Views
No views yet
colville
Retrained onto FLUX.2 [klein] 4B from ms2stationthis/colvilleflux (FLUX.1-dev). |  |
|---|---|
| colville, This colville image is a digital painting depicting a dark, almost black horse… | colville, This is a detailed, realistic digital illustration in a colville style, depicti… |
 |  |
| :---: | :---: |
| colville, This image is a digital painting depicting a woman on a ship, observing the hor… | colville, This is a detailed, realistic drawing in the style of a Colville-esque watercol… |
1import torch
2from diffusers import Flux2Pipeline
3
4pipe = Flux2Pipeline.from_pretrained(
5 "black-forest-labs/FLUX.2-klein-4B", torch_dtype=torch.bfloat16
6).to("cuda")
7pipe.load_lora_weights("ms2stationthis/colvilleflux-klein")
8image = pipe("colville, a character portrait", guidance_scale=4.0, num_inference_steps=25).images[0]
9image.save("out.png")| LoRA strength | Guidance | Steps | Resolution |
|---|---|---|---|
| 0.8–1.0 | 4.0 | 25 | 1024×1024 |
dataset/ (19 image-caption pairs) and the exact config.yaml so the LoRA can be retrained as-is.