tungsten-logo
Sign In
Beautiful Sunset with Oxalis Anime
oxalis-anime:v1.0
evevalentine2017
evevalentine2017
·
Apr 2
122
Input
prompt
Specify things to see in the output
(masterpiece), best quality, high quality, anime screencap, beautiful sunset scenery, tropical beach, jungle, (no humans:1.5)
negative_prompt
Specify things to not see in the output
By bad artist -neg, easynegative, bad quality, worst quality, (3 legs), (3 arms), girl, woman, human, person, people, animal, horse
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
403029143
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.55
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
1
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
1
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 2M Karras
samping_steps
Number of denoising steps
41
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
kl-f8-anime2_fp16.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
easynegative.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
By bad artist -neg.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/72b9effd94bb473cbadc41fedabcddb9/00000-403029143.webp
https://files.tungsten.run/uploads/5f76ad6dee6840c18e5a4386400d25cb/00001-403029144.webp
https://files.tungsten.run/uploads/2d893f8627504ee58b794a8c8f484cf8/00002-403029145.webp
https://files.tungsten.run/uploads/8265cc0c0707499bafc920dbb6757f10/00003-403029146.webp
Finished in 50.4 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/kl-f8-anime2_fp16.safetensors Full prompt: (masterpiece), best quality, high quality, anime screencap, beautiful sunset scenery, tropical beach, jungle, (no humans:1.5) Full negative prompt: By bad artist -neg, easynegative, bad quality, worst quality, (3 legs), (3 arms), girl, woman, human, person, people, animal, horse 0%| | 0/41 [00:00<?, ?it/s] 2%|▏ | 1/41 [00:00<00:25, 1.56it/s] 5%|▍ | 2/41 [00:01<00:25, 1.54it/s] 7%|▋ | 3/41 [00:01<00:24, 1.54it/s] 10%|▉ | 4/41 [00:02<00:24, 1.54it/s] 12%|█▏ | 5/41 [00:03<00:23, 1.54it/s] 15%|█▍ | 6/41 [00:03<00:22, 1.54it/s] 17%|█▋ | 7/41 [00:04<00:22, 1.54it/s] 20%|█▉ | 8/41 [00:05<00:21, 1.54it/s] 22%|██▏ | 9/41 [00:05<00:20, 1.54it/s] 24%|██▍ | 10/41 [00:06<00:20, 1.54it/s] 27%|██▋ | 11/41 [00:07<00:19, 1.54it/s] 29%|██▉ | 12/41 [00:07<00:18, 1.54it/s] 32%|███▏ | 13/41 [00:08<00:18, 1.54it/s] 34%|███▍ | 14/41 [00:09<00:17, 1.54it/s] 37%|███▋ | 15/41 [00:09<00:16, 1.54it/s] 39%|███▉ | 16/41 [00:10<00:16, 1.54it/s] 41%|████▏ | 17/41 [00:11<00:15, 1.54it/s] 44%|████▍ | 18/41 [00:11<00:14, 1.54it/s] 46%|████▋ | 19/41 [00:12<00:14, 1.54it/s] 49%|████▉ | 20/41 [00:12<00:13, 1.54it/s] 51%|█████ | 21/41 [00:13<00:13, 1.54it/s] 54%|█████▎ | 22/41 [00:14<00:12, 1.54it/s] 56%|█████▌ | 23/41 [00:14<00:11, 1.54it/s] 59%|█████▊ | 24/41 [00:15<00:11, 1.53it/s] 61%|██████ | 25/41 [00:16<00:10, 1.54it/s] 63%|██████▎ | 26/41 [00:16<00:09, 1.54it/s] 66%|██████▌ | 27/41 [00:17<00:09, 1.54it/s] 68%|██████▊ | 28/41 [00:18<00:08, 1.54it/s] 71%|███████ | 29/41 [00:18<00:07, 1.53it/s] 73%|███████▎ | 30/41 [00:19<00:07, 1.53it/s] 76%|███████▌ | 31/41 [00:20<00:06, 1.53it/s] 78%|███████▊ | 32/41 [00:20<00:05, 1.53it/s] 80%|████████ | 33/41 [00:21<00:05, 1.53it/s] 83%|████████▎ | 34/41 [00:22<00:04, 1.53it/s] 85%|████████▌ | 35/41 [00:22<00:03, 1.54it/s] 88%|████████▊ | 36/41 [00:23<00:03, 1.53it/s] 90%|█████████ | 37/41 [00:24<00:02, 1.53it/s] 93%|█████████▎| 38/41 [00:24<00:01, 1.53it/s] 95%|█████████▌| 39/41 [00:25<00:01, 1.53it/s] 98%|█████████▊| 40/41 [00:26<00:00, 1.53it/s] 100%|██████████| 41/41 [00:26<00:00, 1.53it/s] 100%|██████████| 41/41 [00:26<00:00, 1.54it/s] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.01s 0: 640x640 (no detections), 6.0ms Speed: 2.2ms preprocess, 6.0ms inference, 6.3ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings.
