Black Image Issue, Not Sure Why.

[DavidAllenNeron]

For some reason no matter what settings I've used, all I'm getting is a black image.

I assume it's something I'm overlooking but I can't figure out why.

[lawrence-cj]

Inference script?

[DavidAllenNeron]

I'm pretty new to all of this and I'm not sure what you're asking. Sorry for my ignorance.

[lawrence-cj]

I mean how did you use the model?

[DavidAllenNeron]

My apologies, I'm using ComfyUI desktop, I've tried several workflows ... all seem to produce a black or grey image.

I'm running a 4090.

[vnguyen972]

I too got black image only... here's what I have following a youtube video instruction

[w0ver]

same thing

got prompt
Missing VAE keys ['encoder.project_in.weight', 'encoder.project_in.bias', 'encoder.stages.0.0.conv1.conv.weight', 'encoder.stages.0.0.conv1.conv.bias', 'encoder.stages.0.0.conv2.conv.weight', 'encoder.stages.0.0.conv2.norm.weight', 'encoder.stages.0.0.conv2.norm.bias', 'encoder.stages.0.1.conv1.conv.weight', 'encoder.stages.0.1.conv1.conv.bias', 'encoder.stages.0.1.conv2.conv.weight', 'encoder.stages.0.1.conv2.norm.weight', 'encoder.stages.0.1.conv2.norm.bias', 'encoder.stages.0.2.main.weight', 'encoder.stages.0.2.main.bias', 'encoder.stages.1.0.conv1.conv.weight', 'encoder.stages.1.0.conv1.conv.bias', 'encoder.stages.1.0.conv2.conv.weight', 'encoder.stages.1.0.conv2.norm.weight', 'encoder.stages.1.0.conv2.norm.bias', 'encoder.stages.1.1.conv1.conv.weight', 'encoder.stages.1.1.conv1.conv.bias', 'encoder.stages.1.1.conv2.conv.weight', 'encoder.stages.1.1.conv2.norm.weight', 'encoder.stages.1.1.conv2.norm.bias', 'encoder.stages.1.2.main.weight', 'encoder.stages.1.2.main.bias', 'encoder.stages.2.0.conv1.conv.weight', 'encoder.stages.2.0.conv1.conv.bias', 'encoder.stages.2.0.conv2.conv.weight', 'encoder.stages.2.0.conv2.norm.weight', 'encoder.stages.2.0.conv2.norm.bias', 'encoder.stages.2.1.conv1.conv.weight', 'encoder.stages.2.1.conv1.conv.bias', 'encoder.stages.2.1.conv2.conv.weight', 'encoder.stages.2.1.conv2.norm.weight', 'encoder.stages.2.1.conv2.norm.bias', 'encoder.stages.2.2.main.weight', 'encoder.stages.2.2.main.bias', 'encoder.stages.3.0.context_module.qkv.0.weight', 'encoder.stages.3.0.context_module.aggreg.0.0.weight', 'encoder.stages.3.0.context_module.aggreg.0.1.weight', 'encoder.stages.3.0.context_module.proj.0.weight', 'encoder.stages.3.0.context_module.proj.1.weight', 'encoder.stages.3.0.context_module.proj.1.bias', 'encoder.stages.3.0.local_module.inverted_conv.conv.weight', 'encoder.stages.3.0.local_module.inverted_conv.conv.bias', 'encoder.stages.3.0.local_module.depth_conv.conv.weight', 'encoder.stages.3.0.local_module.depth_conv.conv.bias', 'encoder.stages.3.0.local_module.point_conv.conv.weight', 'encoder.stages.3.0.local_module.point_conv.norm.weight', 'encoder.stages.3.0.local_module.point_conv.norm.bias', 'encoder.stages.3.1.context_module.qkv.0.weight', 'encoder.stages.3.1.context_module.aggreg.0.0.weight', 'encoder.stages.3.1.context_module.aggreg.0.1.weight', 'encoder.stages.3.1.context_module.proj.0.weight', 'encoder.stages.3.1.context_module.proj.1.weight', 'encoder.stages.3.1.context_module.proj.1.bias', 'encoder.stages.3.1.local_module.inverted_conv.conv.weight', 'encoder.stages.3.1.local_module.inverted_conv.conv.bias', 'encoder.stages.3.1.local_module.depth_conv.conv.weight', 'encoder.stages.3.1.local_module.depth_conv.conv.bias', 'encoder.stages.3.1.local_module.point_conv.conv.weight', 'encoder.stages.3.1.local_module.point_conv.norm.weight', 'encoder.stages.3.1.local_module.point_conv.norm.bias', 'encoder.stages.3.2.context_module.qkv.0.weight', 'encoder.stages.3.2.context_module.aggreg.0.0.weight', 'encoder.stages.3.2.context_module.aggreg.0.1.weight', 'encoder.stages.3.2.context_module.proj.0.weight', 'encoder.stages.3.2.context_module.proj.1.weight', 'encoder.stages.3.2.context_module.proj.1.bias', 'encoder.stages.3.2.local_module.inverted_conv.conv.weight', 'encoder.stages.3.2.local_module.inverted_conv.conv.bias', 'encoder.stages.3.2.local_module.depth_conv.conv.weight', 'encoder.stages.3.2.local_module.depth_conv.conv.bias', 'encoder.stages.3.2.local_module.point_conv.conv.weight', 'encoder.stages.3.2.local_module.point_conv.norm.weight', 'encoder.stages.3.2.local_module.point_conv.norm.bias', 'encoder.stages.3.3.main.weight', 'encoder.stages.3.3.main.bias', 'encoder.stages.4.0.context_module.qkv.0.weight', 'encoder.stages.4.0.context_module.aggreg.0.0.weight', 'encoder.stages.4.0.context_module.aggreg.0.1.weight', 'encoder.stages.4.0.context_module.proj.0.weight', 'encoder.stages.4.0.context_module.proj.1.weight', 'encoder.stages.4.0.context_module.proj.1.bias', 'encoder.stages.4.0.local_module.inverted_conv.conv.weight', 'encoder.stages.4.0.local_module.inverted_conv.conv.bias', 'encoder.stages.4.0.local_module.depth_conv.conv.weight', 'encoder.stages.4.0.local_module.depth_conv.conv.bias', 'encoder.stages.4.0.local_module.point_conv.conv.weight', 'encoder.stages.4.0.local_module.point_conv.norm.weight', 