Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ
Text Generation • 27B • Updated • 12.8k • 52
Enda Rochford
RochyRoch
AI & ML interests
None yet
Recent Activity
new activity about 1 month ago
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ:Loading Failure on LM Studio 04.13 liked a model about 1 month ago
Ex0bit/Qwen3.6-27B-PRISM-PRO-DQ liked a Space 2 months ago
dream2589632147/Dream-wan2-2-faster-ProOrganizations
None yet
Loading Failure on LM Studio 04.13
5
#1 opened about 1 month ago
by RochyRoch
liked a
model about 1 month ago
liked a
Space 2 months ago
Steps and CFG changes?
#10 opened 4 months ago
by RochyRoch
liked a
model 5 months ago
commented on Ling-mini-2.0: Mini-Sized, Maximum Efficiency 5 months ago
An absolutely incredible experience with this model, the sheer speed alongside its massive data set. Hard not to be impressed and should quickly become a favourite for people who like talkative and fast models.
upvoted an article 5 months ago
Article
Ling-mini-2.0: Mini-Sized, Maximum Efficiency
RichardBian
• • 1 issue with the model's prompt template
1
#1 opened 12 months ago
by RochyRoch
New activity in SauRabM/llama-3-8b-Instruct-bnb-4bit-saurab-petitioner-respondent-final about 1 year ago
Great model
2
#1 opened over 1 year ago
by RochyRoch
The weirdest interactions with an LLM
7
#1 opened over 1 year ago
by RochyRoch
liked 4
models over 1 year ago
reacted to elismasilva's post with 🔥 over 1 year ago
Post
3738
Mixture-of-Diffusers pipeline tiling for SDXL
This strives to provide a better tool for image composition by using several diffusion processes in parallel, each configured with a specific prompt and settings, and focused on a particular region of the image. The mixture of diffusion processes is done in a way that harmonizes the generation process, preventing "seam" effects in the generated image. Using several diffusion processes in parallel has also practical advantages when generating very large images, as the GPU memory requirements are similar to that of generating an image of the size of a single tile.
elismasilva/mixture-of-diffusers-sdxl-tiling
This strives to provide a better tool for image composition by using several diffusion processes in parallel, each configured with a specific prompt and settings, and focused on a particular region of the image. The mixture of diffusion processes is done in a way that harmonizes the generation process, preventing "seam" effects in the generated image. Using several diffusion processes in parallel has also practical advantages when generating very large images, as the GPU memory requirements are similar to that of generating an image of the size of a single tile.
elismasilva/mixture-of-diffusers-sdxl-tiling
liked a
Space over 1 year ago
