Version: v6.0
Input
Output
This example was created by sparks
Finished in 41.5 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: <lora:EnvyBetterHiresFixXL01:0.5>, <lora:LCMTurboMix_DPM_SDE_Karras:1>, award winning still image from an adventure movie directed by vincent van gogh, lara croft standing in a ruined jungle temple at night, 8k resolution, trending on art station, ((extreme skin detail)), hdr, ((ultrarealistic)), ((photo)), bokeh, depth of field, 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3, <lora:add-detail-xl:1.0>
Full negative prompt: ziprealism_neg, ac_neg1, ac_neg2, deformed, bad quality, grainy, noisy, plastic, hazy, low contrast
Failed to match keys when loading network /tungsten/models/Lora/LCMTurboMix_DPM_SDE_Karras.safetensors: {'lora_unet_up_blocks_0_upsamplers_0_conv.alpha': 'diffusion_model_up_blocks_0_upsamplers_0_conv', 'lora_unet_up_blocks_0_upsamplers_0_conv.lora_down.weight': 'diffusion_model_up_blocks_0_upsamplers_0_conv', 'lora_unet_up_blocks_0_upsamplers_0_conv.lora_up.weight': 'diffusion_model_up_blocks_0_upsamplers_0_conv'}
0%| | 0/8 [00:00<?, ?it/s]
12%|█▎ | 1/8 [00:04<00:28, 4.14s/it]
25%|██▌ | 2/8 [00:07<00:22, 3.77s/it]
38%|███▊ | 3/8 [00:11<00:18, 3.71s/it]
50%|█████ | 4/8 [00:14<00:14, 3.57s/it]
62%|██████▎ | 5/8 [00:17<00:10, 3.43s/it]
75%|███████▌ | 6/8 [00:21<00:06, 3.35s/it]
88%|████████▊ | 7/8 [00:23<00:03, 3.19s/it]
100%|██████████| 8/8 [00:25<00:00, 2.69s/it]
100%|██████████| 8/8 [00:25<00:00, 3.19s/it]
Decoding latents in cuda:0...
done in 2.89s
Move latents to cpu...
done in 0.03s
Uploading outputs...
Finished.
This example was created by sparks
Finished in 41.5 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: <lora:EnvyBetterHiresFixXL01:0.5>, <lora:LCMTurboMix_DPM_SDE_Karras:1>, award winning still image from an adventure movie directed by vincent van gogh, lara croft standing in a ruined jungle temple at night, 8k resolution, trending on art station, ((extreme skin detail)), hdr, ((ultrarealistic)), ((photo)), bokeh, depth of field, 8k uhd, dslr, soft lighting, high quality, Fujifilm XT3, <lora:add-detail-xl:1.0>
Full negative prompt: ziprealism_neg, ac_neg1, ac_neg2, deformed, bad quality, grainy, noisy, plastic, hazy, low contrast
Failed to match keys when loading network /tungsten/models/Lora/LCMTurboMix_DPM_SDE_Karras.safetensors: {'lora_unet_up_blocks_0_upsamplers_0_conv.alpha': 'diffusion_model_up_blocks_0_upsamplers_0_conv', 'lora_unet_up_blocks_0_upsamplers_0_conv.lora_down.weight': 'diffusion_model_up_blocks_0_upsamplers_0_conv', 'lora_unet_up_blocks_0_upsamplers_0_conv.lora_up.weight': 'diffusion_model_up_blocks_0_upsamplers_0_conv'}
0%| | 0/8 [00:00<?, ?it/s]
12%|█▎ | 1/8 [00:04<00:28, 4.14s/it]
25%|██▌ | 2/8 [00:07<00:22, 3.77s/it]
38%|███▊ | 3/8 [00:11<00:18, 3.71s/it]
50%|█████ | 4/8 [00:14<00:14, 3.57s/it]
62%|██████▎ | 5/8 [00:17<00:10, 3.43s/it]
75%|███████▌ | 6/8 [00:21<00:06, 3.35s/it]
88%|████████▊ | 7/8 [00:23<00:03, 3.19s/it]
100%|██████████| 8/8 [00:25<00:00, 2.69s/it]
100%|██████████| 8/8 [00:25<00:00, 3.19s/it]
Decoding latents in cuda:0...
done in 2.89s
Move latents to cpu...
done in 0.03s
Uploading outputs...
Finished.