tungsten-logo
Sign In
Mouse Warrior with fenris-xl
fenris-xl:v16.4
sparks
sparks
·
Jan 23
383
Input
prompt
Specify things to see in the output
cinematic film still ((photo:1.2)), A mouse outside dramatic lighting, dynamic pose, dynamic camera, masterpiece, best quality, dark shadows, ((dark fantasy)) ,wearing a golden armor, detailed, realistic, 8k uhd, high quality, detailed, realistic, 8k uhd, high quality . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
negative_prompt
Specify things to not see in the output
bad quality, comic, anime, cgi, drawing, illustration, axe
num_outputs
Number of output images
3
width
Output image width
1200
height
Output image height
1200
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
1.5
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
-1
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 SDE Exponential
samping_steps
Number of denoising steps
80
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
sdxl_vae.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)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
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/88e293af67c348bcb09dd3a29922cdb5/00000-2980712675.webp
https://files.tungsten.run/uploads/4036a8b644a64179a37c80b8aa995714/00001-2980712676.webp
https://files.tungsten.run/uploads/83b7a06c7dc44a0db4ec4deaa26f12c0/00002-2980712677.webp
Finished in 300.9 seconds
Setting up the model... Preparing inputs... Processing... Using seed 2980712675 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: cinematic film still ((photo:1.2)), A mouse outside dramatic lighting, dynamic pose, dynamic camera, masterpiece, best quality, dark shadows, ((dark fantasy)) ,wearing a golden armor, detailed, realistic, 8k uhd, high quality, detailed, realistic, 8k uhd, high quality . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy, <lora:add-detail-xl:1.5> Full negative prompt: bad quality, comic, anime, cgi, drawing, illustration, axe 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:04<05:32, 4.20s/it] 2%|▎ | 2/80 [00:07<05:07, 3.94s/it] 4%|▍ | 3/80 [00:11<05:06, 3.98s/it] 5%|▌ | 4/80 [00:16<05:07, 4.05s/it] 6%|▋ | 5/80 [00:20<05:02, 4.03s/it] 8%|▊ | 6/80 [00:24<04:58, 4.03s/it] 9%|▉ | 7/80 [00:28<04:53, 4.03s/it] 10%|█ | 8/80 [00:32<04:54, 4.08s/it] 11%|█▏ | 9/80 [00:36<04:47, 4.05s/it] 12%|█▎ | 10/80 [00:40<04:42, 4.03s/it] 14%|█▍ | 11/80 [00:44<04:37, 4.03s/it] 15%|█▌ | 12/80 [00:48<04:32, 4.01s/it] 16%|█▋ | 13/80 [00:52<04:26, 3.97s/it] 18%|█▊ | 14/80 [00:55<04:18, 3.91s/it] 19%|█▉ | 15/80 [00:59<04:13, 3.90s/it] 20%|██ | 16/80 [01:03<04:10, 3.91s/it] 21%|██▏ | 17/80 [01:07<04:04, 3.87s/it] 22%|██▎ | 18/80 [01:11<04:05, 3.96s/it] 24%|██▍ | 19/80 [01:16<04:07, 4.05s/it] 25%|██▌ | 20/80 [01:19<03:58, 3.98s/it] 26%|██▋ | 21/80 [01:23<03:51, 3.92s/it] 28%|██▊ | 22/80 [01:27<03:48, 3.94s/it] 29%|██▉ | 23/80 [01:31<03:41, 3.89s/it] 30%|███ | 24/80 [01:35<03:41, 3.96s/it] 31%|███▏ | 25/80 [01:39<03:34, 3.90s/it] 32%|███▎ | 26/80 [01:42<03:27, 3.85s/it] 34%|███▍ | 27/80 [01:46<03:26, 3.90s/it] 35%|███▌ | 28/80 [01:50<03:20, 3.86s/it] 36%|███▋ | 29/80 [01:54<03:12, 3.78s/it] 38%|███▊ | 30/80 [01:58<03:09, 3.79s/it] 39%|███▉ | 31/80 [02:01<03:01, 3.70s/it] 40%|████ | 32/80 [02:05<02:55, 3.66s/it] 41%|████▏ | 33/80 [02:08<02:51, 3.64s/it] 42%|████▎ | 34/80 [02:12<02:46, 3.63s/it] 44%|████▍ | 35/80 [02:16<02:46, 3.71s/it] 45%|████▌ | 36/80 [02:19<02:42, 3.70s/it] 46%|████▋ | 37/80 [02:23<02:42, 3.77s/it] 48%|████▊ | 38/80 [02:27<02:36, 3.72s/it] 49%|████▉ | 39/80 [02:31<02:33, 3.75s/it] 50%|█████ | 40/80 [02:35<02:29, 3.73s/it] 51%|█████▏ | 41/80 [02:38<02:24, 3.70s/it] 52%|█████▎ | 42/80 [02:42<02:19, 3.67s/it] 54%|█████▍ | 43/80 [02:46<02:22, 3.85s/it] 55%|█████▌ | 44/80 [02:51<02:27, 4.08s/it] 56%|█████▋ | 45/80 [02:54<02:17, 3.93s/it] 57%|█████▊ | 46/80 [02:58<02:09, 3.81s/it] 59%|█████▉ | 47/80 [03:02<02:06, 3.82s/it] 60%|██████ | 48/80 [03:05<01:58, 3.72s/it] 61%|██████▏ | 49/80 [03:09<01:56, 3.77s/it] 62%|██████▎ | 50/80 [03:13<01:51, 3.72s/it] 64%|██████▍ | 51/80 [03:16<01:45, 3.65s/it] 65%|██████▌ | 52/80 [03:20<01:45, 3.75s/it] 66%|██████▋ | 53/80 [03:24<01:41, 3.77s/it] 68%|██████▊ | 54/80 [03:27<01:35, 3.66s/it] 69%|██████▉ | 55/80 [03:31<01:34, 3.78s/it] 70%|███████ | 56/80 [03:35<01:27, 3.64s/it] 71%|███████▏ | 57/80 [03:39<01:26, 3.77s/it] 72%|███████▎ | 58/80 [03:42<01:20, 3.66s/it] 74%|███████▍ | 59/80 [03:46<01:15, 3.60s/it] 75%|███████▌ | 60/80 [03:49<01:08, 3.43s/it] 76%|███████▋ | 61/80 [03:52<01:06, 3.52s/it] 78%|███████▊ | 62/80 [03:56<01:02, 3.47s/it] 79%|███████▉ | 63/80 [03:59<00:56, 3.35s/it] 80%|████████ | 64/80 [04:02<00:54, 3.41s/it] 81%|████████▏ | 65/80 [04:06<00:50, 3.38s/it] 82%|████████▎ | 66/80 [04:09<00:48, 3.47s/it] 84%|████████▍ | 67/80 [04:13<00:44, 3.39s/it] 85%|████████▌ | 68/80 [04:16<00:41, 3.48s/it] 86%|████████▋ | 69/80 [04:19<00:37, 3.38s/it] 88%|████████▊ | 70/80 [04:22<00:33, 3.30s/it] 89%|████████▉ | 71/80 [04:26<00:30, 3.40s/it] 90%|█████████ | 72/80 [04:29<00:26, 3.36s/it] 91%|█████████▏| 73/80 [04:33<00:23, 3.34s/it] 92%|█████████▎| 74/80 [04:35<00:18, 3.16s/it] 94%|█████████▍| 75/80 [04:38<00:15, 3.00s/it] 95%|█████████▌| 76/80 [04:41<00:11, 2.93s/it] 96%|█████████▋| 77/80 [04:44<00:09, 3.08s/it] 98%|█████████▊| 78/80 [04:47<00:06, 3.07s/it] 99%|█████████▉| 79/80 [04:50<00:02, 2.82s/it] 100%|██████████| 80/80 [04:51<00:00, 2.56s/it] 100%|██████████| 80/80 [04:51<00:00, 3.65s/it] Decoding latents in cuda:0... done in 3.43s Move latents to cpu... done in 0.04s Uploading outputs... Finished.
