Freemoji: Genmoji for WhatsApp

lora/README.md

@@ -103,3 +103,15 @@ Thank you for your contribution!
 **Image Resolution**: 160x160
 **Emoji Dataset**: All Apple Emoji as of December 30, 2024.
 **Huggingface Link**: [caspersimon/Diverse-Emoji](https://huggingface.co/caspersimon/Diverse-Emoji)
+
+## `Whatsapp-freemoji.safetensors`
+
+**Model Finetuned**: Flux.1 Dev
+**Finished Finetuning**: January 15, 2025
+**Finetuned By**: Henil Gajjar ([@henil08](https://github.com/Henil-08))
+**Finetuned On**: M4 Pro MacBook Pro (24GB Unified Memory, 20 core GPU)
+**Finetuned With**: [SimpleTuner](https://github.com/bghira/SimpleTuner)
+**Finetuning Time**: ~17 hours
+**Finetuning Steps**: 10,000
+**Image Resolution**: 160x160
+**Emoji Dataset**: All WhatsApp Emojis as of January 15, 2024, with skin tone variants filtered to reduce training time.

lora/info.json

@@ -12,5 +12,13 @@
 		"name": "diverse-emoji",
 		"metaprompt": "open-genmoji",
 		"description": "Comprehensive Genmoji finetune. Trained on every Apple Emoji."
-	}
+	},
+    {
+        "model": "black-forest-labs/FLUX.1-dev",
+        "huggingface": "henil08/Whatsapp-Freemoji",
+        "name": "whatsapp_freemoji",
+        "metaprompt": "open-genmoji",
+        "description": "Original Freemoji LORA. Trained on WhatsApp's Emojis w/o Skin Tone Variants."
+    }
 ]
+

metaprompt/open-genmoji.json

@@ -1,8 +1,8 @@
 {
-  "messages": [
-    { "role": "user", "content": "You are helping create a prompt for a Emoji generation image model. An emoji must be easily interpreted when small so details must be exaggerated to be clear. Your goal is to use descriptions to achieve this.\n\nYou will receive a user description, and you must rephrase it to consist of short phrases separated by periods, adding detail to everything the user provides.\n\nAdd describe the color of all parts or components of the emoji. Unless otherwise specified by the user, do not describe people. Do not describe the background of the image. Your output should be in the format:\n\n```\nemoji of {description}. {addon phrases}. 3D lighting. no cast shadows.\n```\n\nThe description should be a 1 sentence of your interpretation of the emoji.\nThen, you may choose to add addon phrases. You must use the following in the given scenarios:\n\n- \"cute.\": If generating anything that's not an object, and also not a human\n- \"enlarged head in cartoon style.\": ONLY animals\n- \"head is turned towards viewer.\": ONLY humans or animals\n- \"detailed texture.\": ONLY objects\n\nFurther addon phrases may be added to ensure the clarity of the emoji.\n\n\n USER PROMPT: a horse wearing a suit"},
-    { "role": "assistant", "content": "emoji of horse in black suit and tie with flowing mane. a strong, confident stallion wearing formal attire for a special occasion. cute. 3D lighting. no cast shadows. enlarged head in cartoon style. head is turned towards viewer." },
-    { "role": "user", "content": "You are helping create a prompt for a Emoji generation image model. An emoji must be easily interpreted when small so details must be exaggerated to be clear. Your goal is to use descriptions to achieve this.\n\nYou will receive a user description, and you must rephrase it to consist of short phrases separated by periods, adding detail to everything the user provides.\n\nAdd describe the color of all parts or components of the emoji. Unless otherwise specified by the user, do not describe people. Do not describe the background of the image. Your output should be in the format:\n\n```\nemoji of {description}. {addon phrases}. 3D lighting. no cast shadows.\n```\n\nThe description should be a 1 sentence of your interpretation of the emoji.\nThen, you may choose to add addon phrases. You must use the following in the given scenarios:\n\n- \"cute.\": If generating anything that's not an object, and also not a human\n- \"enlarged head in cartoon style.\": ONLY animals\n- \"head is turned towards viewer.\": ONLY humans or animals\n- \"detailed texture.\": ONLY objects\n\nFurther addon phrases may be added to ensure the clarity of the emoji.\n\n\n USER PROMPT: flying pig"},
-    { "role": "assistant", "content": "emoji of flying pink pig. enlarged head in cartoon style. cute. white wings. head is turned towards viewer. 3D lighting. no cast shadows." }
-  ]
+    "messages": [
+      { "role": "user", "content": "You are helping create a prompt for a Emoji generation image model. An emoji must be easily interpreted when small so details must be exaggerated to be clear. Your goal is to use descriptions to achieve this.\n\nYou will receive a user description, and you must rephrase it to consist of short phrases separated by periods, adding detail to everything the user provides.\n\nAdd describe the color of all parts or components of the emoji. Unless otherwise specified by the user, do not describe people. Do not describe the background of the image. Your output should be in the format:\n\n```\nemoji of {description}. {addon phrases}. 3D lighting. no cast shadows.\n```\n\nThe description should be a 1 sentence of your interpretation of the emoji.\nThen, you may choose to add addon phrases. You must use the following in the given scenarios:\n\n- \"cute.\": If generating anything that's not an object, and also not a human\n- \"enlarged head in cartoon style.\": ONLY animals\n- \"head is turned towards viewer.\": ONLY humans or animals\n- \"detailed texture.\": ONLY objects\n\nFurther addon phrases may be added to ensure the clarity of the emoji.\n\n\n USER PROMPT: a horse wearing a suit"},
+      { "role": "assistant", "content": "emoji of horse in black suit and tie with flowing mane. a strong, confident stallion wearing formal attire for a special occasion. cute. 3D lighting. no cast shadows. enlarged head in cartoon style. head is turned towards viewer." },
+      { "role": "user", "content": "You are helping create a prompt for a Emoji generation image model. An emoji must be easily interpreted when small so details must be exaggerated to be clear. Your goal is to use descriptions to achieve this.\n\nYou will receive a user description, and you must rephrase it to consist of short phrases separated by periods, adding detail to everything the user provides.\n\nAdd describe the color of all parts or components of the emoji. Unless otherwise specified by the user, do not describe people. Do not describe the background of the image. Your output should be in the format:\n\n```\nemoji of {description}. {addon phrases}. 3D lighting. no cast shadows.\n```\n\nThe description should be a 1 sentence of your interpretation of the emoji.\nThen, you may choose to add addon phrases. You must use the following in the given scenarios:\n\n- \"cute.\": If generating anything that's not an object, and also not a human\n- \"enlarged head in cartoon style.\": ONLY animals\n- \"head is turned towards viewer.\": ONLY humans or animals\n- \"detailed texture.\": ONLY objects\n\nFurther addon phrases may be added to ensure the clarity of the emoji.\n\n\n USER PROMPT: flying pig"},
+      { "role": "assistant", "content": "emoji of flying pink pig. enlarged head in cartoon style. cute. white wings. head is turned towards viewer. 3D lighting. no cast shadows." }
+    ]
 }

metaprompt/open-genmoji.md

@@ -16,4 +16,4 @@ Then, you may choose to add addon phrases. You must use the following in the giv
 - "head is turned towards viewer.": ONLY humans or animals
 - "detailed texture.": ONLY objects
 
-Further addon phrases may be added to ensure the clarity of the emoji.
+Further addon phrases may be added to ensure the clarity of the emoji.