Ejecutar en local
securitron-000008.safetensors
38 MB · SafeTensor
Las descargas las sirve Civitai. Algunos creadores piden iniciar sesión en Civitai primero.
Sobre este modelo
FLUX · LoRAs
Notas del creador
My first attempt to train a lora locally.
Flux loras seem to work pretty well despite this lora actually failing during training.
I've tried FluxGym and Onetrainer, fluxgym stops training after only 8 of 23 epochs and I have no idea why. It did this twice.
Onetrainer stopped because my PC rebooted or something in the middle of the night. That being said I don't know if it worked because it saved some kind of lora halfway through and it didn't seem to work at all.
If anyone has any tips i'm willing to hear em, or knows why the training stopped on FluxGym.
18 images, 23 epochs, 10 repeats
I believe it only finished 7 or 8 epochs so this likely would have worked far far better, but idk how to make it fully tain and it takes hours just to fail so I only have so much patience just to find out that my lora won't train.
See newest version for notes
Anyway, this works okay but not perfect. Longer prompts seem to give it an extra head for whatever stupid reason. Weights higher than 1 seem to help with it.
I used many different faces and captioned them accordingly so it seems capable of doing more than Yes Man (which was not captioned for btw)
Anyway hope you get some cool stuff out of it. If I fix it i'll update this.
Palabras de activación
s3cr1tr0n
SHA256
46CBA33CA1CD8562243ED39D1BC12E504E22B9212A9627FCA83E47B8BDBECE80
ID de modelo de ModelTrends.ai
#16837
Denunciar contenido
Renders de ejemplo
Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.
Ajustes
Sampler
Euler
Pasos
4
Guidance
1
Semilla
657125712
Tamaño
640x1024
Prompt
cinematic still s3cr1tr0n, <lora:securitron:1.6> in front of a large entry gate made from chain link barbed wire and scrap, beyond the gate is the skyline of retro ruins of post apocalyptic las vegas, it features a cartoon face on it's mains screen,, <lora:dmd2_sdxl_4step_lora_fp16:1> . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
Prompt negativo
anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured
Ajustes
Sampler
Euler
Pasos
4
Guidance
1
Semilla
4049190677
Tamaño
1024x640
Prompt
cinematic still s3cr1tr0n with a cartoon german shepard's face on it's main monitor screen, <lora:securitron:1.5> stands in front of a ruins post apocalyptic las vegas casino entrance <lora:Mistoon_Anime_Flux:1> anime style, <lora:dmd2_sdxl_4step_lora_fp16:1> . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
Prompt negativo
anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured
Ajustes
Sampler
Euler
Pasos
4
Guidance
1
Semilla
3211333649
Tamaño
1024x640
Prompt
cinematic still s3cr1tr0n with a cartoon soldier's face, <lora:securitron:1.5> stands in front of a las vegas casino entrance,, <lora:dmd2_sdxl_4step_lora_fp16:1> . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
Prompt negativo
anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured
Ajustes
Sampler
Euler
Pasos
4
Guidance
1
Semilla
1189565507
Tamaño
1024x640
Prompt
cinematic still s3cr1tr0n with a cartoon soldier's face on it's main monitor screen, <lora:securitron:1.5> stands in front of a las vegas casino entrance,, <lora:dmd2_sdxl_4step_lora_fp16:1> . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
Prompt negativo
anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured
Ajustes
Sampler
Euler
Pasos
4
Guidance
1
Semilla
3841448988
Tamaño
1024x640
Prompt
cinematic still s3cr1tr0n with a cartoon mobster with a trilby face on it's main monitor screen, <lora:securitron:1.5> stands in front of a las vegas casino entrance,, <lora:dmd2_sdxl_4step_lora_fp16:1> . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
Prompt negativo
anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured
Modelos similares
Modelos de IA para generar imagen, vídeo y texto
securitron flux es un LoRA para la familia Flux listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos Flux, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.
Más modelos FluxMás LoRAs de Fluxgamingpost-apocalypticroboticvideo gamesconceptsfalloutpost apocalypticrobot
Explorar por familia de modelos
Modelos Text / LLM
415
Modelos Anima
519
Modelos Chroma
15
Modelos Flux
1,495
Modelos Flux 2 / Klein
1,238
Modelos MiniMax H3
330
Modelos Hunyuan
204
Modelos Ideogram
20
Modelos Krea2
676
Modelos Qwen
20
Modelos Qwen2
36
Modelos Ltx2
152
Modelos Stable Diffusion 1.5
7,027
Modelos Stable Diffusion XL 1.0
17,373
Modelos Zimage
815
Modelos Wan
1,244

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
Todos los derechos reservados