'encoder.stages.4.0.local_module.point_conv.norm.bias', 'encoder.stages.4.1.context_module.qkv.0.weight', 'encoder.stages.4.1.context_module.aggreg.0.0.weight', 'encoder.stages.4.1.context_module.aggreg.0.1.weight', 'encoder.stages.4.1.context_module.proj.0.weight', 'encoder.stages.4.1.context_module.proj.1.weight', 'encoder.stages.4.1.context_module.proj.1.bias', 'encoder.stages.4.1.local_module.inverted_conv.conv.weight', 'encoder.stages.4.1.local_module.inverted_conv.conv.bias', 'encoder.stages.4.1.local_module.depth_conv.conv.weight', 'encoder.stages.4.1.local_module.depth_conv.conv.bias', 'encoder.stages.4.1.local_module.point_conv.conv.weight', 'encoder.stages.4.1.local_module.point_conv.norm.weight', 'encoder.stages.4.1.local_module.point_conv.norm.bias', 'encoder.stages.4.2.context_module.qkv.0.weight', 'encoder.stages.4.2.context_module.aggreg.0.0.weight', 'encoder.stages.4.2.context_module.aggreg.0.1.weight', 'encoder.stages.4.2.context_module.proj.0.weight', 'encoder.stages.4.2.context_module.proj.1.weight', 'encoder.stages.4.2.context_module.proj.1.bias', 'encoder.stages.4.2.local_module.inverted_conv.conv.weight', 'encoder.stages.4.2.local_module.inverted_conv.conv.bias', 'encoder.stages.4.2.local_module.depth_conv.conv.weight', 'encoder.stages.4.2.local_module.depth_conv.conv.bias', 'encoder.stages.4.2.local_module.point_conv.conv.weight', 'encoder.stages.4.2.local_module.point_conv.norm.weight', 'encoder.stages.4.2.local_module.point_conv.norm.bias', 'encoder.stages.4.3.main.weight', 'encoder.stages.4.3.main.bias', 'encoder.stages.5.0.context_module.qkv.0.weight', 'encoder.stages.5.0.context_module.aggreg.0.0.weight', 'encoder.stages.5.0.context_module.aggreg.0.1.weight', 'encoder.stages.5.0.context_module.proj.0.weight', 'encoder.stages.5.0.context_module.proj.1.weight', 'encoder.stages.5.0.context_module.proj.1.bias', 'encoder.stages.5.0.local_module.inverted_conv.conv.weight', 'encoder.stages.5.0.local_module.inverted_conv.conv.bias', 'encoder.stages.5.0.local_module.depth_conv.conv.weight', 'encoder.stages.5.0.local_module.depth_conv.conv.bias', 'encoder.stages.5.0.local_module.point_conv.conv.weight', 'encoder.stages.5.0.local_module.point_conv.norm.weight', 'encoder.stages.5.0.local_module.point_conv.norm.bias', 'encoder.stages.5.1.context_module.qkv.0.weight', 'encoder.stages.5.1.context_module.aggreg.0.0.weight', 'encoder.stages.5.1.context_module.aggreg.0.1.weight', 'encoder.stages.5.1.context_module.proj.0.weight', 'encoder.stages.5.1.context_module.proj.1.weight', 'encoder.stages.5.1.context_module.proj.1.bias', 'encoder.stages.5.1.local_module.inverted_conv.conv.weight', 'encoder.stages.5.1.local_module.inverted_conv.conv.bias', 'encoder.stages.5.1.local_module.depth_conv.conv.weight', 'encoder.stages.5.1.local_module.depth_conv.conv.bias', 'encoder.stages.5.1.local_module.point_conv.conv.weight', 'encoder.stages.5.1.local_module.point_conv.norm.weight', 'encoder.stages.5.1.local_module.point_conv.norm.bias', 'encoder.stages.5.2.context_module.qkv.0.weight', 'encoder.stages.5.2.context_module.aggreg.0.0.weight', 'encoder.stages.5.2.context_module.aggreg.0.1.weight', 'encoder.stages.5.2.context_module.proj.0.weight', 'encoder.stages.5.2.context_module.proj.1.weight', 'encoder.stages.5.2.context_module.proj.1.bias', 'encoder.stages.5.2.local_module.inverted_conv.conv.weight', 'encoder.stages.5.2.local_module.inverted_conv.conv.bias', 'encoder.stages.5.2.local_module.depth_conv.conv.weight', 'encoder.stages.5.2.local_module.depth_conv.conv.bias', 'encoder.stages.5.2.local_module.point_conv.conv.weight', 'encoder.stages.5.2.local_module.point_conv.norm.weight', 'encoder.stages.5.2.local_module.point_conv.norm.bias', 'encoder.project_out.main.0.conv.weight', 'encoder.project_out.main.0.conv.bias', 'decoder.project_in.main.conv.weight', 'decoder.project_in.main.conv.bias', 'decoder.stages.0.0.main.conv.weight', 'decoder.stages.0.0.main.conv.bias', 'decoder.stages.0.1.conv1.conv.weight', 'decoder.stages.0.1.conv1.conv.bias', 'decoder.stages.0.1.conv2.conv.weight', 'decoder.stages.0.1.conv2.norm.weight', 'decoder.stages.0.1.conv2.norm.bias', 'decoder.stages.0.2.conv1.conv.weight', 'decoder.stages.0.2.conv1.conv.bias', 'decoder.stages.0.2.conv2.conv.weight', 'decoder.stages.0.2.conv2.norm.weight', 'decoder.stages.0.2.conv2.norm.bias', 'decoder.stages.0.3.conv1.conv.weight', 'decoder.stages.0.3.conv1.conv.bias', 'decoder.stages.0.3.conv2.conv.weight', 'decoder.stages.0.3.conv2.norm.weight', 'decoder.stages.0.3.conv2.norm.bias', 'decoder.stages.1.0.main.conv.weight', 'decoder.stages.1.0.main.conv.bias', 'decoder.stages.1.1.conv1.conv.weight', 'decoder.stages.1.1.conv1.conv.bias', 'decoder.stages.1.1.conv2.conv.weight', 'decoder.stages.1.1.conv2.norm.weight', 'decoder.stages.1.1.conv2.norm.bias', 'decoder.stages.1.2.conv1.conv.weight', 'decoder.stages.1.2.conv1.conv.bias', 'decoder.stages.1.2.conv2.conv.weight', 'decoder.stages.1.2.conv2.norm.weight', 'decoder.stages.1.2.conv2.norm.bias', 