prompt
Specify things to see in the output
cinematic film still ((photo:1.2)), A mouse outside dramatic lighting, dynamic pose, dynamic camera, masterpiece, best quality, dark shadows, ((dark fantasy)) ,wearing a golden armor, detailed, realistic, 8k uhd, high quality, detailed, realistic, 8k uhd, high quality . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
negative_prompt
Specify things to not see in the output
bad quality, comic, anime, cgi, drawing, illustration, axe
num_outputs
Number of output images
3
width
Output image width
1200
height
Output image height
1200
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
1.5
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
-1
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 SDE Exponential
samping_steps
Number of denoising steps
80
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
sdxl_vae.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)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
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/88e293af67c348bcb09dd3a29922cdb5/00000-2980712675.webp
https://files.tungsten.run/uploads/4036a8b644a64179a37c80b8aa995714/00001-2980712676.webp
https://files.tungsten.run/uploads/83b7a06c7dc44a0db4ec4deaa26f12c0/00002-2980712677.webp
Finished in 300.9 seconds
Setting up the model... Preparing inputs... Processing... Using seed 2980712675 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: cinematic film still ((photo:1.2)), A mouse outside dramatic lighting, dynamic pose, dynamic camera, masterpiece, best quality, dark shadows, ((dark fantasy)) ,wearing a golden armor, detailed, realistic, 8k uhd, high quality, detailed, realistic, 8k uhd, high quality . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy, <lora:add-detail-xl:1.5> Full negative prompt: bad quality, comic, anime, cgi, drawing, illustration, axe 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:04<05:32, 4.20s/it] 2%|▎ | 2/80 [00:07<05:07, 3.94s/it] 4%|▍ | 3/80 [00:11<05:06, 3.98s/it] 5%|▌ | 4/80 [00:16<05:07, 4.05s/it] 6%|▋ | 5/80 [00:20<05:02, 4.03s/it] 8%|▊ | 6/80 [00:24<04:58, 4.03s/it] 9%|▉ | 7/80 [00:28<04:53, 4.03s/it] 10%|█ | 8/80 [00:32<04:54, 4.08s/it] 11%|█▏ | 9/80 [00:36<04:47, 4.05s/it] 12%|█▎ | 10/80 [00:40<04:42, 4.03s/it] 14%|█▍ | 11/80 [00:44<04:37, 4.03s/it] 15%|█▌ | 12/80 [00:48<04:32, 4.01s/it] 16%|█▋ | 13/80 [00:52<04:26, 3.97s/it] 18%|█▊ | 14/80 [00:55<04:18, 3.91s/it] 19%|█▉ | 15/80 [00:59<04:13, 3.90s/it] 20%|██ | 16/80 [01:03<04:10, 3.91s/it] 21%|██▏ | 17/80 [01:07<04:04, 3.87s/it] 22%|██▎ | 18/80 [01:11<04:05, 3.96s/it] 24%|██▍ | 19/80 [01:16<04:07, 4.05s/it] 25%|██▌ | 20/80 [01:19<03:58, 3.98s/it] 26%|██▋ | 21/80 [01:23<03:51, 3.92s/it] 28%|██▊ | 22/80 [01:27<03:48, 3.94s/it] 29%|██▉ | 23/80 [01:31<03:41, 3.89s/it] 30%|███ | 24/80 [01:35<03:41, 3.96s/it] 31%|███▏ | 25/80 [01:39<03:34, 3.90s/it] 32%|███▎ | 26/80 [01:42<03:27, 3.85s/it] 34%|███▍ | 27/80 [01:46<03:26, 3.90s/it] 35%|███▌ | 28/80 [01:50<03:20, 3.86s/it] 36%|███▋ | 29/80 [01:54<03:12, 3.78s/it] 38%|███▊ | 30/80 [01:58<03:09, 3.79s/it] 39%|███▉ | 31/80 [02:01<03:01, 3.70s/it] 40%|████ | 32/80 [02:05<02:55, 3.66s/it] 41%|████▏ | 33/80 [02:08<02:51, 3.64s/it] 42%|████▎ | 34/80 [02:12<02:46, 3.63s/it] 44%|████▍ | 35/80 [02:16<02:46, 3.71s/it] 45%|████▌ | 36/80 [02:19<02:42, 3.70s/it] 46%|████▋ | 37/80 [02:23<02:42, 3.77s/it] 48%|████▊ | 38/80 [02:27<02:36, 3.72s/it] 49%|████▉ | 39/80 [02:31<02:33, 3.75s/it] 50%|█████ | 40/80 [02:35<02:29, 3.73s/it] 51%|█████▏ | 41/80 [02:38<02:24, 3.70s/it] 52%|█████▎ | 42/80 [02:42<02:19, 3.67s/it] 54%|█████▍ | 43/80 [02:46<02:22, 3.85s/it] 55%|█████▌ | 44/80 [02:51<02:27, 4.08s/it] 56%|█████▋ | 45/80 [02:54<02:17, 3.93s/it] 57%|█████▊ | 46/80 [02:58<02:09, 3.81s/it] 59%|█████▉ | 47/80 [03:02<02:06, 3.82s/it] 60%|██████ | 48/80 [03:05<01:58, 3.72s/it] 61%|██████▏ | 49/80 [03:09<01:56, 3.77s/it] 62%|██████▎ | 50/80 [03:13<01:51, 3.72s/it] 64%|██████▍ | 51/80 [03:16<01:45, 3.65s/it] 65%|██████▌ | 52/80 [03:20<01:45, 3.75s/it] 66%|██████▋ | 53/80 [03:24<01:41, 3.77s/it] 68%|██████▊ | 54/80 [03:27<01:35, 3.66s/it] 69%|██████▉ | 55/80 [03:31<01:34, 3.78s/it] 70%|███████ | 56/80 [03:35<01:27, 3.64s/it] 71%|███████▏ | 57/80 [03:39<01:26, 3.77s/it] 72%|███████▎ | 58/80 [03:42<01:20, 3.66s/it] 74%|███████▍ | 59/80 [03:46<01:15, 3.60s/it] 75%|███████▌ | 60/80 [03:49<01:08, 3.43s/it] 76%|███████▋ | 61/80 [03:52<01:06, 3.52s/it] 78%|███████▊ | 62/80 [03:56<01:02, 3.47s/it] 79%|███████▉ | 63/80 [03:59<00:56, 3.35s/it] 80%|████████ | 64/80 [04:02<00:54, 3.41s/it] 81%|████████▏ | 65/80 [04:06<00:50, 3.38s/it] 82%|████████▎ | 66/80 [04:09<00:48, 3.47s/it] 84%|████████▍ | 67/80 [04:13<00:44, 3.39s/it] 85%|████████▌ | 68/80 [04:16<00:41, 3.48s/it] 86%|████████▋ | 69/80 [04:19<00:37, 3.38s/it] 88%|████████▊ | 70/80 [04:22<00:33, 3.30s/it] 89%|████████▉ | 71/80 [04:26<00:30, 3.40s/it] 90%|█████████ | 72/80 [04:29<00:26, 3.36s/it] 91%|█████████▏| 73/80 [04:33<00:23, 3.34s/it] 92%|█████████▎| 74/80 [04:35<00:18, 3.16s/it] 94%|█████████▍| 75/80 [04:38<00:15, 3.00s/it] 95%|█████████▌| 76/80 [04:41<00:11, 2.93s/it] 96%|█████████▋| 77/80 [04:44<00:09, 3.08s/it] 98%|█████████▊| 78/80 [04:47<00:06, 3.07s/it] 99%|█████████▉| 79/80 [04:50<00:02, 2.82s/it] 100%|██████████| 80/80 [04:51<00:00, 2.56s/it] 100%|██████████| 80/80 [04:51<00:00, 3.65s/it] Decoding latents in cuda:0... done in 3.43s Move latents to cpu... done in 0.04s Uploading outputs... Finished.