Upload 897413/1990969/README.md with huggingface_hub

897413/1990969/README.md

@@ -1,7 +1,6 @@
 ---
 license: other
 tags:
-- base model
 - girls
 - photorealistic
 - realistic
@@ -17,7 +16,7 @@ tags:
 
 **Trigger Words**: None
 
-**Tags**: base model, girls, photorealistic, realistic, sexy, woman
+**Tags**: girls, photorealistic, realistic, sexy, woman
 
 ## Gallery
 
@@ -44,7 +43,7 @@ tags:
 
 ## Description
 
-### **Alternatively download Big Love Ultra5, Photo6, Zuna1 or Zia1 for $5.50 and Hyper1 for $10 on** [**Fanvue**](https://www.fanvue.com/subtleshader)**. Click 'Follow', buy a post, check your Fanvue DMs! You can get Klein2 by** [**tipping me**](https://civitai.red/user/SubtleShader) **20k buzz or for $10 on** [**Tensor Art**](https://tensor.art/models/979609056106831593/Big-Love-Klein2-fp8)**.**
+### **Alternatively download Big Love Eryn1, Ultra5, Photo6, Zuna1 or Zia1 for $5.50 and Hyper1 for $10 on** [**Fanvue**](https://www.fanvue.com/subtleshader)**. Click 'Follow', buy a post, check your Fanvue DMs! You can get Klein2 for $10 on** [**Tensor Art**](https://tensor.art/models/979609056106831593/Big-Love-Klein2-fp8)**.**
 
 **To create up to 85 free images per day in highest quality you can use** [**Big Love here**](https://tensor.art/models/942991393301752322?source_id=nzu0r1_nkEa0o_QubHvz8BUm)**. For discussing photorealistic image generation join me on** [**Discord**](https://discord.gg/Ub69S8VRna)**.**
 
@@ -64,8 +63,13 @@ Big Love is a merge of various SDXL models. The newest Photo/Insta/Lust versions
 
 **Big Love Hyper** supports generating at image sizes of 1664x2232 (4 megapixel) and higher. Can be easily upscaled to 9 megapixel unlike the normal low-res images. Hyper currently has not fully stable anatomy, so needs more runs. Some prompts work better than others. It produces highly detailed and life-like images close to real photos. It has a special quality that cannot be achieved by just upscaling. The Hyper versions of Big Love are pay-only and special license conditions apply. See below.
 
+**Big Love Eryn** is a fine-tune of Ernie-Image(-Turbo). You can run it locally with ComfyUI and [**Forge Neo**](https://github.com/Haoming02/sd-webui-forge-classic/tree/neo). The fp8 version works with 8 & 12 GB VRAM. Use the (pruned) bf16 version if you have 16 GB VRAM or more. The "Full" versions are only meant for training a lora (coming soon!). Put the downloaded model into the *diffusion models* sub folder of ComfyUI or the *StableDiffusion* sub folder of Forge Neo. You additionally need to place [ministral-3-3b.safetensors](https://huggingface.co/Comfy-Org/ERNIE-Image/resolve/main/text_encoders/ministral-3-3b.safetensors?download=true) in the text\_encoder sub folder and [flux2-vae.safetensors](https://huggingface.co/Comfy-Org/ERNIE-Image/resolve/main/vae/flux2-vae.safetensors?download=true) in the VAE sub folder.
+
 Pony1/Pony2/XL1 versions were optimized for the Lightning lora while the newer versions were optimized for the DMD2 lora. Both loras speed up rendering by a factor of 3-6x and let Big Love produce more photorealistic results. It is not recommended to use SDXL version of Big Love without DMD2 or at least Lightning. The results will be not be as good. Big Love ZT, Zia and Klein already have a "speed lora" built-in.
 
+**Eryn Settings:**  
+4-6 steps (3-4 steps for upscaling), cfg1, Euler sampler, Beta scheduler, 832x1216 or 1024x1536 pixels
+
 **Klein Settings:**  
 4 steps (2 steps for upscaling), cfg1, Euler sampler, Beta scheduler, 832x1216, 1024x1536, 1280x1920 or 1536x2240 pixels
 
@@ -94,7 +98,7 @@ Download one of the following images and drag'n'drop it onto Comfy:
 [SDXL DMD2 txt2ing & Upscale for Big Love Ultra](https://civitai.com/images/112124886)  
 [SDXL DMD2 img2img Workflow](https://civitai.com/images/106855958)  
 [SDXL Lightning Workflow](https://civitai.com/images/40128760)  
-**Klein workflows are embedded in the showcase images. Just drag'n'drop into Comfy.**  
+**Klein and Eryn workflows are embedded in the showcase images. Just drag'n'drop into Comfy.**  
 With the Lightning lora it is better to use [Forge](https://github.com/lllyasviel/stable-diffusion-webui-forge). ComfyUI is not able to do as many upscaling steps with Lightning as Forge without adding grain. But if you use the DMD2 lora, ComfyUI does just fine.
 