'decoder.stages.1.3.conv1.conv.weight', 'decoder.stages.1.3.conv1.conv.bias', 'decoder.stages.1.3.conv2.conv.weight', 'decoder.stages.1.3.conv2.norm.weight', 'decoder.stages.1.3.conv2.norm.bias', 'decoder.stages.2.0.main.conv.weight', 'decoder.stages.2.0.main.conv.bias', 'decoder.stages.2.1.conv1.conv.weight', 'decoder.stages.2.1.conv1.conv.bias', 'decoder.stages.2.1.conv2.conv.weight', 'decoder.stages.2.1.conv2.norm.weight', 'decoder.stages.2.1.conv2.norm.bias', 'decoder.stages.2.2.conv1.conv.weight', 'decoder.stages.2.2.conv1.conv.bias', 'decoder.stages.2.2.conv2.conv.weight', 'decoder.stages.2.2.conv2.norm.weight', 'decoder.stages.2.2.conv2.norm.bias', 'decoder.stages.2.3.conv1.conv.weight', 'decoder.stages.2.3.conv1.conv.bias', 'decoder.stages.2.3.conv2.conv.weight', 'decoder.stages.2.3.conv2.norm.weight', 'decoder.stages.2.3.conv2.norm.bias', 'decoder.stages.3.0.main.conv.weight', 'decoder.stages.3.0.main.conv.bias', 'decoder.stages.3.1.context_module.qkv.0.weight', 'decoder.stages.3.1.context_module.aggreg.0.0.weight', 'decoder.stages.3.1.context_module.aggreg.0.1.weight', 'decoder.stages.3.1.context_module.proj.0.weight', 'decoder.stages.3.1.context_module.proj.1.weight', 'decoder.stages.3.1.context_module.proj.1.bias', 'decoder.stages.3.1.local_module.inverted_conv.conv.weight', 'decoder.stages.3.1.local_module.inverted_conv.conv.bias', 'decoder.stages.3.1.local_module.depth_conv.conv.weight', 'decoder.stages.3.1.local_module.depth_conv.conv.bias', 'decoder.stages.3.1.local_module.point_conv.conv.weight', 'decoder.stages.3.1.local_module.point_conv.norm.weight', 'decoder.stages.3.1.local_module.point_conv.norm.bias', 'decoder.stages.3.2.context_module.qkv.0.weight', 'decoder.stages.3.2.context_module.aggreg.0.0.weight', 'decoder.stages.3.2.context_module.aggreg.0.1.weight', 'decoder.stages.3.2.context_module.proj.0.weight', 'decoder.stages.3.2.context_module.proj.1.weight', 'decoder.stages.3.2.context_module.proj.1.bias', 'decoder.stages.3.2.local_module.inverted_conv.conv.weight', 'decoder.stages.3.2.local_module.inverted_conv.conv.bias', 'decoder.stages.3.2.local_module.depth_conv.conv.weight', 'decoder.stages.3.2.local_module.depth_conv.conv.bias', 'decoder.stages.3.2.local_module.point_conv.conv.weight', 'decoder.stages.3.2.local_module.point_conv.norm.weight', 'decoder.stages.3.2.local_module.point_conv.norm.bias', 'decoder.stages.3.3.context_module.qkv.0.weight', 'decoder.stages.3.3.context_module.aggreg.0.0.weight', 'decoder.stages.3.3.context_module.aggreg.0.1.weight', 'decoder.stages.3.3.context_module.proj.0.weight', 'decoder.stages.3.3.context_module.proj.1.weight', 'decoder.stages.3.3.context_module.proj.1.bias', 'decoder.stages.3.3.local_module.inverted_conv.conv.weight', 'decoder.stages.3.3.local_module.inverted_conv.conv.bias', 'decoder.stages.3.3.local_module.depth_conv.conv.weight', 'decoder.stages.3.3.local_module.depth_conv.conv.bias', 'decoder.stages.3.3.local_module.point_conv.conv.weight', 'decoder.stages.3.3.local_module.point_conv.norm.weight', 'decoder.stages.3.3.local_module.point_conv.norm.bias', 'decoder.stages.4.0.main.conv.weight', 'decoder.stages.4.0.main.conv.bias', 'decoder.stages.4.1.context_module.qkv.0.weight', 'decoder.stages.4.1.context_module.aggreg.0.0.weight', 'decoder.stages.4.1.context_module.aggreg.0.1.weight', 'decoder.stages.4.1.context_module.proj.0.weight', 'decoder.stages.4.1.context_module.proj.1.weight', 'decoder.stages.4.1.context_module.proj.1.bias', 'decoder.stages.4.1.local_module.inverted_conv.conv.weight', 'decoder.stages.4.1.local_module.inverted_conv.conv.bias', 'decoder.stages.4.1.local_module.depth_conv.conv.weight', 'decoder.stages.4.1.local_module.depth_conv.conv.bias', 'decoder.stages.4.1.local_module.point_conv.conv.weight', 'decoder.stages.4.1.local_module.point_conv.norm.weight', 'decoder.stages.4.1.local_module.point_conv.norm.bias', 'decoder.stages.4.2.context_module.qkv.0.weight', 'decoder.stages.4.2.context_module.aggreg.0.0.weight', 'decoder.stages.4.2.context_module.aggreg.0.1.weight', 'decoder.stages.4.2.context_module.proj.0.weight', 'decoder.stages.4.2.context_module.proj.1.weight', 'decoder.stages.4.2.context_module.proj.1.bias', 'decoder.stages.4.2.local_module.inverted_conv.conv.weight', 'decoder.stages.4.2.local_module.inverted_conv.conv.bias', 'decoder.stages.4.2.local_module.depth_conv.conv.weight', 'decoder.stages.4.2.local_module.depth_conv.conv.bias', 'decoder.stages.4.2.local_module.point_conv.conv.weight', 'decoder.stages.4.2.local_module.point_conv.norm.weight', 'decoder.stages.4.2.local_module.point_conv.norm.bias', 'decoder.stages.4.3.context_module.qkv.0.weight', 'decoder.stages.4.3.context_module.aggreg.0.0.weight', 'decoder.stages.4.3.context_module.aggreg.0.1.weight', 'decoder.stages.4.3.context_module.proj.0.weight', 'decoder.stages.4.3.context_module.proj.1.weight', 'decoder.stages.4.3.context_module.proj.1.bias', 'decoder.stages.4.3.local_module.inverted_conv.conv.weight', 'decoder.stages.4.3.local_module.inverted_conv.conv.bias', 