DOLL-E XL v2
I give you Doll-E v2. A skillful mix of @RAMTHRUST's Black Magic , @DucHaiten's DucHaiten-AIart-SDXL, and @Yamer's Realistic V5 Checkpoints. The fusion of which has produced a Versatile XL Masterpiece!
Doll-E is capable of generating a wide range of art styles from anime to photography when prompted to do so! It, however, excels and is meant for 2.5D Render type images. For the best effect I suggest adding "2.5D Render" to your prompt for maximum impact! I also encourage you to experiment with it as well and unlock all it's secrets!
The goal of v2 was to improve the lighting effects and color saturation of generations. I believe I have accomplished this without sacrificing the versatility of v1. This was achieved by adding an additional model to the mix (DucHaiten-AIart-SDXL) and switching Yamer's Realistic v5TX with the regular v5 for improved clarity. Let me know what you think with a comment and image post below! I do take your feedback into account.
v3 is already being worked on as well. I will be focusing on anatomy with a specific focus on the hands, and feet. Please be patient as this version could take awhile to nail down.
A special thank you to: @RAMTHRUST, @EZorg, and @hellrunner for helping me stress test the new version!
All images were created in ComfyUI using DPM++ 3M Expo, 60 steps, CLIP -2, and 5.4 CFG.
(ADetailers are rarely needed, but are suggested after an Upscale specifically for the faces.)
I hope you enjoy! Don't forget to give it a thumbs up if you did and share your generations! It's always a pleasure to see what you do with my models! Also feel free to follow me for updates and future releases!
License Stuff:
License & Use
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content.
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license.
3. You may re-distribute the weights. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the modified CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully).
Please read the full license.
Use Restrictions:
You agree not to use the Model or Derivatives of the Model:
- In any way that violates any applicable national, federal, state, local or international law or regulation
- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way
- To generate or disseminate verifiably false information and/or content with the purpose of harming others
- To generate or disseminate personal identifiable information that can be used to harm an individual
- To defame, disparage or otherwise harass others
- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation
- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics
- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm
- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories
- To provide medical advice and medical results interpretation
- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
Terms of use:
- You are solely responsible for any legal liability resulting from unethical use of this model(s)
- If you use any of these models for merging, please state what steps you took to do so and clearly indicate where modifications have been made.
Description
Added another model to assist with better lighting and color saturation. Maintained the versatility of v1.
v3 will focus on improved anatomy especially focusing on the hands. This will take time so please be patient.
FAQ
Comments (8)
Thank you for your time making this beautiful model and thank you for sharing and caring...
My Pleasure!
This is a great checkpoint, needs to be more popular!
I totally agree!
At last, finally an XL checkpoint capable of generating beautiful fashion models without big boobas.
Still one of my favorite checkpoints
Doll‑E XL v2.0 is one of those checkpoints that makes you feel like you’ve unlocked a whole new toolbox for creativity.
I’ve been testing it out, and the first thing that hits you is the versatility. This isn’t just locked into one style—it can swing from anime to near‑photographic realism, but where it really shines is in that sweet spot of 2.5D renders. Add “2.5D Render” to your prompt and suddenly your generations have this polished, game‑ready look with depth, lighting, and saturation that feels alive.
The creator clearly put a lot of thought into the merge. It’s a mix of RAMTHRUST’s Black Magic, DucHaiten’s AIart SDXL, and Yamer’s Realistic V5, and you can tell the fusion was done with care. The result is a checkpoint that feels balanced—no weird artifacts, no washed‑out colors. Instead, you get strong lighting effects, rich saturation, and crisp clarity. Compared to v1, v2 definitely feels like a step up in terms of vibrancy without losing flexibility.
Another thing I appreciate is how easy it is to use. You don’t need to overcomplicate your prompts or rely heavily on ADetailers. Even with basic setups, the outputs look clean, and if you upscale, faces hold up nicely. It’s the kind of model that makes experimenting fun because you don’t feel like you’re fighting the checkpoint—you’re just exploring what it can do.
And honestly, it feels like the creator is building toward something bigger. They’ve already teased v3 with a focus on anatomy (hands and feet especially), which shows they’re listening to feedback and refining things step by step. That kind of commitment makes me want to stick around and see how this evolves.
Bottom line: Doll‑E XL v2.0 is a must‑try if you love stylized realism with a fantasy edge. It’s versatile, vibrant, and reliable, and it makes your generations look like they belong in a polished artbook or a high‑end game concept. Definitely worth adding to your lineup if you want a checkpoint that delivers both style and substance.
still legendary