 **Trained Concepts:**  
@@ -109,7 +113,7 @@ Newer versions of Big Love include the concepts of older versions, e.g. Photo4 c
 
 **Training a (character) lora**  
 My advice is this: Take 10-30 high quality images (at least 50-100 for styles or poses), download [OneTrainer](https://github.com/Nerogar/OneTrainer), click the SDXL lora preset, choose Big Love as the base checkpoint, add your images as a concept, add tags on the Tools tab, and start training. If you train on Big Love Ultra change the training resolution to 1536 and provide 1248x1832 images.  
-You will only get the full Big Love quality by training on real photos or extremely photorealistic images, which is usually not the case with a fictional character. It is all about image quality and not choosing boring images. Don't add posing images to a character lora, because Big Love provides the posing later for it. Focus mainly on good portraits with a few upper and full body images. Rather fewer higher quality images than a lot of average images. Read here for [traing a lora on Big Love ZT2](https://civitai.com/models/897413?modelVersionId=2580484&dialog=commentThread&commentId=1073311), [ZT3](https://civitai.com/models/897413/big-love?modelVersionId=2768854&dialog=commentThread&commentId=1117342), [Zia1](https://civitai.com/models/897413/big-love?dialog=commentThread&commentId=1158101) and [Zuna1](https://civitai.com/models/897413/big-love?dialog=commentThread&commentId=1157288).
+You will only get the full Big Love quality by training on real photos or extremely photorealistic images, which is usually not the case with a fictional character. It is all about image quality and not choosing boring images. Don't add posing images to a character lora, because Big Love provides the posing later for it. Focus mainly on good portraits with a few upper and full body images. Rather fewer higher quality images than a lot of average images. Read here for [traing a lora on Big Love ZT2](https://civitai.com/models/897413?modelVersionId=2580484&dialog=commentThread&commentId=1073311), [ZT3](https://civitai.com/models/897413/big-love?modelVersionId=2768854&dialog=commentThread&commentId=1117342), [Zia1](https://civitai.com/models/897413/big-love?dialog=commentThread&commentId=1158101), [Zuna1](https://civitai.com/models/897413/big-love?dialog=commentThread&commentId=1157288) or [Eryn1](https://civitai.red/models/897413/big-love?modelVersionId=2883972&dialog=commentThread&commentId=1178177).
 
 **Fixing Anatomy**  
 If you want to keep the seed and repair anatomical problems in an image, activate the Extra checkbox in A1111/Forge and set Variation Strength to 0.01 to 0.1. Then generate until anatomy is fine. In Comfy there are sampler nodes that support variation seed (e.g. [Inspire Pack](https://github.com/ltdrdata/ComfyUI-Inspire-Pack)), which do the same thing. Also possible to change steps or add commas to the prompt, but I do not recommend it. Extra/Variation Seed is more powerful and convenient as it gives you endless variations with just one click. There is always a variation which looks similar or even better with great anatomy.  
@@ -163,7 +167,7 @@ You can highly improve the images generated with this model by using img2img, up
 Big Love SDXL versions are licensed under CreativeML Open RAIL++M (dated July 26, 2023), the Big Love Z-Image versions are licensed under Apache 2.0, and the Big Love Klein versions are licensed under the FLUX Non-Commercial License (Black Forest Labs Inc.), with the following additional terms:   
   
 For clarity, the following version tiers are defined:  
-***Restricted versions****: Ultra, Hyper, Klein, Zia, Zuna*  
+***Restricted versions****: Ultra, Hyper, Klein, Zia, Zuna, Eryn*  
 ***Open versions****: Pony, XL, Photo, Insta, Lust, ZT*   
   
 *1. You may use Big Love without crediting the creator.*  
@@ -176,7 +180,7 @@ For clarity, the following version tiers are defined:
 *8. All use-based restrictions of the CreativeML Open RAIL++M license apply to SDXL versions and their derivatives. All use-based restrictions of the FLUX Non-Commercial License apply to Klein versions and their derivatives.*  
 *9. Any restrictions in these additional terms may be waived only with explicit written permission from the creator.*   
   
-TLDR: This is basically the same license as before (just stated more clearly), so nothing changes for the *Pony, XL, Photo, Insta, Lust and ZT* versions of Big Love. However, further restrictions were added for *Ultra, Hyper, Klein, Zia and Zuna* versions (no merging, no redistribution). The "Share merges" condition below the license on the right hand side was only deactivated because of the restricted versions. Merging is still allowed for the open versions.
+TLDR: This is basically the same license as before (just stated more clearly), so nothing changes for the *Pony, XL, Photo, Insta, Lust and ZT* versions of Big Love. However, restrictions were added for *Ultra, Hyper, Klein, Zia, Zuna and Eryn* versions (no merging, no redistribution). The "Share merges" condition below the license on the right hand side was only deactivated because of the restricted versions. Merging is still allowed for the open versions.
 
 *Many thanks to the creators of SDXL, Z, Flux klein, Pony, bigAsp and Lustify for making their wonderful models available. Big thanks to* [*RaymondLuxuryYacht*](https://civitai.com/user/RaymondLuxuryYacht) *for allowing me to train on his fabulous images.*
 
@@ -188,4 +192,4 @@ Model: [CivitAI Model Page](https://civitai.com/models/897413?modelVersionId=199
 
 Archive: [CivArchive Page](https://civarchive.com/models/897413?modelVersionId=1990969)
 
-<!-- Version: 20260422_v4_update -->
+<!-- Version: 20260502_upload -->