'decoder.stages.4.3.local_module.depth_conv.conv.weight', 'decoder.stages.4.3.local_module.depth_conv.conv.bias', 'decoder.stages.4.3.local_module.point_conv.conv.weight', 'decoder.stages.4.3.local_module.point_conv.norm.weight', 'decoder.stages.4.3.local_module.point_conv.norm.bias', 'decoder.stages.5.0.context_module.qkv.0.weight', 'decoder.stages.5.0.context_module.aggreg.0.0.weight', 'decoder.stages.5.0.context_module.aggreg.0.1.weight', 'decoder.stages.5.0.context_module.proj.0.weight', 'decoder.stages.5.0.context_module.proj.1.weight', 'decoder.stages.5.0.context_module.proj.1.bias', 'decoder.stages.5.0.local_module.inverted_conv.conv.weight', 'decoder.stages.5.0.local_module.inverted_conv.conv.bias', 'decoder.stages.5.0.local_module.depth_conv.conv.weight', 'decoder.stages.5.0.local_module.depth_conv.conv.bias', 'decoder.stages.5.0.local_module.point_conv.conv.weight', 'decoder.stages.5.0.local_module.point_conv.norm.weight', 'decoder.stages.5.0.local_module.point_conv.norm.bias', 'decoder.stages.5.1.context_module.qkv.0.weight', 'decoder.stages.5.1.context_module.aggreg.0.0.weight', 'decoder.stages.5.1.context_module.aggreg.0.1.weight', 'decoder.stages.5.1.context_module.proj.0.weight', 'decoder.stages.5.1.context_module.proj.1.weight', 'decoder.stages.5.1.context_module.proj.1.bias', 'decoder.stages.5.1.local_module.inverted_conv.conv.weight', 'decoder.stages.5.1.local_module.inverted_conv.conv.bias', 'decoder.stages.5.1.local_module.depth_conv.conv.weight', 'decoder.stages.5.1.local_module.depth_conv.conv.bias', 'decoder.stages.5.1.local_module.point_conv.conv.weight', 'decoder.stages.5.1.local_module.point_conv.norm.weight', 'decoder.stages.5.1.local_module.point_conv.norm.bias', 'decoder.stages.5.2.context_module.qkv.0.weight', 'decoder.stages.5.2.context_module.aggreg.0.0.weight', 'decoder.stages.5.2.context_module.aggreg.0.1.weight', 'decoder.stages.5.2.context_module.proj.0.weight', 'decoder.stages.5.2.context_module.proj.1.weight', 'decoder.stages.5.2.context_module.proj.1.bias', 'decoder.stages.5.2.local_module.inverted_conv.conv.weight', 'decoder.stages.5.2.local_module.inverted_conv.conv.bias', 'decoder.stages.5.2.local_module.depth_conv.conv.weight', 'decoder.stages.5.2.local_module.depth_conv.conv.bias', 'decoder.stages.5.2.local_module.point_conv.conv.weight', 'decoder.stages.5.2.local_module.point_conv.norm.weight', 'decoder.stages.5.2.local_module.point_conv.norm.bias', 'decoder.project_out.0.weight', 'decoder.project_out.0.bias', 'decoder.project_out.2.conv.weight', 'decoder.project_out.2.conv.bias']
Leftover VAE keys ['encoder.conv_in.bias', 'encoder.conv_in.weight', 'encoder.conv_out.bias', 'encoder.conv_out.weight', 'encoder.down_blocks.0.0.conv1.bias', 'encoder.down_blocks.0.0.conv1.weight', 'encoder.down_blocks.0.0.conv2.weight', 'encoder.down_blocks.0.0.norm.bias', 'encoder.down_blocks.0.0.norm.weight', 'encoder.down_blocks.0.1.conv1.bias', 'encoder.down_blocks.0.1.conv1.weight', 'encoder.down_blocks.0.1.conv2.weight', 'encoder.down_blocks.0.1.norm.bias', 'encoder.down_blocks.0.1.norm.weight', 'encoder.down_blocks.0.2.conv.bias', 'encoder.down_blocks.0.2.conv.weight', 'encoder.down_blocks.1.0.conv1.bias', 'encoder.down_blocks.1.0.conv1.weight', 'encoder.down_blocks.1.0.conv2.weight', 'encoder.down_blocks.1.0.norm.bias', 'encoder.down_blocks.1.0.norm.weight', 'encoder.down_blocks.1.1.conv1.bias', 'encoder.down_blocks.1.1.conv1.weight', 'encoder.down_blocks.1.1.conv2.weight', 'encoder.down_blocks.1.1.norm.bias', 'encoder.down_blocks.1.1.norm.weight', 'encoder.down_blocks.1.2.conv.bias', 'encoder.down_blocks.1.2.conv.weight', 'encoder.down_blocks.2.0.conv1.bias', 'encoder.down_blocks.2.0.conv1.weight', 'encoder.down_blocks.2.0.conv2.weight', 'encoder.down_blocks.2.0.norm.bias', 'encoder.down_blocks.2.0.norm.weight', 'encoder.down_blocks.2.1.conv1.bias', 'encoder.down_blocks.2.1.conv1.weight', 'encoder.down_blocks.2.1.conv2.weight', 'encoder.down_blocks.2.1.norm.bias', 'encoder.down_blocks.2.1.norm.weight', 'encoder.down_blocks.2.2.conv.bias', 'encoder.down_blocks.2.2.conv.weight', 'encoder.down_blocks.3.0.attn.norm_out.bias', 'encoder.down_blocks.3.0.attn.norm_out.weight', 'encoder.down_blocks.3.0.attn.to_k.weight', 'encoder.down_blocks.3.0.attn.to_out.weight', 'encoder.down_blocks.3.0.attn.to_q.weight', 'encoder.down_blocks.3.0.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.3.0.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.3.0.attn.to_v.weight', 'encoder.down_blocks.3.0.conv_out.conv_depth.bias', 'encoder.down_blocks.3.0.conv_out.conv_depth.weight', 'encoder.down_blocks.3.0.conv_out.conv_inverted.bias', 'encoder.down_blocks.3.0.conv_out.conv_inverted.weight', 'encoder.down_blocks.3.0.conv_out.conv_point.weight', 'encoder.down_blocks.3.0.conv_out.norm.bias', 'encoder.down_blocks.3.0.conv_out.norm.weight', 'encoder.down_blocks.3.1.attn.norm_out.bias', 'encoder.down_blocks.3.1.attn.norm_out.weight', 'encoder.down_blocks.3.1.attn.to_k.weight', 'encoder.down_blocks.3.1.attn.to_out.weight', 'encoder.down_blocks.3.1.attn.to_q.weight', 'encoder.down_blocks.3.1.