Verified: a year ago
SafeTensor
Created on Civitai
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
❌💲 Commercial use of this model is not allowed
This LoRA works terribly, and it's not just about arms. Sometimes it also produces images with "lowres" blur.
I can't experiment with finetunes because my PC can't even run Flux Schnell. I can't disable on-site generation. If there's a finetune that somehow gives better results I'd like to see that.
🖼DATASET
All original images are property of Team17.
Dataset does NOT contain images of worms from behind or with closed eyes.
Trained on 16 images (I reused some from my Worms render mix dataset and added 1 more image), 10 of which are from Worms Forts: Under Siege renders, the rest followed a similar style. I removed parts of text and logo in a couple of images, applied Surface blur to some images to reduce JPG artifacts, upscaled one simple image with Fooocus and... manually edited it in Photoshop (some details were lost), I wanted to upscale more but AI added unwanted details to more detailed images.