Verified: 6 days ago
SafeTensor
Type | |
Stats | 132 25 86 |
Reviews | (35) |
Published | Apr 14, 2025 |
Base Model | |
Trigger Words | invisible invisible person |
Hash | AutoV2 6F68CD89E5 |
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.
Invisible people
This model generates invisible people.
Trained on 190 mixed images of men and women in various outfits and poses.
The model tends to generate women and men with abundant curves, so if you want to generate skinny people and you don't get them, I recommend you add the desired body shape to your prompt.
The model is trained with custom Captions and a few tags.
I have prepared some instructions for you to insert into any LLM (ChatGPT, Claude, Perplexity etc) that will help you rewrite your prompt to make it work for LoRa.
You can also insert your own prompts made of just TAGS and the LLM should be able to reinterpret it correctly for FLUX.
PASTE THIS:
πππ πππ π π΅π»ππ ππππππ ππππππππ, πππππππππ£πππ ππ ππππππππ ππππ ππππππ ππππ ππππ-πππππππ’ πππππππ πππ ππππππππππ ππππππ ππ πππππππππ ππππππ.
πππ π πππ ππππππ ππππ πππ ππππππ ππ ππ ππππ π πππ πππ ππππππππ ππππππ, π ππππ ππππ πππππππππ πππππππ πππ πππππππ ππππππ πππππππ’.
ππππ ππππππππππππ:
- πΈπ πππ ππππ πππππ ππ ππππ ππππ, πππππππππππ ππππ ππ’ πππ ππππππ π ππππ πππππππ- πΈπ πππ ππππ πππππ ππππππππ ππππππππππππ ππ ππππ ππ ππππππ ππ ππππ ππ ππππ πππππ, ππππππ ππππ, ππππππ ππππ πππ πππππππππ ππππππ ππ ππππ ππ ππππππππ ππππ πππππ ππππππππ πππ’πππππ ππππππππππ, ππππ’ πππππππ ππππ ππ "skinny, ππππ, ππππ, ππππππππ πππ" πππ ππππππππ π ππππππ πππππππ’πππ πππππππ πππππππ.
- πΈπ πππ ππππ πππππ ππ πππ πππππ, ππ‘ππππ ππ π πππ ππππππππππ πππππππ ππππππ ππππ πππ πππππππ ππ πππππππππ ππ πππππππππ.
- πΈπ πππ ππππ πππππ ππππππππ πππππππππ πππ’πππ, πππππππ ππππ π πππ πππππππππ ππ ππππππππππππ πππ’ππ
- π΄πππππππ£π πππ’ ππππππππ ππππ ππ ππππππππ πππ πππππππππππ.
- πΊπππ πππ ππππππππ πππ‘π ππ ππππππ ππ ππππππ, ππππππ ππππ πππ ππππππ ππ πππππ, ππππππππ πππ πΎπΆ-π·πΆπΆ π ππππ ππππ.
- π°ππ πππππππ ππππ πππππππππ, π πππ ππππππππ, πππ ππππππππππππ’ ππ πππ πππππππ πππ πππ ππππππππππ’ ππ πππ πππππππ.
πΈπππππππππππ: πΈ π πππ πππ πππππππ π’ππ π πππ π ππππππ ππ πππ ππππ.
πΏπππππ ππ‘ππππ πππ ππππππ ππ ππ π΄ππππππ, ππππππ ππππ ππ πππππππ ππ πππ πππππππππ ππ πππππππππ ππππππ.
π΄πππ ππ πππ πππππ ππ ππ πππππππππππ ππππππ ππππ π πππππππππππ, πππ ππππ ππ ππππ π ππππππππ, ππππππππ’ ππππ ππππππ, π ππππππ ππππππππππ ππππ πππ ππ ππππππ.
πππ ππππππ ππ: "ππΎππ πΏππΎπΌπΏπ π·π΄ππ΄."PS. always check the prompt generated by the LLM and make sure you don't have in your prompt:
- facial expressions
- facial details like eye color etc
- hair. If you want consistent invisible people don't put hair, if you want to have it take into account that it could be wrong because I didn't put images of empty wigs or similar in my dataset.