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.3.1.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.3.1.attn.to_v.weight', 'encoder.down_blocks.3.1.conv_out.conv_depth.bias', 'encoder.down_blocks.3.1.conv_out.conv_depth.weight', 'encoder.down_blocks.3.1.conv_out.conv_inverted.bias', 'encoder.down_blocks.3.1.conv_out.conv_inverted.weight', 'encoder.down_blocks.3.1.conv_out.conv_point.weight', 'encoder.down_blocks.3.1.conv_out.norm.bias', 'encoder.down_blocks.3.1.conv_out.norm.weight', 'encoder.down_blocks.3.2.attn.norm_out.bias', 'encoder.down_blocks.3.2.attn.norm_out.weight', 'encoder.down_blocks.3.2.attn.to_k.weight', 'encoder.down_blocks.3.2.attn.to_out.weight', 'encoder.down_blocks.3.2.attn.to_q.weight', 'encoder.down_blocks.3.2.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.3.2.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.3.2.attn.to_v.weight', 'encoder.down_blocks.3.2.conv_out.conv_depth.bias', 'encoder.down_blocks.3.2.conv_out.conv_depth.weight', 'encoder.down_blocks.3.2.conv_out.conv_inverted.bias', 'encoder.down_blocks.3.2.conv_out.conv_inverted.weight', 'encoder.down_blocks.3.2.conv_out.conv_point.weight', 'encoder.down_blocks.3.2.conv_out.norm.bias', 'encoder.down_blocks.3.2.conv_out.norm.weight', 'encoder.down_blocks.3.3.conv.bias', 'encoder.down_blocks.3.3.conv.weight', 'encoder.down_blocks.4.0.attn.norm_out.bias', 'encoder.down_blocks.4.0.attn.norm_out.weight', 'encoder.down_blocks.4.0.attn.to_k.weight', 'encoder.down_blocks.4.0.attn.to_out.weight', 'encoder.down_blocks.4.0.attn.to_q.weight', 'encoder.down_blocks.4.0.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.4.0.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.4.0.attn.to_v.weight', 'encoder.down_blocks.4.0.conv_out.conv_depth.bias', 'encoder.down_blocks.4.0.conv_out.conv_depth.weight', 'encoder.down_blocks.4.0.conv_out.conv_inverted.bias', 'encoder.down_blocks.4.0.conv_out.conv_inverted.weight', 'encoder.down_blocks.4.0.conv_out.conv_point.weight', 'encoder.down_blocks.4.0.conv_out.norm.bias', 'encoder.down_blocks.4.0.conv_out.norm.weight', 'encoder.down_blocks.4.1.attn.norm_out.bias', 'encoder.down_blocks.4.1.attn.norm_out.weight', 'encoder.down_blocks.4.1.attn.to_k.weight', 'encoder.down_blocks.4.1.attn.to_out.weight', 'encoder.down_blocks.4.1.attn.to_q.weight', 'encoder.down_blocks.4.1.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.4.1.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.4.1.attn.to_v.weight', 'encoder.down_blocks.4.1.conv_out.conv_depth.bias', 'encoder.down_blocks.4.1.conv_out.conv_depth.weight', 'encoder.down_blocks.4.1.conv_out.conv_inverted.bias', 'encoder.down_blocks.4.1.conv_out.conv_inverted.weight', 'encoder.down_blocks.4.1.conv_out.conv_point.weight', 'encoder.down_blocks.4.1.conv_out.norm.bias', 'encoder.down_blocks.4.1.conv_out.norm.weight', 'encoder.down_blocks.4.2.attn.norm_out.bias', 'encoder.down_blocks.4.2.attn.norm_out.weight', 'encoder.down_blocks.4.2.attn.to_k.weight', 'encoder.down_blocks.4.2.attn.to_out.weight', 'encoder.down_blocks.4.2.attn.to_q.weight', 'encoder.down_blocks.4.2.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.4.2.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.4.2.attn.to_v.weight', 'encoder.down_blocks.4.2.conv_out.conv_depth.bias', 'encoder.down_blocks.4.2.conv_out.conv_depth.weight', 'encoder.down_blocks.4.2.conv_out.conv_inverted.bias', 'encoder.down_blocks.4.2.conv_out.conv_inverted.weight', 'encoder.down_blocks.4.2.conv_out.conv_point.weight', 'encoder.down_blocks.4.2.conv_out.norm.bias', 'encoder.down_blocks.4.2.conv_out.norm.weight', 'encoder.down_blocks.4.3.conv.bias', 'encoder.down_blocks.4.3.conv.weight', 'encoder.down_blocks.5.0.attn.norm_out.bias', 'encoder.down_blocks.5.0.attn.norm_out.weight', 'encoder.down_blocks.5.0.attn.to_k.weight', 'encoder.down_blocks.5.0.attn.to_out.weight', 'encoder.down_blocks.5.0.attn.to_q.weight', 'encoder.down_blocks.5.0.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.5.0.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.5.0.attn.to_v.weight', 'encoder.down_blocks.5.0.conv_out.conv_depth.bias', 'encoder.down_blocks.5.0.conv_out.conv_depth.weight', 'encoder.down_blocks.5.0.conv_out.conv_inverted.bias', 'encoder.down_blocks.5.0.conv_out.conv_inverted.weight', 'encoder.down_blocks.5.0.conv_out.conv_point.weight', 'encoder.down_blocks.5.0.conv_out.norm.bias', 'encoder.down_blocks.5.0.conv_out.norm.weight', 'encoder.down_blocks.5.1.attn.norm_out.bias', 'encoder.down_blocks.5.1.attn.norm_out.weight', 'encoder.down_blocks.5.1.attn.to_k.weight', 'encoder.down_blocks.5.1.attn.to_out.weight', 'encoder.down_blocks.5.1.attn.to_q.weight', 'encoder.down_blocks.5.1.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.5.1.