Input
prompt
Input prompt
outdoors, sky, tree, no humans, grass, ground vehicle, building, scenery, motor vehicle, fence, car, road, bush, lamppost, street
negative_prompt
Specify things to not see in the output
reference_image
Image that the output should be similar to
reference_pose_image
Image with a reference pose
reference_depth_image
Image with a reference depth
image_dimensions
Pixel dimensions of output image (width x height)
512x768
num_outputs
Number of output images
1
seed
Random seed. Set as -1 to randomize the seed
-1
sampler
Sampler type
Restart
samping_steps
Number of denoising steps
20
cfg_scale
Scale for classifier-free guidance
7.5
clip_skip
Whether to ignore the last layer of CLIP network or not
true
lora
LoRA file. You can apply and adjust the magnitude by putting the following to the prompt: <lora:[FILE_NAME]:[MAGNITUDE]>
Output
https://files.tungsten.run/uploads/322bd2f1aa864850bb6c775505ef6c65/tmp15be6o8k.png
Finished in 9.4 seconds
Preparing inputs... Processing... Using seed 1401375729 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:09, 1.94it/s] 10%|█ | 2/20 [00:00<00:08, 2.13it/s] 15%|█▌ | 3/20 [00:01<00:07, 2.19it/s] 20%|██ | 4/20 [00:01<00:07, 2.23it/s] 25%|██▌ | 5/20 [00:02<00:06, 2.25it/s] 30%|███ | 6/20 [00:02<00:06, 2.25it/s] 35%|███▌ | 7/20 [00:03<00:05, 2.26it/s] 40%|████ | 8/20 [00:03<00:05, 2.26it/s] 45%|████▌ | 9/20 [00:04<00:04, 2.27it/s] 50%|█████ | 10/20 [00:04<00:04, 2.26it/s] 55%|█████▌ | 11/20 [00:04<00:03, 2.27it/s] 60%|██████ | 12/20 [00:05<00:03, 2.27it/s] 65%|██████▌ | 13/20 [00:05<00:03, 2.27it/s] 70%|███████ | 14/20 [00:06<00:02, 2.27it/s] 75%|███████▌ | 15/20 [00:06<00:02, 2.27it/s] 80%|████████ | 16/20 [00:07<00:01, 2.26it/s] 85%|████████▌ | 17/20 [00:07<00:01, 2.27it/s] 90%|█████████ | 18/20 [00:08<00:00, 2.27it/s] 95%|█████████▌| 19/20 [00:08<00:00, 2.27it/s] 100%|██████████| 20/20 [00:08<00:00, 2.67it/s] 100%|██████████| 20/20 [00:08<00:00, 2.31it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Finished.
prompt
Input prompt
outdoors, sky, tree, no humans, grass, ground vehicle, building, scenery, motor vehicle, fence, car, road, bush, lamppost, street
negative_prompt
Specify things to not see in the output
reference_image
Image that the output should be similar to
reference_pose_image
Image with a reference pose
reference_depth_image
Image with a reference depth
image_dimensions
Pixel dimensions of output image (width x height)
512x768
num_outputs
Number of output images
1
seed
Random seed. Set as -1 to randomize the seed
-1
sampler
Sampler type
Restart
samping_steps
Number of denoising steps
20
cfg_scale
Scale for classifier-free guidance
7.5
clip_skip
Whether to ignore the last layer of CLIP network or not
true
lora
LoRA file. You can apply and adjust the magnitude by putting the following to the prompt: <lora:[FILE_NAME]:[MAGNITUDE]>
https://files.tungsten.run/uploads/322bd2f1aa864850bb6c775505ef6c65/tmp15be6o8k.png
Finished in 9.4 seconds
Preparing inputs... Processing... Using seed 1401375729 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:09, 1.94it/s] 10%|█ | 2/20 [00:00<00:08, 2.13it/s] 15%|█▌ | 3/20 [00:01<00:07, 2.19it/s] 20%|██ | 4/20 [00:01<00:07, 2.23it/s] 25%|██▌ | 5/20 [00:02<00:06, 2.25it/s] 30%|███ | 6/20 [00:02<00:06, 2.25it/s] 35%|███▌ | 7/20 [00:03<00:05, 2.26it/s] 40%|████ | 8/20 [00:03<00:05, 2.26it/s] 45%|████▌ | 9/20 [00:04<00:04, 2.27it/s] 50%|█████ | 10/20 [00:04<00:04, 2.26it/s] 55%|█████▌ | 11/20 [00:04<00:03, 2.27it/s] 60%|██████ | 12/20 [00:05<00:03, 2.27it/s] 65%|██████▌ | 13/20 [00:05<00:03, 2.27it/s] 70%|███████ | 14/20 [00:06<00:02, 2.27it/s] 75%|███████▌ | 15/20 [00:06<00:02, 2.27it/s] 80%|████████ | 16/20 [00:07<00:01, 2.26it/s] 85%|████████▌ | 17/20 [00:07<00:01, 2.27it/s] 90%|█████████ | 18/20 [00:08<00:00, 2.27it/s] 95%|█████████▌| 19/20 [00:08<00:00, 2.27it/s] 100%|██████████| 20/20 [00:08<00:00, 2.67it/s] 100%|██████████| 20/20 [00:08<00:00, 2.31it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Finished.