GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
obann001
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
obann001
Model Tree
black-forest-labs/FLUX.1-dev
Input Modalities
Output Modalities
Supported Functionality
LoRA FLUX orientée personnage Fowx (checkpoint step 344), publiée pour évaluation visuelle et itération rapide.
DARK/flux_lora_file_fowx_network128_rank32_bf16-step00344flux_lora_file_fowx_network128_rank32_bf16-step00344.safetensorsfowx| Champ | Valeur |
|---|---|
| Identité | Fowx (avatar) |
| Trigger / token | fowx |
| Stack | FLUX LoRA |
| Rank / Alpha | 32 / 128 |
| Dataset source | /raid1_II/Pictures/Avatars_et_Persos/FowxBrown/Step_3/images/1_fowx/ |
| Step checkpoint | 344 |
| Objectif | fidélité personnage + généralisation contrôlée |
portrait photo of fowx, soft daylight, 85mm lens, shallow depth of fieldfowx, cinematic indoor scene, side lighting, natural skin texturefull body photo of fowx walking in city at dusk, realistic detailsfowx holding a cup, hands visible, casual outfit, neutral backgroundNegative prompt conseillé:
deformed hands, extra fingers, bad anatomy, blurry, low quality, overexposed, watermark, text
python
from diffusers import FluxPipelineimport torch pipe = FluxPipeline.from_pretrained( "black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)pipe.load_lora_weights( "DARK/flux_lora_file_fowx_network128_rank32_bf16-step00344", weight_name="flux_lora_file_fowx_network128_rank32_bf16-step00344.safetensors")pipe.to("cuda") image = pipe( "portrait photo of fowx, soft daylight, 85mm lens", guidance_scale=3.5, num_inference_steps=28).images[0]image.save("fowx_step00344.png")from diffusers import FluxPipelineimport torch pipe = FluxPipeline.from_pretrained( "black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)pipe.load_lora_weights( "DARK/flux_lora_file_fowx_network128_rank32_bf16-step00344", weight_name="flux_lora_file_fowx_network128_rank32_bf16-step00344.safetensors")pipe.to("cuda") image = pipe( "portrait photo of fowx, soft daylight, 85mm lens", guidance_scale=3.5, num_inference_steps=28).images[0]image.save("fowx_step00344.png")