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.5.1.attn.to_v.weight', 'encoder.down_blocks.5.1.conv_out.conv_depth.bias', 'encoder.down_blocks.5.1.conv_out.conv_depth.weight', 'encoder.down_blocks.5.1.conv_out.conv_inverted.bias', 'encoder.down_blocks.5.1.conv_out.conv_inverted.weight', 'encoder.down_blocks.5.1.conv_out.conv_point.weight', 'encoder.down_blocks.5.1.conv_out.norm.bias', 'encoder.down_blocks.5.1.conv_out.norm.weight', 'encoder.down_blocks.5.2.attn.norm_out.bias', 'encoder.down_blocks.5.2.attn.norm_out.weight', 'encoder.down_blocks.5.2.attn.to_k.weight', 'encoder.down_blocks.5.2.attn.to_out.weight', 'encoder.down_blocks.5.2.attn.to_q.weight', 'encoder.down_blocks.5.2.attn.to_qkv_multiscale.0.proj_in.weight', 'encoder.down_blocks.5.2.attn.to_qkv_multiscale.0.proj_out.weight', 'encoder.down_blocks.5.2.attn.to_v.weight', 'encoder.down_blocks.5.2.conv_out.conv_depth.bias', 'encoder.down_blocks.5.2.conv_out.conv_depth.weight', 'encoder.down_blocks.5.2.conv_out.conv_inverted.bias', 'encoder.down_blocks.5.2.conv_out.conv_inverted.weight', 'encoder.down_blocks.5.2.conv_out.conv_point.weight', 'encoder.down_blocks.5.2.conv_out.norm.bias', 'encoder.down_blocks.5.2.conv_out.norm.weight', 'decoder.conv_in.bias', 'decoder.conv_in.weight', 'decoder.conv_out.bias', 'decoder.conv_out.weight', 'decoder.norm_out.bias', 'decoder.norm_out.weight', 'decoder.up_blocks.0.0.conv.bias', 'decoder.up_blocks.0.0.conv.weight', 'decoder.up_blocks.0.1.conv1.bias', 'decoder.up_blocks.0.1.conv1.weight', 'decoder.up_blocks.0.1.conv2.weight', 'decoder.up_blocks.0.1.norm.bias', 'decoder.up_blocks.0.1.norm.weight', 'decoder.up_blocks.0.2.conv1.bias', 'decoder.up_blocks.0.2.conv1.weight', 'decoder.up_blocks.0.2.conv2.weight', 'decoder.up_blocks.0.2.norm.bias', 'decoder.up_blocks.0.2.norm.weight', 'decoder.up_blocks.0.3.conv1.bias', 'decoder.up_blocks.0.3.conv1.weight', 'decoder.up_blocks.0.3.conv2.weight', 'decoder.up_blocks.0.3.norm.bias', 'decoder.up_blocks.0.3.norm.weight', 'decoder.up_blocks.1.0.conv.bias', 'decoder.up_blocks.1.0.conv.weight', 'decoder.up_blocks.1.1.conv1.bias', 'decoder.up_blocks.1.1.conv1.weight', 'decoder.up_blocks.1.1.conv2.weight', 'decoder.up_blocks.1.1.norm.bias', 'decoder.up_blocks.1.1.norm.weight', 'decoder.up_blocks.1.2.conv1.bias', 'decoder.up_blocks.1.2.conv1.weight', 'decoder.up_blocks.1.2.conv2.weight', 'decoder.up_blocks.1.2.norm.bias', 'decoder.up_blocks.1.2.norm.weight', 'decoder.up_blocks.1.3.conv1.bias', 'decoder.up_blocks.1.3.conv1.weight', 'decoder.up_blocks.1.3.conv2.weight', 'decoder.up_blocks.1.3.norm.bias', 'decoder.up_blocks.1.3.norm.weight', 'decoder.up_blocks.2.0.conv.bias', 'decoder.up_blocks.2.0.conv.weight', 'decoder.up_blocks.2.1.conv1.bias', 'decoder.up_blocks.2.1.conv1.weight', 'decoder.up_blocks.2.1.conv2.weight', 'decoder.up_blocks.2.1.norm.bias', 'decoder.up_blocks.2.1.norm.weight', 'decoder.up_blocks.2.2.conv1.bias', 'decoder.up_blocks.2.2.conv1.weight', 'decoder.up_blocks.2.2.conv2.weight', 'decoder.up_blocks.2.2.norm.bias', 'decoder.up_blocks.2.2.norm.weight', 'decoder.up_blocks.2.3.conv1.bias', 'decoder.up_blocks.2.3.conv1.weight', 'decoder.up_blocks.2.3.conv2.weight', 'decoder.up_blocks.2.3.norm.bias', 'decoder.up_blocks.2.3.norm.weight', 'decoder.up_blocks.3.0.conv.bias', 'decoder.up_blocks.3.0.conv.weight', 'decoder.up_blocks.3.1.attn.norm_out.bias', 'decoder.up_blocks.3.1.attn.norm_out.weight', 'decoder.up_blocks.3.1.attn.to_k.weight', 'decoder.up_blocks.3.1.attn.to_out.weight', 'decoder.up_blocks.3.1.attn.to_q.weight', 'decoder.up_blocks.3.1.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.3.1.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.3.1.attn.to_v.weight', 'decoder.up_blocks.3.1.conv_out.conv_depth.bias', 'decoder.up_blocks.3.1.conv_out.conv_depth.weight', 'decoder.up_blocks.3.1.conv_out.conv_inverted.bias', 'decoder.up_blocks.3.1.conv_out.conv_inverted.weight', 'decoder.up_blocks.3.1.conv_out.conv_point.weight', 'decoder.up_blocks.3.1.conv_out.norm.bias', 'decoder.up_blocks.3.1.conv_out.norm.weight', 'decoder.up_blocks.3.2.attn.norm_out.bias', 'decoder.up_blocks.3.2.attn.norm_out.weight', 'decoder.up_blocks.3.2.attn.to_k.weight', 'decoder.up_blocks.3.2.attn.to_out.weight', 'decoder.up_blocks.3.2.attn.to_q.weight', 'decoder.up_blocks.3.2.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.3.2.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.3.2.attn.to_v.weight', 'decoder.up_blocks.3.2.conv_out.conv_depth.bias', 'decoder.up_blocks.3.2.conv_out.conv_depth.weight', 'decoder.up_blocks.3.2.conv_out.conv_inverted.bias', 'decoder.up_blocks.3.2.conv_out.conv_inverted.weight', 'decoder.up_blocks.3.2.conv_out.conv_point.weight', 'decoder.up_blocks.3.2.conv_out.norm.bias', 'decoder.up_blocks.3.2.conv_out.norm.weight', 'decoder.up_blocks.3.3.attn.norm_out.bias', 'decoder.up_blocks.3.3.attn.norm_out.weight', 'decoder.up_blocks.3.3.attn.to_k.weight', 'decoder.up_blocks.3.3.attn.to_out.weight', 'decoder.up_blocks.3.3.attn.to_q.weight', 'decoder.up_blocks.3.3.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.3.3.