Verified: 9 months ago
SafeTensor
Type | |
Stats | 1,800 1,125 5.9k |
Reviews | (308) |
Published | Aug 20, 2024 |
Base Model | |
Training | Steps: 1,726 Epochs: 34 |
Usage Tips | Clip Skip: 1 |
Hash | AutoV2 00F1CB2743 |
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.
Like my work?
Join me on the FLUX64 Discord and have a chat with me!
Since FLUX64 is so well received, I will be training a V2 to hopefully get even more believable results, this might take a little time and a little money, as I will be trying different methods to see what works best. Thank you for your great feedback, I'm glad you enjoy this Lora as much as I do!
Welcome to FLUX64!
This Lora was trained on screenshots of both N64 and PS1 games, altough it has heavy influence by the Zelda style.
Try using the tag "ningraphix", sometimes you'll archive better results without it though.
Good tags to use:
third person
facing camera/away from camera
legend of zelda
heads up display
If the generated image doesn't quite look like a game screenshot, try increasing Flux guidance to above 3.5 (I tend to have good results at around 4)