running error with clipLoader. my comfyui has been updated 0.9.2. why?????????? I just used all the full models no quant..
The BF16 '9B Base Workflow' has Unet set to: 'flux-2-klein-base-9b-fp8.safetensors' (distilled) and its corresponding clip where it should have 'flux-2-klein-base-9b.safetensors' (base) and whatever clip it uses.
1. Click on ‘assets’ in the left-hand column. 2. Right-click on the image that opens and click on ‘copy’. 3. Click on the input image and press “Ctrl” and ‘V’ simultaneously. Done!
I hope I am asking this correctly.. Are these designed to be used with the 5xxx series Blackwell chips? Or will they also work with a 3xxx series? Or does it matter?
CLIPLoader
Error(s) in loading state_dict for Llama2:
size mismatch for model.embed_tokens.weight: copying a param with shape torch.Size([151936, 4096]) from checkpoint, the shape in current model is torch.Size([128256, 4096]).
I get this error:
UNETLoader
Got [32, 32, 32, 32] but expected positional dim 64
* Load diffusion model node is highlighted border in red
It has set as flux-2-klein-4b-fp8.safetensors
* Load clip set to qwen_3_4b.safetensors
* VAE as flux2-vae.safetensors
Desktop install
ComfyUI v0.8.2 / ComfyUI_frontend v1.35.9 / ComfyUI_desktop v0.7.2
klein_9b with Qwen_3_8b on Mac desktop, running error with clipLoader. my comfyui has been updated 0.9.2. why?????????? I just used all the full models no quant..
fix: comfyui version 0.8.2
The BF16 '9B Base Workflow' has Unet set to: 'flux-2-klein-base-9b-fp8.safetensors' (distilled) and its corresponding clip where it should have 'flux-2-klein-base-9b.safetensors' (base) and whatever clip it uses.
where is the 9B worflow image generation ? Download Text-to-Image Workflow
how do one do the iteration to the image created? Its always been a mystery to me!
1. Click on ‘assets’ in the left-hand column. 2. Right-click on the image that opens and click on ‘copy’. 3. Click on the input image and press “Ctrl” and ‘V’ simultaneously. Done!
I hope I am asking this correctly.. Are these designed to be used with the 5xxx series Blackwell chips? Or will they also work with a 3xxx series? Or does it matter?
The NVFP4 is meant for the 50 series cards. You wont see the performance gain on 40 series or H100.
It works for me on 3090, no problemos.