Evgeniy Hristoforu

ehristoforu

AI & ML interests

Diffusers, LLM and others ML.

Recent Activity

updated a model 2 days ago
ehristoforu/SoRu-0009
updated a Space 2 days ago
ehristoforu/Qwen-7B-instruct
updated a Space 2 days ago
ehristoforu/Qwen-7B-instruct
View all activity

Organizations

video-p2p-library's profile picture Open-Source AI Meetup's profile picture lora concepts library's profile picture Tune a video concepts library's profile picture Stable Diffusion Dreambooth Concepts Library's profile picture Blog-explorers's profile picture OpenSky's profile picture DreamDrop AI's profile picture ZeroGPU Explorers's profile picture Project Fluently's profile picture test-org's profile picture Project Dreamly's profile picture ReLP's profile picture TensorMistral's profile picture TensorLlama's profile picture MLX Community's profile picture Theme repo for Gradio's profile picture GuardAI (GAI)'s profile picture Public League AI's profile picture Social Post Explorers's profile picture MiniSearch's profile picture Project Fluently LM's profile picture Dev Mode Explorers's profile picture Different LLM Sizes's profile picture Different LLM's profile picture ChatGPT Community (Unoffical, Non-profit)'s profile picture Stable Diffusion Community (Unofficial)'s profile picture Stable Diffusion Community (Unofficial, Non-profit)'s profile picture Synergetic AI's profile picture Diffusers Testing's profile picture LoRA Factory's profile picture Hugging Face Discord Community's profile picture Enhanced By Ehristoforu (EBE)'s profile picture LM Layers (Research)'s profile picture Fluently Lab.'s profile picture Puregen AI's profile picture

ehristoforu's activity

Reacted to their post with β€οΈπŸ‘€βž•πŸ§ πŸ€πŸ€―πŸ€—πŸš€πŸ‘πŸ˜ŽπŸ”₯ 4 months ago
view post
Post
3660
😏 Hello from Project Fluently Team!

✨ Finally we can give you some details about Supple Diffusion. We worked on it for a long time and we have little left, we apologize that we had to increase the work time.

πŸ› οΈ Some technical information. The first version will be the Small version (there will also be Medium, Large, Huge, possibly Tiny), it will be based on the SD1 architecture, that is, one text encoder, U-net, VAE. Now about each component, the first is a text encoder, it will be a CLIP model (perhaps not CLIP-L-path14), CLIP was specially retrained by us in order to achieve the universality of the model in understanding completely different styles and to simplify the prompt as much as possible. Next, we did U-net, U-net in a rather complicated way, first we trained different parts (types) of data with different U-nets, then we carried out merging using different methods, then we trained DPO and SPO using methods, and then we looked at the remaining shortcomings and further trained model, details will come later. We left VAE the same as in SD1 architecture.

πŸ™Œ Compatibility. Another goal of the Supple model series is full compatibility with Auto1111 and ComfyUI already at the release stage, the model is fully supported by these interfaces and the diffusers library and does not require adaptation, your usual Sampling methods are also compatible, such as DPM++ 2M Karras, DPM++ SDE and others.

🧐 Today, without demo images (there wasn’t much time), final work is underway on the model and we are already preparing to develop the Medium version, the release of the Small version will most likely be in mid-August or earlier.

😻 Feel free to ask your questions in the comments below the post, we will be happy to answer them, have a nice day!
  • 1 reply
Β·
posted an update 4 months ago
view post
Post
3660
😏 Hello from Project Fluently Team!

✨ Finally we can give you some details about Supple Diffusion. We worked on it for a long time and we have little left, we apologize that we had to increase the work time.

πŸ› οΈ Some technical information. The first version will be the Small version (there will also be Medium, Large, Huge, possibly Tiny), it will be based on the SD1 architecture, that is, one text encoder, U-net, VAE. Now about each component, the first is a text encoder, it will be a CLIP model (perhaps not CLIP-L-path14), CLIP was specially retrained by us in order to achieve the universality of the model in understanding completely different styles and to simplify the prompt as much as possible. Next, we did U-net, U-net in a rather complicated way, first we trained different parts (types) of data with different U-nets, then we carried out merging using different methods, then we trained DPO and SPO using methods, and then we looked at the remaining shortcomings and further trained model, details will come later. We left VAE the same as in SD1 architecture.

πŸ™Œ Compatibility. Another goal of the Supple model series is full compatibility with Auto1111 and ComfyUI already at the release stage, the model is fully supported by these interfaces and the diffusers library and does not require adaptation, your usual Sampling methods are also compatible, such as DPM++ 2M Karras, DPM++ SDE and others.

🧐 Today, without demo images (there wasn’t much time), final work is underway on the model and we are already preparing to develop the Medium version, the release of the Small version will most likely be in mid-August or earlier.

😻 Feel free to ask your questions in the comments below the post, we will be happy to answer them, have a nice day!
  • 1 reply
Β·
replied to their post 5 months ago
view reply

Detailed technical information will come later.

Reacted to their post with πŸ‘πŸ€—πŸ”₯πŸš€β€οΈ 5 months ago
view post
Post
6121
πŸ€— Hello from the Project Fluently team!

πŸ₯ We are ready to announce a new series of Supple Diffusion models, these are new generation diffusion models (about 1-2 weeks left before release).

🦾 The new series aims to take diffusion models to the next level, with performance and versatility as the main goal.

🧐 How will our models be better than others? Firstly, we worked on the CLIP models, now they understand your requests better, it will become easier to process. Secondly, we trained the models with high quality, even better than all our previous ones. Thirdly, you won’t have to keep 20 models on your disk; only 4-6 will be enough.

πŸ—ΊοΈ Roadmap:
1. Create Supple Diffusion Small
2. Creating Supple Diffusion Medium
3. Create Supple Diffusion Large

πŸŽ† Our models are universal for realism, and for cartoons, and for anime, and for caricatures.

πŸ’– The project really needs your support and your recommendations and reviews, please do not hesitate to write comments under this post, thank you!

πŸ–ΌοΈ Below are demo images made with the pre-release version of Supple Diffusion Small.
Β·
posted an update 5 months ago
view post
Post
6121
πŸ€— Hello from the Project Fluently team!

πŸ₯ We are ready to announce a new series of Supple Diffusion models, these are new generation diffusion models (about 1-2 weeks left before release).

🦾 The new series aims to take diffusion models to the next level, with performance and versatility as the main goal.

🧐 How will our models be better than others? Firstly, we worked on the CLIP models, now they understand your requests better, it will become easier to process. Secondly, we trained the models with high quality, even better than all our previous ones. Thirdly, you won’t have to keep 20 models on your disk; only 4-6 will be enough.

πŸ—ΊοΈ Roadmap:
1. Create Supple Diffusion Small
2. Creating Supple Diffusion Medium
3. Create Supple Diffusion Large

πŸŽ† Our models are universal for realism, and for cartoons, and for anime, and for caricatures.

πŸ’– The project really needs your support and your recommendations and reviews, please do not hesitate to write comments under this post, thank you!

πŸ–ΌοΈ Below are demo images made with the pre-release version of Supple Diffusion Small.
Β·
Reacted to their post with πŸš€ 6 months ago
view post
Post
3860
🦾 Hello, I present Visionix Alpha - a new hyper-realistic model based on SDXL. The main difference from all existing realism models is the attention to detail, that is, I improved not only hyperrealism, but also the overall aesthetics, anatomy, the beauty of nature, and more, and the model also has the most different faces. This model is suitable not only for realistic photos, but also for generating 2.5d anime, realistic cartoons and more.

πŸ€— Model on HF: ehristoforu/Visionix-alpha
πŸ₯ Model on CivitAI: https://civitai.com/models/505719
πŸͺ„ Playground (with base and inpaint model): ehristoforu/Visionix-Playground

✏️ Inpaint version on HF: ehristoforu/Visionix-alpha-inpainting
πŸ–‹οΈ Inpaint version on CivitAI: https://civitai.com/models/505719?modelVersionId=563519
  • 1 reply
Β·