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.3.3.attn.to_v.weight', 'decoder.up_blocks.3.3.conv_out.conv_depth.bias', 'decoder.up_blocks.3.3.conv_out.conv_depth.weight', 'decoder.up_blocks.3.3.conv_out.conv_inverted.bias', 'decoder.up_blocks.3.3.conv_out.conv_inverted.weight', 'decoder.up_blocks.3.3.conv_out.conv_point.weight', 'decoder.up_blocks.3.3.conv_out.norm.bias', 'decoder.up_blocks.3.3.conv_out.norm.weight', 'decoder.up_blocks.4.0.conv.bias', 'decoder.up_blocks.4.0.conv.weight', 'decoder.up_blocks.4.1.attn.norm_out.bias', 'decoder.up_blocks.4.1.attn.norm_out.weight', 'decoder.up_blocks.4.1.attn.to_k.weight', 'decoder.up_blocks.4.1.attn.to_out.weight', 'decoder.up_blocks.4.1.attn.to_q.weight', 'decoder.up_blocks.4.1.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.4.1.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.4.1.attn.to_v.weight', 'decoder.up_blocks.4.1.conv_out.conv_depth.bias', 'decoder.up_blocks.4.1.conv_out.conv_depth.weight', 'decoder.up_blocks.4.1.conv_out.conv_inverted.bias', 'decoder.up_blocks.4.1.conv_out.conv_inverted.weight', 'decoder.up_blocks.4.1.conv_out.conv_point.weight', 'decoder.up_blocks.4.1.conv_out.norm.bias', 'decoder.up_blocks.4.1.conv_out.norm.weight', 'decoder.up_blocks.4.2.attn.norm_out.bias', 'decoder.up_blocks.4.2.attn.norm_out.weight', 'decoder.up_blocks.4.2.attn.to_k.weight', 'decoder.up_blocks.4.2.attn.to_out.weight', 'decoder.up_blocks.4.2.attn.to_q.weight', 'decoder.up_blocks.4.2.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.4.2.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.4.2.attn.to_v.weight', 'decoder.up_blocks.4.2.conv_out.conv_depth.bias', 'decoder.up_blocks.4.2.conv_out.conv_depth.weight', 'decoder.up_blocks.4.2.conv_out.conv_inverted.bias', 'decoder.up_blocks.4.2.conv_out.conv_inverted.weight', 'decoder.up_blocks.4.2.conv_out.conv_point.weight', 'decoder.up_blocks.4.2.conv_out.norm.bias', 'decoder.up_blocks.4.2.conv_out.norm.weight', 'decoder.up_blocks.4.3.attn.norm_out.bias', 'decoder.up_blocks.4.3.attn.norm_out.weight', 'decoder.up_blocks.4.3.attn.to_k.weight', 'decoder.up_blocks.4.3.attn.to_out.weight', 'decoder.up_blocks.4.3.attn.to_q.weight', 'decoder.up_blocks.4.3.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.4.3.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.4.3.attn.to_v.weight', 'decoder.up_blocks.4.3.conv_out.conv_depth.bias', 'decoder.up_blocks.4.3.conv_out.conv_depth.weight', 'decoder.up_blocks.4.3.conv_out.conv_inverted.bias', 'decoder.up_blocks.4.3.conv_out.conv_inverted.weight', 'decoder.up_blocks.4.3.conv_out.conv_point.weight', 'decoder.up_blocks.4.3.conv_out.norm.bias', 'decoder.up_blocks.4.3.conv_out.norm.weight', 'decoder.up_blocks.5.0.attn.norm_out.bias', 'decoder.up_blocks.5.0.attn.norm_out.weight', 'decoder.up_blocks.5.0.attn.to_k.weight', 'decoder.up_blocks.5.0.attn.to_out.weight', 'decoder.up_blocks.5.0.attn.to_q.weight', 'decoder.up_blocks.5.0.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.5.0.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.5.0.attn.to_v.weight', 'decoder.up_blocks.5.0.conv_out.conv_depth.bias', 'decoder.up_blocks.5.0.conv_out.conv_depth.weight', 'decoder.up_blocks.5.0.conv_out.conv_inverted.bias', 'decoder.up_blocks.5.0.conv_out.conv_inverted.weight', 'decoder.up_blocks.5.0.conv_out.conv_point.weight', 'decoder.up_blocks.5.0.conv_out.norm.bias', 'decoder.up_blocks.5.0.conv_out.norm.weight', 'decoder.up_blocks.5.1.attn.norm_out.bias', 'decoder.up_blocks.5.1.attn.norm_out.weight', 'decoder.up_blocks.5.1.attn.to_k.weight', 'decoder.up_blocks.5.1.attn.to_out.weight', 'decoder.up_blocks.5.1.attn.to_q.weight', 'decoder.up_blocks.5.1.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.5.1.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.5.1.attn.to_v.weight', 'decoder.up_blocks.5.1.conv_out.conv_depth.bias', 'decoder.up_blocks.5.1.conv_out.conv_depth.weight', 'decoder.up_blocks.5.1.conv_out.conv_inverted.bias', 'decoder.up_blocks.5.1.conv_out.conv_inverted.weight', 'decoder.up_blocks.5.1.conv_out.conv_point.weight', 'decoder.up_blocks.5.1.conv_out.norm.bias', 'decoder.up_blocks.5.1.conv_out.norm.weight', 'decoder.up_blocks.5.2.attn.norm_out.bias', 'decoder.up_blocks.5.2.attn.norm_out.weight', 'decoder.up_blocks.5.2.attn.to_k.weight', 'decoder.up_blocks.5.2.attn.to_out.weight', 'decoder.up_blocks.5.2.attn.to_q.weight', 'decoder.up_blocks.5.2.attn.to_qkv_multiscale.0.proj_in.weight', 'decoder.up_blocks.5.2.attn.to_qkv_multiscale.0.proj_out.weight', 'decoder.up_blocks.5.2.attn.to_v.weight', 'decoder.up_blocks.5.2.conv_out.conv_depth.bias', 'decoder.up_blocks.5.2.conv_out.conv_depth.weight', 'decoder.up_blocks.5.2.conv_out.conv_inverted.bias', 'decoder.up_blocks.5.2.conv_out.conv_inverted.weight', 'decoder.up_blocks.5.2.conv_out.conv_point.weight', 'decoder.up_blocks.5.2.conv_out.norm.bias', 'decoder.up_blocks.5.2.conv_out.norm.weight']
model_type FLOW
Requested to load EXM_Sana_Model
loaded completely 9.5367431640625e+25 3059.7485961914062 True
100%|██████████████████████████████████████████████████████████████████████████████████| 30/30 [00:05<00:00,  5.95it/s]
Prompt executed in 34.53 seconds