prompt
Specify things to see in the output
(masterpiece), best quality, high quality, anime screencap, beautiful sunset scenery, tropical beach, jungle, (no humans:1.5)
negative_prompt
Specify things to not see in the output
By bad artist -neg, easynegative, bad quality, worst quality, (3 legs), (3 arms), girl, woman, human, person, people, animal, horse
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
403029143
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0.55
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
1
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
1
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
1
sampler
Sampler type
DPM++ 2M Karras
samping_steps
Number of denoising steps
41
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
kl-f8-anime2_fp16.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
easynegative.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
By bad artist -neg.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/72b9effd94bb473cbadc41fedabcddb9/00000-403029143.webp
https://files.tungsten.run/uploads/5f76ad6dee6840c18e5a4386400d25cb/00001-403029144.webp
https://files.tungsten.run/uploads/2d893f8627504ee58b794a8c8f484cf8/00002-403029145.webp
https://files.tungsten.run/uploads/8265cc0c0707499bafc920dbb6757f10/00003-403029146.webp
Finished in 50.4 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/kl-f8-anime2_fp16.safetensors Full prompt: (masterpiece), best quality, high quality, anime screencap, beautiful sunset scenery, tropical beach, jungle, (no humans:1.5) Full negative prompt: By bad artist -neg, easynegative, bad quality, worst quality, (3 legs), (3 arms), girl, woman, human, person, people, animal, horse 0%| | 0/41 [00:00<?, ?it/s] 2%|▏ | 1/41 [00:00<00:25, 1.56it/s] 5%|▍ | 2/41 [00:01<00:25, 1.54it/s] 7%|▋ | 3/41 [00:01<00:24, 1.54it/s] 10%|▉ | 4/41 [00:02<00:24, 1.54it/s] 12%|█▏ | 5/41 [00:03<00:23, 1.54it/s] 15%|█▍ | 6/41 [00:03<00:22, 1.54it/s] 17%|█▋ | 7/41 [00:04<00:22, 1.54it/s] 20%|█▉ | 8/41 [00:05<00:21, 1.54it/s] 22%|██▏ | 9/41 [00:05<00:20, 1.54it/s] 24%|██▍ | 10/41 [00:06<00:20, 1.54it/s] 27%|██▋ | 11/41 [00:07<00:19, 1.54it/s] 29%|██▉ | 12/41 [00:07<00:18, 1.54it/s] 32%|███▏ | 13/41 [00:08<00:18, 1.54it/s] 34%|███▍ | 14/41 [00:09<00:17, 1.54it/s] 37%|███▋ | 15/41 [00:09<00:16, 1.54it/s] 39%|███▉ | 16/41 [00:10<00:16, 1.54it/s] 41%|████▏ | 17/41 [00:11<00:15, 1.54it/s] 44%|████▍ | 18/41 [00:11<00:14, 1.54it/s] 46%|████▋ | 19/41 [00:12<00:14, 1.54it/s] 49%|████▉ | 20/41 [00:12<00:13, 1.54it/s] 51%|█████ | 21/41 [00:13<00:13, 1.54it/s] 54%|█████▎ | 22/41 [00:14<00:12, 1.54it/s] 56%|█████▌ | 23/41 [00:14<00:11, 1.54it/s] 59%|█████▊ | 24/41 [00:15<00:11, 1.53it/s] 61%|██████ | 25/41 [00:16<00:10, 1.54it/s] 63%|██████▎ | 26/41 [00:16<00:09, 1.54it/s] 66%|██████▌ | 27/41 [00:17<00:09, 1.54it/s] 68%|██████▊ | 28/41 [00:18<00:08, 1.54it/s] 71%|███████ | 29/41 [00:18<00:07, 1.53it/s] 73%|███████▎ | 30/41 [00:19<00:07, 1.53it/s] 76%|███████▌ | 31/41 [00:20<00:06, 1.53it/s] 78%|███████▊ | 32/41 [00:20<00:05, 1.53it/s] 80%|████████ | 33/41 [00:21<00:05, 1.53it/s] 83%|████████▎ | 34/41 [00:22<00:04, 1.53it/s] 85%|████████▌ | 35/41 [00:22<00:03, 1.54it/s] 88%|████████▊ | 36/41 [00:23<00:03, 1.53it/s] 90%|█████████ | 37/41 [00:24<00:02, 1.53it/s] 93%|█████████▎| 38/41 [00:24<00:01, 1.53it/s] 95%|█████████▌| 39/41 [00:25<00:01, 1.53it/s] 98%|█████████▊| 40/41 [00:26<00:00, 1.53it/s] 100%|██████████| 41/41 [00:26<00:00, 1.53it/s] 100%|██████████| 41/41 [00:26<00:00, 1.54it/s] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.01s 0: 640x640 (no detections), 6.0ms Speed: 2.2ms preprocess, 6.0ms inference, 6.3ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings.