import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SDXL", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("jarod2212/Ellie_TLOU_XL")
prompt = "-"
image = pipe(prompt).images[0]Ellie_TLOU_LoRA_XL
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
Model description
Ellie_TLOU_XL is an identity‑focused SDXL LoRA trained on approximately 80 original images, all created exclusively from scratch for this dataset. No downloaded material or external images were used. Every image was generated, selected, and refined manually to ensure full control over identity, lighting, and consistency.
The dataset includes:
high‑quality portraits
half‑body shots
neutral and environmental lighting
narrative scenes
recognizable locations inspired by the videogame’s world, enhancing atmosphere and contextual coherence
Training was performed on SDXL and intentionally stopped at 1750 steps, the optimal point before overfitting. This preserves:
natural skin texture
stable proportions
strong identity consistency
zero artifacts
reliable performance even under complex lighting
Best Checkpoint: The model performs exceptionally well with SDXL Base, achieving maximum identity fidelity and the most natural rendering. It also works with other neutral checkpoints, but SDXL Base remains the recommended choice.
Recommended Strength:
0.75 → maximum stability; ideal for half‑body, narrative scenes, and complex environments
0.85 → professional sweet spot; strong identity with natural skin
0.9 → maximum safe strength; extremely faithful identity without introducing artifacts
Ideal Use Cases:
Excellent for portraits (highest likeness, clean skin, precise details)
Very good for half‑body shots (stable proportions, consistent identity)
Reliable in narrative scenes (environment, dramatic lighting, post‑apocalyptic mood)
Example Prompts to generate Ellie: samples: - prompt: "ellie_tlou, close-up portrait, soft natural light, neutral background, clean skin texture, sharp eyes, subtle freckles, brown hair, realistic colors, high detail, photographic clarity" - prompt: "ellie_tlou, half body shot, natural soft light, neutral background, relaxed posture, clean outfit, realistic skin texture, sharp eyes, balanced colors, high detail, photographic clarity" - prompt: "ellie_tlou, cinematic narrative scene, dramatic lighting, expressive atmosphere, realistic textures, detailed environment, storytelling mood, high detail, filmic depth" - prompt: "detailed environment, cinematic lighting, atmospheric scenery, realistic textures, high detail, filmic depth, no people, no characters"
Download model
Trigger words
You should use ellie_tlou to trigger the image generation.
Download them in the Files & versions tab.
- Downloads last month
- 38