[SUP3RMASS1VE]

Not a black image but this is all i get

[juanml82]

Same issue

[w0ver]

Not a black image but this is all i get

@SUP3RMASS1VE i used to get same result as will :\ !

[ashrafbay]

The problem lies in two aspects
First, the vea model is not correct, a black screen appears
Second, taking samples and the structure is incorrect, an unclear image appears
Use ddim + Linear Shield
Try several samples that suit you, but keep the structure linear
I was able to run only 600 million models but 1600 I don't know

[gsiisg]

see city96/ComfyUI_ExtraModels#93 for solution that worked for me

[lawrence-cj]

Guys, could you please follow this guidance to install and run?
Here is the guidance: https://github.com/NVlabs/Sana/blob/main/asset/docs/ComfyUI/comfyui.md
And this is our comfyUI code: https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels
this is our comfyUI code: https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels
this is our comfyUI code: https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels
this is our comfyUI code: https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels

git clone https://github.com/comfyanonymous/ComfyUI.git
cd ComfyUI
git clone https://github.com/Efficient-Large-Model/ComfyUI_ExtraModels.git custom_nodes/ComfyUI_ExtraModels

python main.py

Solution is here, refer to: city96/ComfyUI_ExtraModels#93

[vnguyen972]

see city96/ComfyUI_ExtraModels#93 for solution that worked for me

Thanks. That worked for me too!